How to Overclock Your GPU Safely (2026 Guide)

.
2. IMMEDIATELY:

As an Amazon Associate we earn from qualifying purchases. Prices and availability are accurate as of the date/time indicated and are subject to change.

3. ≥1250 words.
4.

/

with “overclock” / “GPU”. Cover, as clear steps: what GPU overclocking is + is it safe, tools (MSI Afterburner, GPU-Z), benchmark baseline (Heaven/Superposition/3DMark), raise power limit + temp limit, incrementally bump core clock then memory clock, test for stability/artifacts, find the crash point then back off, undervolting as an alternative for cooler/quieter, save profile, monitor temps. Include safety cautions.
5. Exactly ONE comparison

titled around recommended overclocking tools/monitoring — 5 rows, columns: Tool | Purpose | Free? | Rating (MSI Afterburner, GPU-Z, Unigine Heaven, 3DMark, HWiNFO). First row = the main tool (Afterburner).
6.

Frequently Asked Questions

with 4

Q

+

A

(is overclocking a GPU safe; how much performance does GPU overclocking give; is undervolting better than overclocking; will overclocking void my warranty).
7. Exactly 4 anchor internal links.
8. NO Amazon links/shortcodes/img. Prose + one table.
Output the HTML body as final message.
3b5396a0-6107-4a25-89ae-cce24338eabe
2026-07-12T10:58:30.128Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
3b5396a0-6107-4a25-89ae-cce24338eabe
ab9d1e77bfa57e6d2
hook_success
SubagentStart:general-purpose
55028cbe-cc2c-4678-814c-3b5e486385b7
SubagentStart

{“hookSpecificOutput”:{“hookEventName”:”SubagentStart”,”additionalContext”:”## Subagent: general-purpose\nID: ab9d1e77bfa57e6d2 | CWD: /Users/PRINCESS/White\n\n## Context\n- Plan: none\n- Reports: /Users/PRINCESS/White/plans/reports\n- Paths: /Users/PRINCESS/White/plans/ | /Users/PRINCESS/White/docs/\n\n## Rules\n- Reports → /Users/PRINCESS/White/plans/reports\n- YAGNI / KISS / DRY\n- Concise, list unresolved Qs at end\n- Python scripts in $HOME/.claude/skills/: Use `~/.claude/skills/.venv/bin/python3`\n- Never use global pip install\n\n## Naming\n- Report: /Users/PRINCESS/White/plans/reports/general-purpose-260712-1758-{slug}.md\n- Plan dir: /Users/PRINCESS/White/plans/260712-1758-{slug}/”}}

node “$HOME/.claude/hooks/subagent-init.cjs”
attachment
ded525a8-3609-4b9f-84cf-cc379541d317
2026-07-12T10:58:30.271Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
ded525a8-3609-4b9f-84cf-cc379541d317
ab9d1e77bfa57e6d2
hook_additional_context
## Subagent: general-purpose
ID: ab9d1e77bfa57e6d2 | CWD: /Users/PRINCESS/White

## Context
– Plan: none
– Reports: /Users/PRINCESS/White/plans/reports
– Paths: /Users/PRINCESS/White/plans/ | /Users/PRINCESS/White/docs/

## Rules
– Reports → /Users/PRINCESS/White/plans/reports
– YAGNI / KISS / DRY
– Concise, list unresolved Qs at end
– Python scripts in $HOME/.claude/skills/: Use `~/.claude/skills/.venv/bin/python3`
– Never use global pip install

## Naming
– Report: /Users/PRINCESS/White/plans/reports/general-purpose-260712-1758-{slug}.md
– Plan dir: /Users/PRINCESS/White/plans/260712-1758-{slug}/
SubagentStart
71d490ac-28cb-4436-83ca-7069dd75dc42
SubagentStart
attachment
ccd96f1f-8c5e-4e2f-b224-ccf10877e75d
2026-07-12T10:58:30.271Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
ccd96f1f-8c5e-4e2f-b224-ccf10877e75d
ab9d1e77bfa57e6d2
deferred_tools_delta
EnterWorktree
ExitWorktree
Monitor
NotebookEdit
SendMessage
TaskStop
WebFetch
WebSearch
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__apply_sensitive_message_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__apply_sensitive_thread_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__create_draft
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__create_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__get_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__get_thread
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__label_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__label_thread
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__list_drafts
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__list_labels
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__search_threads
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__unlabel_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__unlabel_thread
mcp__ccd_directory__request_directory
mcp__ccd_session_mgmt__archive_session
mcp__ccd_session_mgmt__get_session
mcp__ccd_session_mgmt__list_events
mcp__ccd_session_mgmt__list_sessions
mcp__ccd_session_mgmt__search_session_transcripts
mcp__ccd_session_mgmt__send_message
mcp__ccd_session_mgmt__set_session_title
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__copy_file
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__create_file
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__download_file_content
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__get_file_metadata
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__get_file_permissions
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__list_recent_files
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__read_file_content
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__search_files
mcp__claude-in-chrome__browser_batch
mcp__claude-in-chrome__computer
mcp__claude-in-chrome__file_upload
mcp__claude-in-chrome__find
mcp__claude-in-chrome__form_input
mcp__claude-in-chrome__get_page_text
mcp__claude-in-chrome__gif_creator
mcp__claude-in-chrome__javascript_tool
mcp__claude-in-chrome__list_connected_browsers
mcp__claude-in-chrome__navigate
mcp__claude-in-chrome__read_console_messages
mcp__claude-in-chrome__read_network_requests
mcp__claude-in-chrome__read_page
mcp__claude-in-chrome__resize_window
mcp__claude-in-chrome__select_browser
mcp__claude-in-chrome__shortcuts_execute
mcp__claude-in-chrome__shortcuts_list
mcp__claude-in-chrome__switch_browser
mcp__claude-in-chrome__tabs_close_mcp
mcp__claude-in-chrome__tabs_context_mcp
mcp__claude-in-chrome__tabs_create_mcp
mcp__claude-in-chrome__upload_image
mcp__computer-use__computer_batch
mcp__computer-use__cursor_position
mcp__computer-use__double_click
mcp__computer-use__hold_key
mcp__computer-use__key
mcp__computer-use__left_click
mcp__computer-use__left_click_drag
mcp__computer-use__left_mouse_down
mcp__computer-use__left_mouse_up
mcp__computer-use__list_granted_applications
mcp__computer-use__middle_click
mcp__computer-use__mouse_move
mcp__computer-use__open_application
mcp__computer-use__read_clipboard
mcp__computer-use__request_access
mcp__computer-use__request_teach_access
mcp__computer-use__right_click
mcp__computer-use__screenshot
mcp__computer-use__scroll
mcp__computer-use__switch_display
mcp__computer-use__teach_batch
mcp__computer-use__teach_step
mcp__computer-use__triple_click
mcp__computer-use__type
mcp__computer-use__wait
mcp__computer-use__write_clipboard
mcp__computer-use__zoom
mcp__mcp-registry__list_connectors
mcp__mcp-registry__search_mcp_registry
mcp__mcp-registry__suggest_connectors
mcp__plugin_bio-research_biorxiv__get_categories
mcp__plugin_bio-research_biorxiv__get_content_statistics
mcp__plugin_bio-research_biorxiv__get_preprint
mcp__plugin_bio-research_biorxiv__get_usage_statistics
mcp__plugin_bio-research_biorxiv__search_by_funder
mcp__plugin_bio-research_biorxiv__search_preprints
mcp__plugin_bio-research_biorxiv__search_published_preprints
mcp__plugin_bio-research_c-trials__analyze_endpoints
mcp__plugin_bio-research_c-trials__get_trial_details
mcp__plugin_bio-research_c-trials__search_by_eligibility
mcp__plugin_bio-research_c-trials__search_by_sponsor
mcp__plugin_bio-research_c-trials__search_investigators
mcp__plugin_bio-research_c-trials__search_trials
mcp__plugin_bio-research_chembl__compound_search
mcp__plugin_bio-research_chembl__drug_search
mcp__plugin_bio-research_chembl__get_admet
mcp__plugin_bio-research_chembl__get_bioactivity
mcp__plugin_bio-research_chembl__get_mechanism
mcp__plugin_bio-research_chembl__target_search
mcp__plugin_bio-research_consensus__search
mcp__plugin_bio-research_ot__batch_query_open_targets_graphql
mcp__plugin_bio-research_ot__get_open_targets_graphql_schema
mcp__plugin_bio-research_ot__get_type_dependencies
mcp__plugin_bio-research_ot__query_open_targets_graphql
mcp__plugin_bio-research_ot__search_entities
mcp__plugin_bio-research_pubmed__convert_article_ids
mcp__plugin_bio-research_pubmed__find_related_articles
mcp__plugin_bio-research_pubmed__get_article_metadata
mcp__plugin_bio-research_pubmed__get_copyright_status
mcp__plugin_bio-research_pubmed__get_full_text_article
mcp__plugin_bio-research_pubmed__lookup_article_by_citation
mcp__plugin_bio-research_pubmed__search_articles
mcp__plugin_pdf-viewer_pdf__display_pdf
mcp__plugin_pdf-viewer_pdf__interact
mcp__plugin_pdf-viewer_pdf__list_pdfs
mcp__plugin_pdf-viewer_pdf__poll_pdf_commands
mcp__plugin_pdf-viewer_pdf__read_pdf_bytes
mcp__plugin_pdf-viewer_pdf__save_pdf
mcp__plugin_pdf-viewer_pdf__submit_page_data
mcp__plugin_pdf-viewer_pdf__submit_save_data
mcp__plugin_pdf-viewer_pdf__submit_viewer_state
mcp__plugin_twilio-developer-kit_twilio-docs__twilio__retrieve
mcp__plugin_twilio-developer-kit_twilio-docs__twilio__search
mcp__scheduled-tasks__create_scheduled_task
mcp__scheduled-tasks__delete_scheduled_task
mcp__scheduled-tasks__list_scheduled_tasks
mcp__scheduled-tasks__update_scheduled_task
EnterWorktree
ExitWorktree
Monitor
NotebookEdit
SendMessage
TaskStop
WebFetch
WebSearch
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__apply_sensitive_message_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__apply_sensitive_thread_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__create_draft
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__create_label
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__get_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__get_thread
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__label_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__label_thread
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__list_drafts
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__list_labels
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__search_threads
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__unlabel_message
mcp__b5d9bd54-34c4-4239-b2ae-7d0b6e559005__unlabel_thread
mcp__ccd_directory__request_directory
mcp__ccd_session_mgmt__archive_session
mcp__ccd_session_mgmt__get_session
mcp__ccd_session_mgmt__list_events
mcp__ccd_session_mgmt__list_sessions
mcp__ccd_session_mgmt__search_session_transcripts
mcp__ccd_session_mgmt__send_message
mcp__ccd_session_mgmt__set_session_title
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__copy_file
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__create_file
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__download_file_content
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__get_file_metadata
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__get_file_permissions
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__list_recent_files
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__read_file_content
mcp__cec217c8-cfe9-41cc-9b94-b24aa01ce3dd__search_files
mcp__claude-in-chrome__browser_batch
mcp__claude-in-chrome__computer
mcp__claude-in-chrome__file_upload
mcp__claude-in-chrome__find
mcp__claude-in-chrome__form_input
mcp__claude-in-chrome__get_page_text
mcp__claude-in-chrome__gif_creator
mcp__claude-in-chrome__javascript_tool
mcp__claude-in-chrome__list_connected_browsers
mcp__claude-in-chrome__navigate
mcp__claude-in-chrome__read_console_messages
mcp__claude-in-chrome__read_network_requests
mcp__claude-in-chrome__read_page
mcp__claude-in-chrome__resize_window
mcp__claude-in-chrome__select_browser
mcp__claude-in-chrome__shortcuts_execute
mcp__claude-in-chrome__shortcuts_list
mcp__claude-in-chrome__switch_browser
mcp__claude-in-chrome__tabs_close_mcp
mcp__claude-in-chrome__tabs_context_mcp
mcp__claude-in-chrome__tabs_create_mcp
mcp__claude-in-chrome__upload_image
mcp__computer-use__computer_batch
mcp__computer-use__cursor_position
mcp__computer-use__double_click
mcp__computer-use__hold_key
mcp__computer-use__key
mcp__computer-use__left_click
mcp__computer-use__left_click_drag
mcp__computer-use__left_mouse_down
mcp__computer-use__left_mouse_up
mcp__computer-use__list_granted_applications
mcp__computer-use__middle_click
mcp__computer-use__mouse_move
mcp__computer-use__open_application
mcp__computer-use__read_clipboard
mcp__computer-use__request_access
mcp__computer-use__request_teach_access
mcp__computer-use__right_click
mcp__computer-use__screenshot
mcp__computer-use__scroll
mcp__computer-use__switch_display
mcp__computer-use__teach_batch
mcp__computer-use__teach_step
mcp__computer-use__triple_click
mcp__computer-use__type
mcp__computer-use__wait
mcp__computer-use__write_clipboard
mcp__computer-use__zoom
mcp__mcp-registry__list_connectors
mcp__mcp-registry__search_mcp_registry
mcp__mcp-registry__suggest_connectors
mcp__plugin_bio-research_biorxiv__get_categories
mcp__plugin_bio-research_biorxiv__get_content_statistics
mcp__plugin_bio-research_biorxiv__get_preprint
mcp__plugin_bio-research_biorxiv__get_usage_statistics
mcp__plugin_bio-research_biorxiv__search_by_funder
mcp__plugin_bio-research_biorxiv__search_preprints
mcp__plugin_bio-research_biorxiv__search_published_preprints
mcp__plugin_bio-research_c-trials__analyze_endpoints
mcp__plugin_bio-research_c-trials__get_trial_details
mcp__plugin_bio-research_c-trials__search_by_eligibility
mcp__plugin_bio-research_c-trials__search_by_sponsor
mcp__plugin_bio-research_c-trials__search_investigators
mcp__plugin_bio-research_c-trials__search_trials
mcp__plugin_bio-research_chembl__compound_search
mcp__plugin_bio-research_chembl__drug_search
mcp__plugin_bio-research_chembl__get_admet
mcp__plugin_bio-research_chembl__get_bioactivity
mcp__plugin_bio-research_chembl__get_mechanism
mcp__plugin_bio-research_chembl__target_search
mcp__plugin_bio-research_consensus__search
mcp__plugin_bio-research_ot__batch_query_open_targets_graphql
mcp__plugin_bio-research_ot__get_open_targets_graphql_schema
mcp__plugin_bio-research_ot__get_type_dependencies
mcp__plugin_bio-research_ot__query_open_targets_graphql
mcp__plugin_bio-research_ot__search_entities
mcp__plugin_bio-research_pubmed__convert_article_ids
mcp__plugin_bio-research_pubmed__find_related_articles
mcp__plugin_bio-research_pubmed__get_article_metadata
mcp__plugin_bio-research_pubmed__get_copyright_status
mcp__plugin_bio-research_pubmed__get_full_text_article
mcp__plugin_bio-research_pubmed__lookup_article_by_citation
mcp__plugin_bio-research_pubmed__search_articles
mcp__plugin_pdf-viewer_pdf__display_pdf
mcp__plugin_pdf-viewer_pdf__interact
mcp__plugin_pdf-viewer_pdf__list_pdfs
mcp__plugin_pdf-viewer_pdf__poll_pdf_commands
mcp__plugin_pdf-viewer_pdf__read_pdf_bytes
mcp__plugin_pdf-viewer_pdf__save_pdf
mcp__plugin_pdf-viewer_pdf__submit_page_data
mcp__plugin_pdf-viewer_pdf__submit_save_data
mcp__plugin_pdf-viewer_pdf__submit_viewer_state
mcp__plugin_twilio-developer-kit_twilio-docs__twilio__retrieve
mcp__plugin_twilio-developer-kit_twilio-docs__twilio__search
mcp__scheduled-tasks__create_scheduled_task
mcp__scheduled-tasks__delete_scheduled_task
mcp__scheduled-tasks__list_scheduled_tasks
mcp__scheduled-tasks__update_scheduled_task
attachment
ba15f4f6-03d5-4f42-96f4-bfd5345cae58
2026-07-12T10:58:30.272Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
ba15f4f6-03d5-4f42-96f4-bfd5345cae58
ab9d1e77bfa57e6d2
skill_listing
– agent-browser: AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
– ai-artist: Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use –skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.
– ai-multimodal: Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4, Nano Banana 2, MiniMax), videos (Veo 3, Hailuo), speech (MiniMax TTS), music (MiniMax). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.
– ask: Answer technical and architectural questions with expert analysis. Use for design decisions, best practices evaluation, solution comparison.
– backend-development: Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
– better-auth: Add authentication with Better Auth (TypeScript). Use for email/password, OAuth providers (Google, GitHub), 2FA/MFA, passkeys/WebAuthn, sessions, RBAC, rate limiting.
– bootstrap: Bootstrap new projects with research, tech stack, design, planning, and implementation. Modes: full (interactive), auto (default), fast (skip research), parallel (multi-agent).
– brainstorm: Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
– chrome-devtools: Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.
– ck-autoresearch: Run autonomous optimization loops (deprecated alias for ck-loop). Use for metric-driven iteration, coverage improvement, performance tuning.
– ck-debug: Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, system investigation.
– ck-loop: Autonomous iterative optimization loop — run N iterations against a mechanical metric, learn from git history, auto-keep/discard changes. Use for improving measurable metrics (coverage, performance, bundle size, etc.) through repeated experimentation.
– ck-plan: Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation strategy, phase documentation.
– ck-predict: 5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
– ck-scenario: Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.
– ck-security: STRIDE + OWASP-based security audit with optional auto-fix. Scans code for vulnerabilities, categorizes by severity, and can iteratively fix findings using ck:autoresearch pattern.
– code-review: Review code quality with adversarial rigor. Supports input modes: pending changes, PR number, commit hash, codebase scan. Always-on red-team analysis finds security holes, false assumptions, and failure modes.
– coding-level: Set coding experience level for tailored output. Use for adjusting explanation depth, code complexity, and response format to user expertise.
– context-engineering: Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
– cook: Implement features, plans, and fixes with structured workflow. Use for feature development, plan execution, code implementation pipelines.
– copywriting: Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.
– databases: Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.
– deploy: Deploy projects to any platform with auto-detection. Use when user says “deploy”, “publish”, “ship”, “go live”, “push to production”, “host this app”, or mentions any hosting platform (Vercel, Netlify, Cloudflare, Railway, Fly.io, Render, Heroku, TOSE, Github Pages, AWS, GCP, Digital Ocean, Vultr, Coolify, Dokploy). Auto-detects deployment target from config files and docs/deployment.md.
– design: Design brand identity, logos, banners, and visual assets. Use for brand systems, design tokens, corporate identity programs. Not for UI code patterns.
– devops: Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.
– docs: Analyze codebase and manage project documentation. Use for doc initialization, updates, summaries, codebase analysis.
– docs-seeker: Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
– excalidraw: Create Excalidraw diagrams — architecture, data flow, workflows, system design. Use when user wants to visualize, diagram, draw architecture, show data flow, create flowcharts, map components, or export .excalidraw files to PNG/SVG. Supports two modes: live MCP canvas (real-time) or file-based JSON + Playwright rendering. Also supports zero-config codebase auto-diagramming — just say “diagram this repo” or “visualize the architecture”.
– find-skills: Helps users discover and install agent skills when they ask questions like “how do I do X”, “find a skill for X”, “is there a skill that can…”, or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
– fix: Fix bugs, errors, test failures, and CI/CD issues with intelligent routing. Use for type errors, lint issues, log errors, UI bugs, code problems.
– frontend-design: Create polished frontend interfaces from designs/screenshots/videos. Use for web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop.
– frontend-development: Build React/TypeScript frontends with modern patterns. Use for components, Suspense, lazy loading, useSuspenseQuery, MUI v7 styling, TanStack Router, performance optimization.
– git: Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.
– gkg: Semantic code analysis with GitLab Knowledge Graph. Use for go-to-definition, find-usages, impact analysis, architecture visualization. Supports Ruby, Java, Kotlin, Python, TypeScript/JavaScript.
– google-adk-python: Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.
– graphify: Build queryable knowledge graphs from code, docs, papers, and images. Use for codebase understanding, architecture analysis, cross-file relationship discovery, token-efficient navigation.
– journal: Write technical journal entries analyzing recent changes. Use for session reflections, change analysis, decision documentation.
– kanban: Orchestrate AI agent tasks on a visual board. Use for multi-agent coordination, task tracking, team workflows. Not for plan files (use plans-kanban).
– llms: Generate llms.txt files from docs or codebase scanning. Follows llmstxt.org spec. Use for LLM-friendly site indexes, documentation summaries, AI context optimization.
– markdown-novel-viewer: View markdown files with calm, book-like reading experience via HTTP server. Use for long-form content, documentation preview, novel reading, report viewing, distraction-free reading.
– mcp-builder: Build MCP servers for LLM-external service integration. Use for FastMCP (Python), MCP SDK (Node/TypeScript), tool design, API integration, resource providers.
– mcp-management: Manage MCP servers – discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.
– media-processing: Process media with FFmpeg (video/audio), ImageMagick (images), RMBG (AI background removal). Use for encoding, format conversion, filters, thumbnails, batch processing, HLS/DASH streaming.
– mermaidjs-v11: Create diagrams with Mermaid.js v11 syntax. Use for flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, state diagrams, architecture diagrams, timelines, user journeys.
– mintlify: Build and deploy documentation sites with Mintlify. Use when creating API docs, developer portals, or knowledge bases. Covers docs.json configuration, MDX components (Cards, Steps, Tabs, Accordions, CodeGroup, Callouts, Mermaid, View, Tiles, Tree, Badge, Banner, Color, Tooltips, Panel), page frontmatter, navigation structure (tabs, anchors, dropdowns, products, versions, languages), theming (7 themes), OpenAPI/AsyncAPI integration, AI features (llms.txt, MCP, skill.md), deployment (GitHub, GitLab, Vercel, Cloudflare, AWS), and CLI commands for local development and validation.
– mobile-development: Build mobile apps with React Native, Flutter, Swift/SwiftUI, Kotlin/Jetpack Compose. Use for iOS/Android, mobile UX, performance optimization, offline-first, app store deployment.
– payment-integration: Integrate payments with SePay (VietQR), Polar, Stripe, Paddle (MoR subscriptions), Creem.io (licensing). Checkout, webhooks, subscriptions, QR codes, multi-provider orders.
– plans-kanban: View plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status overview, phase progress, milestone tracking, project visibility.
– preview: View files or generate visual explanations, slides, and diagrams. Use for code walkthroughs, architecture visualization, HTML/Markdown presentations.
– problem-solving: Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
– project-management: Track progress, update plan statuses, manage Claude Tasks, generate reports, coordinate docs updates. Use for project oversight, status checks, plan completion, task hydration, cross-session continuity.
– project-organization: Organize files, directories, and content structure in any project. Use when creating files, determining output paths, organizing existing assets, or standardizing project layout.
– react-best-practices
– remotion
– repomix
– research
– retro
– scout
– security-scan: Scan codebase for security vulnerabilities, hardcoded secrets, dependency issues, and OWASP patterns. Use when asked to ‘security scan’, ‘check for secrets’, ‘audit security’, or before major releases.
– sequential-thinking
– shader
– ship
– shopify
– show-off
– skill-creator
– stitch
– tanstack
– team
– template-skill
– test
– threejs
– ui-styling
– ui-ux-pro-max: UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
– use-mcp
– watzup
– web-design-guidelines: Review UI code for Web Interface Guidelines compliance. Use when asked to “review my UI”, “check accessibility”, “audit design”, “review UX”, or “check my site against best practices”.
– web-frameworks
– web-testing
– worktree
– xia
– deep-research: Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. – When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., “what car to buy” without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.
– pdf-viewer:annotate
– pdf-viewer:fill-form
– pdf-viewer:open
– pdf-viewer:sign
– common-room:generate-account-plan
– common-room:weekly-brief
– brand-voice:discover-brand
– brand-voice:enforce-voice
– brand-voice:generate-guidelines
– product-management:brainstorm
– slack-by-salesforce:channel-digest
– slack-by-salesforce:draft-announcement
– slack-by-salesforce:find-discussions
– slack-by-salesforce:standup
– slack-by-salesforce:summarize-channel
– pdf-viewer:view-pdf
– legal:brief
– legal:compliance-check
– legal:legal-response
– legal:legal-risk-assessment
– legal:meeting-briefing
– legal:review-contract
– legal:signature-request
– legal:triage-nda
– legal:vendor-check
– productivity:memory-management
– productivity:start
– productivity:task-management
– productivity:update
– customer-support:customer-escalation
– customer-support:customer-research
– customer-support:draft-response
– customer-support:kb-article
– customer-support:ticket-triage
– twilio-developer-kit:twilio-account-setup
– twilio-developer-kit:twilio-agent-augmentation-architect
– twilio-developer-kit:twilio-agent-connect
– twilio-developer-kit:twilio-ai-agent-architect
– twilio-developer-kit:twilio-call-recordings
– twilio-developer-kit:twilio-cli-reference
– twilio-developer-kit:twilio-compliance-onboarding
– twilio-developer-kit:twilio-compliance-traffic
– twilio-developer-kit:twilio-conference-calls
– twilio-developer-kit:twilio-content-template-builder
– twilio-developer-kit:twilio-conversation-intelligence
– twilio-developer-kit:twilio-conversation-memory
– twilio-developer-kit:twilio-conversation-orchestrator
– twilio-developer-kit:twilio-conversations-classic-api
– twilio-developer-kit:twilio-customer-support-architect
– twilio-developer-kit:twilio-debugging-observability
– twilio-developer-kit:twilio-email-deliverability-advisor
– twilio-developer-kit:twilio-email-send
– twilio-developer-kit:twilio-enterprise-knowledge
– twilio-developer-kit:twilio-iam-auth-setup
– twilio-developer-kit:twilio-identity-verification-advisor
– twilio-developer-kit:twilio-lookup-phone-intelligence
– twilio-developer-kit:twilio-marketing-promotions-advisor
– twilio-developer-kit:twilio-messaging-channel-advisor
– twilio-developer-kit:twilio-messaging-overview
– twilio-developer-kit:twilio-messaging-services
– twilio-developer-kit:twilio-messaging-webhooks
– twilio-developer-kit:twilio-notifications-alerts-advisor
– twilio-developer-kit:twilio-numbers-senders
– twilio-developer-kit:twilio-organizations-setup
– twilio-developer-kit:twilio-rcs-messaging
– twilio-developer-kit:twilio-regulatory-compliance-bundles
– twilio-developer-kit:twilio-reliability-patterns
– twilio-developer-kit:twilio-security-api-auth
– twilio-developer-kit:twilio-security-compliance-hipaa
– twilio-developer-kit:twilio-security-hardening
– twilio-developer-kit:twilio-send-message
– twilio-developer-kit:twilio-sms-isv-setup
– twilio-developer-kit:twilio-sms-send-message
– twilio-developer-kit:twilio-studio-flows
– twilio-developer-kit:twilio-taskrouter-routing
– twilio-developer-kit:twilio-verify-send-otp
– twilio-developer-kit:twilio-voice-conversation-relay
– twilio-developer-kit:twilio-voice-outbound-calls
– twilio-developer-kit:twilio-voice-twiml
– twilio-developer-kit:twilio-webhook-architecture
– twilio-developer-kit:twilio-whatsapp-manage-senders
– twilio-developer-kit:twilio-whatsapp-send-message
– twilio-developer-kit:twilio-sendgrid-account-setup
– twilio-developer-kit:twilio-sendgrid-deliverability-advisor
– twilio-developer-kit:twilio-sendgrid-email-send
– twilio-developer-kit:twilio-sendgrid-email-settings
– twilio-developer-kit:twilio-sendgrid-engagement-quality
– twilio-developer-kit:twilio-sendgrid-inbound-parse
– twilio-developer-kit:twilio-sendgrid-suppressions
– twilio-developer-kit:twilio-sendgrid-webhooks
– common-room:account-research
– common-room:call-prep
– common-room:compose-outreach
– common-room:contact-research
– common-room:prospect
– common-room:weekly-prep-brief
– brand-voice:brand-voice-enforcement
– brand-voice:discover-brand
– brand-voice:guideline-generation
– operations:capacity-plan
– operations:change-request
– operations:compliance-tracking
– operations:process-doc
– operations:process-optimization
– operations:risk-assessment
– operations:runbook
– operations:status-report
– operations:vendor-review
– product-management:competitive-brief
– product-management:metrics-review
– product-management:product-brainstorming
– product-management:roadmap-update
– product-management:sprint-planning
– product-management:stakeholder-update
– product-management:synthesize-research
– product-management:write-spec
– human-resources:comp-analysis
– human-resources:draft-offer
– human-resources:interview-prep
– human-resources:onboarding
– human-resources:org-planning
– human-resources:people-report
– human-resources:performance-review
– human-resources:policy-lookup
– human-resources:recruiting-pipeline
– slack-by-salesforce:slack-messaging
– slack-by-salesforce:slack-search
– bio-research:instrument-data-to-allotrope
– bio-research:nextflow-development
– bio-research:scientific-problem-selection
– bio-research:scvi-tools
– bio-research:single-cell-rna-qc
– bio-research:start
– marketing:brand-review
– marketing:campaign-plan
– marketing:competitive-brief
– marketing:content-creation
– marketing:draft-content
– marketing:email-sequence
– marketing:performance-report
– marketing:seo-audit
– engineering:architecture
– engineering:code-review
– engineering:debug
– engineering:deploy-checklist
– engineering:documentation
– engineering:incident-response
– engineering:standup
– engineering:system-design
– engineering:tech-debt
– engineering:testing-strategy
– cockroachdb:benchmarking-transaction-patterns
– cockroachdb:designing-application-transactions
– cockroachdb:designing-multi-region-applications
– cockroachdb:analyzing-range-distribution
– cockroachdb:analyzing-schema-change-storage-risk
– cockroachdb:auditing-table-statistics
– cockroachdb:monitoring-background-jobs
– cockroachdb:profiling-statement-fingerprints
– cockroachdb:profiling-transaction-fingerprints
– cockroachdb:triaging-live-sql-activity
– cockroachdb:molt-fetch
– cockroachdb:molt-replicator
– cockroachdb:molt-verify
– cockroachdb:setting-up-local-cluster
– cockroachdb:managing-certificates-and-encryption
– cockroachdb:managing-cluster-capacity
– cockroachdb:managing-cluster-settings
– cockroachdb:performing-cluster-maintenance
– cockroachdb:provisioning-cluster-for-production
– cockroachdb:reviewing-cluster-health
– cockroachdb:upgrading-cluster-version
– cockroachdb:cockroachdb-sql
– cockroachdb:auditing-cloud-cluster-security
– cockroachdb:configuring-audit-logging
– cockroachdb:configuring-ip-allowlists
– cockroachdb:configuring-log-export
– cockroachdb:configuring-private-connectivity
– cockroachdb:configuring-sso-and-scim
– cockroachdb:enabling-cmek-encryption
– cockroachdb:enforcing-password-policies
– cockroachdb:hardening-user-privileges
– cockroachdb:managing-tls-certificates
– cockroachdb:preparing-compliance-documentation
– finance:audit-support
– finance:close-management
– finance:financial-statements
– finance:journal-entry
– finance:journal-entry-prep
– finance:reconciliation
– finance:sox-testing
– finance:variance-analysis
– apollo:enrich-lead
– apollo:prospect
– apollo:sequence-load
– zoom-plugin:build-zoom-bot
– zoom-plugin:build-zoom-meeting-app
– zoom-plugin:choose-zoom-approach
– zoom-plugin:cobrowse-sdk
– zoom-plugin:contact-center
– zoom-plugin:debug-zoom
– zoom-plugin:debug-zoom-integration
– zoom-plugin:design-mcp-workflow
– zoom-plugin:general
– zoom-plugin:meeting-sdk
– zoom-plugin:oauth
– zoom-plugin:phone
– zoom-plugin:plan-zoom-integration
– zoom-plugin:plan-zoom-product
– zoom-plugin:probe-sdk
– zoom-plugin:rest-api
– zoom-plugin:rivet-sdk
– zoom-plugin:rtms
– zoom-plugin:scribe
– zoom-plugin:setup-zoom-mcp
– zoom-plugin:setup-zoom-oauth
– zoom-plugin:start
– zoom-plugin:team-chat
– zoom-plugin:ui-toolkit
– zoom-plugin:video-sdk
– zoom-plugin:virtual-agent
– zoom-plugin:webhooks
– zoom-plugin:websockets
– zoom-plugin:zoom-apps-sdk
– zoom-plugin:zoom-mcp
– sales:account-research
– sales:call-prep
– sales:call-summary
– sales:competitive-intelligence
– sales:create-an-asset
– sales:daily-briefing
– sales:draft-outreach
– sales:forecast
– sales:pipeline-review
– data:analyze
– data:build-dashboard
– data:create-viz
– data:data-context-extractor
– data:data-visualization
– data:explore-data
– data:sql-queries
– data:statistical-analysis
– data:validate-data
– data:write-query
– enterprise-search:digest
– enterprise-search:knowledge-synthesis
– enterprise-search:search
– enterprise-search:search-strategy
– enterprise-search:source-management
– design:accessibility-review
– design:design-critique
– design:design-handoff
– design:design-system
– design:research-synthesis
– design:user-research
– design:ux-copy
– anthropic-skills:consolidate-memory
– anthropic-skills:docx: Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of ‘Word doc’, ‘word document’, ‘.docx’, ‘.dotx’, or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a ‘report’, ‘memo’, ‘letter’, ‘template’, or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
– anthropic-skills:pdf: Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
– anthropic-skills:pptx
– anthropic-skills:schedule
– anthropic-skills:setup-cowork
– anthropic-skills:skill-creator
– anthropic-skills:xlsx: Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like “the xlsx in my downloads”) — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
– dataviz: Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file’s values for your brand’s. Triggers on: “chart”, “graph”, “plot”, “data viz”, “visualization”, “dashboard”, “analytics”, “visualize data”, “categorical colors”, “sequential / diverging palette”, “stat tile”, “sparkline”, “heatmap”, “legend”, “axis”, “tooltip”, “chart colors”, “color by series”.
– artifact-design: Design guidance and fundamentals for Artifacts.
– update-config: Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (“from now on when X”, “each time X”, “whenever X”, “before/after X”) require hooks configured in settings.json – the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (“allow X”, “add permission”, “move permission to”), env vars (“set X=Y”), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: “allow npm commands”, “add bq permission to global settings”, “move permission to user settings”, “set DEBUG=true”, “when claude stops show X”. For simple settings like theme/model, suggest the /config command.
– keybindings-help: Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json. Examples: “rebind ctrl+s”, “add a chord shortcut”, “change the submit key”, “customize keybindings”.
– verify: Verify that a code change actually does what it’s supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo’s project verify skill if none exists yet. Don’t invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there’s nothing to observe.
– simplify: Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.
– fewer-permission-prompts: Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
– loop: Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace. – When the user wants to set up a recurring task, poll for status, or run something repeatedly on an interval (e.g. “check the deploy every 5 minutes”, “keep running /babysit-prs”). Do NOT invoke for one-off tasks.
– schedule: Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule. – When the user wants to schedule a recurring cloud agent, set up automated tasks, create a cron job for Claude Code, or manage their scheduled agents/routines. Also use when the user wants a one-time scheduled run (“run this once at 3pm”, “remind me to check X tomorrow”).
– claude-api: Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
TRIGGER — read BEFORE opening the target file; don’t skip because it “looks like a one-liner” — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).
SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE ‘openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama’` over the project hits (run this grep FIRST if no provider named — don’t Read the file).
– run: Launch and drive this project’s app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).
– init
– review
– security-review
agent-browser
ai-artist
ai-multimodal
ask
backend-development
better-auth
bootstrap
brainstorm
chrome-devtools
ck-autoresearch
ck-debug
ck-loop
ck-plan
ck-predict
ck-scenario
ck-security
code-review
coding-level
context-engineering
cook
copywriting
databases
deploy
design
devops
docs
docs-seeker
excalidraw
find-skills
fix
frontend-design
frontend-development
git
gkg
google-adk-python
graphify
journal
kanban
llms
markdown-novel-viewer
mcp-builder
mcp-management
media-processing
mermaidjs-v11
mintlify
mobile-development
payment-integration
plans-kanban
preview
problem-solving
project-management
project-organization
react-best-practices
remotion
repomix
research
retro
scout
security-scan
sequential-thinking
shader
ship
shopify
show-off
skill-creator
stitch
tanstack
team
template-skill
test
threejs
ui-styling
ui-ux-pro-max
use-mcp
watzup
web-design-guidelines
web-frameworks
web-testing
worktree
xia
deep-research
pdf-viewer:annotate
pdf-viewer:fill-form
pdf-viewer:open
pdf-viewer:sign
common-room:generate-account-plan
common-room:weekly-brief
brand-voice:discover-brand
brand-voice:enforce-voice
brand-voice:generate-guidelines
product-management:brainstorm
slack-by-salesforce:channel-digest
slack-by-salesforce:draft-announcement
slack-by-salesforce:find-discussions
slack-by-salesforce:standup
slack-by-salesforce:summarize-channel
pdf-viewer:view-pdf
legal:brief
legal:compliance-check
legal:legal-response
legal:legal-risk-assessment
legal:meeting-briefing
legal:review-contract
legal:signature-request
legal:triage-nda
legal:vendor-check
productivity:memory-management
productivity:start
productivity:task-management
productivity:update
customer-support:customer-escalation
customer-support:customer-research
customer-support:draft-response
customer-support:kb-article
customer-support:ticket-triage
twilio-developer-kit:twilio-account-setup
twilio-developer-kit:twilio-agent-augmentation-architect
twilio-developer-kit:twilio-agent-connect
twilio-developer-kit:twilio-ai-agent-architect
twilio-developer-kit:twilio-call-recordings
twilio-developer-kit:twilio-cli-reference
twilio-developer-kit:twilio-compliance-onboarding
twilio-developer-kit:twilio-compliance-traffic
twilio-developer-kit:twilio-conference-calls
twilio-developer-kit:twilio-content-template-builder
twilio-developer-kit:twilio-conversation-intelligence
twilio-developer-kit:twilio-conversation-memory
twilio-developer-kit:twilio-conversation-orchestrator
twilio-developer-kit:twilio-conversations-classic-api
twilio-developer-kit:twilio-customer-support-architect
twilio-developer-kit:twilio-debugging-observability
twilio-developer-kit:twilio-email-deliverability-advisor
twilio-developer-kit:twilio-email-send
twilio-developer-kit:twilio-enterprise-knowledge
twilio-developer-kit:twilio-iam-auth-setup
twilio-developer-kit:twilio-identity-verification-advisor
twilio-developer-kit:twilio-lookup-phone-intelligence
twilio-developer-kit:twilio-marketing-promotions-advisor
twilio-developer-kit:twilio-messaging-channel-advisor
twilio-developer-kit:twilio-messaging-overview
twilio-developer-kit:twilio-messaging-services
twilio-developer-kit:twilio-messaging-webhooks
twilio-developer-kit:twilio-notifications-alerts-advisor
twilio-developer-kit:twilio-numbers-senders
twilio-developer-kit:twilio-organizations-setup
twilio-developer-kit:twilio-rcs-messaging
twilio-developer-kit:twilio-regulatory-compliance-bundles
twilio-developer-kit:twilio-reliability-patterns
twilio-developer-kit:twilio-security-api-auth
twilio-developer-kit:twilio-security-compliance-hipaa
twilio-developer-kit:twilio-security-hardening
twilio-developer-kit:twilio-send-message
twilio-developer-kit:twilio-sms-isv-setup
twilio-developer-kit:twilio-sms-send-message
twilio-developer-kit:twilio-studio-flows
twilio-developer-kit:twilio-taskrouter-routing
twilio-developer-kit:twilio-verify-send-otp
twilio-developer-kit:twilio-voice-conversation-relay
twilio-developer-kit:twilio-voice-outbound-calls
twilio-developer-kit:twilio-voice-twiml
twilio-developer-kit:twilio-webhook-architecture
twilio-developer-kit:twilio-whatsapp-manage-senders
twilio-developer-kit:twilio-whatsapp-send-message
twilio-developer-kit:twilio-sendgrid-account-setup
twilio-developer-kit:twilio-sendgrid-deliverability-advisor
twilio-developer-kit:twilio-sendgrid-email-send
twilio-developer-kit:twilio-sendgrid-email-settings
twilio-developer-kit:twilio-sendgrid-engagement-quality
twilio-developer-kit:twilio-sendgrid-inbound-parse
twilio-developer-kit:twilio-sendgrid-suppressions
twilio-developer-kit:twilio-sendgrid-webhooks
common-room:account-research
common-room:call-prep
common-room:compose-outreach
common-room:contact-research
common-room:prospect
common-room:weekly-prep-brief
brand-voice:brand-voice-enforcement
brand-voice:discover-brand
brand-voice:guideline-generation
operations:capacity-plan
operations:change-request
operations:compliance-tracking
operations:process-doc
operations:process-optimization
operations:risk-assessment
operations:runbook
operations:status-report
operations:vendor-review
product-management:competitive-brief
product-management:metrics-review
product-management:product-brainstorming
product-management:roadmap-update
product-management:sprint-planning
product-management:stakeholder-update
product-management:synthesize-research
product-management:write-spec
human-resources:comp-analysis
human-resources:draft-offer
human-resources:interview-prep
human-resources:onboarding
human-resources:org-planning
human-resources:people-report
human-resources:performance-review
human-resources:policy-lookup
human-resources:recruiting-pipeline
slack-by-salesforce:slack-messaging
slack-by-salesforce:slack-search
bio-research:instrument-data-to-allotrope
bio-research:nextflow-development
bio-research:scientific-problem-selection
bio-research:scvi-tools
bio-research:single-cell-rna-qc
bio-research:start
marketing:brand-review
marketing:campaign-plan
marketing:competitive-brief
marketing:content-creation
marketing:draft-content
marketing:email-sequence
marketing:performance-report
marketing:seo-audit
engineering:architecture
engineering:code-review
engineering:debug
engineering:deploy-checklist
engineering:documentation
engineering:incident-response
engineering:standup
engineering:system-design
engineering:tech-debt
engineering:testing-strategy
cockroachdb:benchmarking-transaction-patterns
cockroachdb:designing-application-transactions
cockroachdb:designing-multi-region-applications
cockroachdb:analyzing-range-distribution
cockroachdb:analyzing-schema-change-storage-risk
cockroachdb:auditing-table-statistics
cockroachdb:monitoring-background-jobs
cockroachdb:profiling-statement-fingerprints
cockroachdb:profiling-transaction-fingerprints
cockroachdb:triaging-live-sql-activity
cockroachdb:molt-fetch
cockroachdb:molt-replicator
cockroachdb:molt-verify
cockroachdb:setting-up-local-cluster
cockroachdb:managing-certificates-and-encryption
cockroachdb:managing-cluster-capacity
cockroachdb:managing-cluster-settings
cockroachdb:performing-cluster-maintenance
cockroachdb:provisioning-cluster-for-production
cockroachdb:reviewing-cluster-health
cockroachdb:upgrading-cluster-version
cockroachdb:cockroachdb-sql
cockroachdb:auditing-cloud-cluster-security
cockroachdb:configuring-audit-logging
cockroachdb:configuring-ip-allowlists
cockroachdb:configuring-log-export
cockroachdb:configuring-private-connectivity
cockroachdb:configuring-sso-and-scim
cockroachdb:enabling-cmek-encryption
cockroachdb:enforcing-password-policies
cockroachdb:hardening-user-privileges
cockroachdb:managing-tls-certificates
cockroachdb:preparing-compliance-documentation
finance:audit-support
finance:close-management
finance:financial-statements
finance:journal-entry
finance:journal-entry-prep
finance:reconciliation
finance:sox-testing
finance:variance-analysis
apollo:enrich-lead
apollo:prospect
apollo:sequence-load
zoom-plugin:build-zoom-bot
zoom-plugin:build-zoom-meeting-app
zoom-plugin:choose-zoom-approach
zoom-plugin:cobrowse-sdk
zoom-plugin:contact-center
zoom-plugin:debug-zoom
zoom-plugin:debug-zoom-integration
zoom-plugin:design-mcp-workflow
zoom-plugin:general
zoom-plugin:meeting-sdk
zoom-plugin:oauth
zoom-plugin:phone
zoom-plugin:plan-zoom-integration
zoom-plugin:plan-zoom-product
zoom-plugin:probe-sdk
zoom-plugin:rest-api
zoom-plugin:rivet-sdk
zoom-plugin:rtms
zoom-plugin:scribe
zoom-plugin:setup-zoom-mcp
zoom-plugin:setup-zoom-oauth
zoom-plugin:start
zoom-plugin:team-chat
zoom-plugin:ui-toolkit
zoom-plugin:video-sdk
zoom-plugin:virtual-agent
zoom-plugin:webhooks
zoom-plugin:websockets
zoom-plugin:zoom-apps-sdk
zoom-plugin:zoom-mcp
sales:account-research
sales:call-prep
sales:call-summary
sales:competitive-intelligence
sales:create-an-asset
sales:daily-briefing
sales:draft-outreach
sales:forecast
sales:pipeline-review
data:analyze
data:build-dashboard
data:create-viz
data:data-context-extractor
data:data-visualization
data:explore-data
data:sql-queries
data:statistical-analysis
data:validate-data
data:write-query
enterprise-search:digest
enterprise-search:knowledge-synthesis
enterprise-search:search
enterprise-search:search-strategy
enterprise-search:source-management
design:accessibility-review
design:design-critique
design:design-handoff
design:design-system
design:research-synthesis
design:user-research
design:ux-copy
anthropic-skills:consolidate-memory
anthropic-skills:docx
anthropic-skills:pdf
anthropic-skills:pptx
anthropic-skills:schedule
anthropic-skills:setup-cowork
anthropic-skills:skill-creator
anthropic-skills:xlsx
dataviz
artifact-design
update-config
keybindings-help
verify
simplify
fewer-permission-prompts
loop
schedule
claude-api
run
init
review
security-review
attachment
b8226ab0-cc3c-4a92-a2fb-64c279eeff4e
2026-07-12T10:58:30.274Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
b8226ab0-cc3c-4a92-a2fb-64c279eeff4e
ab9d1e77bfa57e6d2
claude-opus-4-8
msg_011Ccx3aVqutK5gF9aGgDq3y
message
assistant
thinking

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
standard
not_available
req_011Ccx3aUJe5u3eUcuBG1QFa
general-purpose
assistant
7cb56217-3f00-4d37-b42a-f31ed6ac1611
2026-07-12T10:58:32.998Z
external
claude-desktop
/Users/PRINCESS/White
9f65250c-b1af-4c71-9e36-a2a709f3271c
2.1.205
HEAD
synchronous-bubbling-cupcake
7cb56217-3f00-4d37-b42a-f31ed6ac1611
ab9d1e77bfa57e6d2
claude-opus-4-8
msg_011Ccx3aVqutK5gF9aGgDq3y
message
assistant
text

Overclocking your GPU is one of the most satisfying ways to squeeze extra frames out of hardware you already own, and in 2026 the tools are safer and more automated than ever. But “safer” does not mean “risk-free” — push too far without understanding what you are doing, and you can crash games, corrupt benchmarks, or run your card hotter than it should be. This guide walks you through the entire process of how to overclock your GPU safely, from installing the right software to finding your card’s real limits and locking in a stable, everyday profile. Whether you are on an older RTX 3060 or a shiny new 2026 flagship, the fundamentals are the same, and by the end you will know exactly how far to push and when to stop.

As an Amazon Associate we earn from qualifying purchases. Prices and availability are accurate as of the date/time indicated and are subject to change.

What GPU Overclocking Is (and Is It Safe?)

At its core, GPU overclocking means running your graphics card’s core and memory chips at higher clock speeds than the factory default. Manufacturers ship cards with conservative settings so that every single unit — even the weakest one off the line — runs reliably. That leaves headroom, and overclocking reclaims it. A modern GPU also dynamically boosts its clocks based on temperature, power, and voltage headroom, so much of overclocking in 2026 is really about giving the card more room to boost rather than forcing a fixed frequency.

Is overclocking a GPU safe? For the most part, yes. Today’s cards have robust built-in protections: if you push the core clock too high, the driver crashes or the game closes rather than damaging silicon. Thermal throttling automatically reduces clocks if temperatures climb too high, and hard voltage caps prevent you from feeding the chip a dangerous amount of power. The two real long-term risks are excess heat (which shortens component lifespan over years, not days) and instability that can, in rare cases, corrupt data during a crash. Follow the incremental method in this guide, keep temperatures in check, and the process is genuinely low-risk. If you want a deeper primer on thermals first, see our GPU temperature guide.

Step 1: Install the Right GPU Overclocking Tools

You need two pieces of free software before you touch a single slider. The first is MSI Afterburner, the de facto standard overclocking utility that works with virtually any GPU brand, not just MSI cards. It exposes sliders for core clock, memory clock, power limit, temperature limit, fan curve, and voltage. The second is GPU-Z, a lightweight monitoring tool that reports your exact GPU model, VRAM type, current clocks, voltages, and — critically — whether your card is showing memory errors under load.

Install both, then open Afterburner and enable the on-screen display (OSD) so you can watch clocks, temperatures, and framerate in real time while a game or benchmark runs. Take a moment to note your card’s stock behavior: idle temperature, load temperature, and the clock speeds it naturally boosts to. This baseline is what every future change gets measured against. For picking hardware that overclocks well in the first place, our best GPUs of 2026 roundup breaks down which models have the most thermal headroom.

Step 2: Benchmark Your Baseline

Before overclocking, you must know your starting point objectively. Run a repeatable benchmark and record the score. The three gold-standard tools are Unigine Superposition (or the older Heaven), and 3DMark (Time Spy and Steel Nomad are the modern presets). Pick one, run it three times at stock, and average the score. Note the maximum GPU temperature and the average framerate as well.

This baseline matters for two reasons. First, it tells you how much your overclock actually gains — chasing frames you cannot measure is pointless. Second, benchmarks are excellent stability stress tests: a card that renders a scene incorrectly will produce visible artifacts (flickering textures, stray polygons, colored dots) that instantly reveal an unstable overclock. Keep the benchmark window handy; you will return to it after every adjustment.

Step 3: Raise the Power Limit and Temperature Limit First

The single most effective first move is to max out the power limit slider in Afterburner (often labeled TDP %) and raise the temperature limit to its ceiling, typically around 87–90°C. This does not increase your clocks directly. Instead, it removes the artificial throttles that stop your GPU from boosting as high as it otherwise could. On many cards, simply unlocking the power limit yields a free performance bump with zero manual clock tuning because the card can now sustain its boost clocks longer.

Apply the change, run your benchmark, and confirm the card is stable and temperatures stay in a comfortable range (under 80°C is ideal for longevity, though the low-to-mid 80s is acceptable). If your card is already hitting the temperature limit at stock, focus on improving cooling — case airflow, a repaste, or a better fan curve — before pushing clocks further.

Step 4: Incrementally Bump the Core Clock, Then the Memory Clock

Now the real overclocking begins. Increase the core clock offset in small steps of +15 to +25 MHz at a time. After each bump, apply the setting and run a short benchmark loop or a graphically demanding game for a few minutes. Watch for crashes, driver resets, or artifacts. If everything is clean, add another 15–25 MHz and repeat. This patience is the whole secret to how to overclock a GPU safely — small steps make it trivial to identify the exact point where instability begins.

Once the core clock is dialed in, reset it to stock temporarily and tune the memory clock separately using the same method, though memory tolerates larger steps of +50 to +100 MHz. GDDR6X and GDDR7 memory have built-in error correction, which is a trap: instead of crashing, over-clocked memory silently corrects errors and drops performance. That is why you watch the benchmark score, not just stability — if your score stops rising or falls as you add memory clock, you have gone too far. Once both are tuned individually, combine your best stable core and memory offsets and re-test together.

Step 5: Test for Stability and Find the Crash Point, Then Back Off

Stability testing separates a benchmark-stable overclock from an everyday-stable one. Loop Superposition or 3DMark’s stress test for 20 minutes and play your most demanding games for an hour or two. A card that passes a five-minute benchmark can still crash after 40 minutes of a real game because sustained heat and varied workloads expose weaknesses.

Deliberately find your crash point: keep pushing until the driver resets or artifacts appear, note that value, then back off by 15–30 MHz on the core to build in a safety margin. An overclock that runs at the absolute edge will feel fine until the one game that crashes at a critical moment. A slightly conservative overclock that never crashes is worth far more than a headline number you cannot rely on. If you hit persistent crashes even at modest offsets, our guide to fixing GPU crashes covers driver and power supply culprits.

Undervolting: The Cooler, Quieter Alternative

If lower temperatures and fan noise appeal to you more than raw performance, consider undervolting instead of a traditional overclock. Using Afterburner’s voltage-frequency curve editor (Ctrl+F), you lock the GPU to a specific frequency at a lower voltage than stock. The result is a card that runs significantly cooler and quieter while often maintaining — or even slightly exceeding — stock performance, because it no longer throttles from heat. Undervolting is arguably the smartest tune for most gamers in 2026: it extends component life, reduces power draw, and is essentially risk-free since you are lowering voltage, not raising it. Many enthusiasts combine a mild undervolt with a modest clock offset for the best of both worlds.

Recommended GPU Overclocking and Monitoring Tools

Tool	Purpose	Free?	Rating
MSI Afterburner	Core/memory overclocking, power & temp limits, undervolting, fan curves, OSD	Yes	★★★★★
GPU-Z	Hardware ID, live sensor readout, memory error detection, VRAM/BIOS info	Yes	★★★★★
Unigine Heaven / Superposition	Repeatable render benchmark and artifact-spotting stress test	Yes (free tier)	★★★★☆
3DMark	Industry-standard benchmark scores and dedicated GPU stress test	Free demo (paid full)	★★★★☆
HWiNFO	Deep, all-sensor logging of temps, clocks, voltages and power	Yes	★★★★☆

Step 6: Save Your Profile and Keep Monitoring Temperatures

Once you have a stable, tested overclock, save it as a profile in Afterburner and, if you like, set it to apply automatically at Windows startup. Afterburner supports multiple profile slots, so you can keep a conservative “everyday” profile and a more aggressive “benchmark” profile side by side.

Overclocking is not entirely set-and-forget. As seasons change and ambient room temperature rises in summer, a tune that was stable in winter may need a small step back. Keep the OSD or HWiNFO logging enabled for your first week of daily use and glance at load temperatures periodically. If you ever see temperatures creeping past the low 80s or the occasional artifact returning, dial the offset back slightly. For maintaining airflow over the long term, our PC cooling tips keep your overclock stable for years.

Frequently Asked Questions

Is overclocking a GPU safe?

Yes, when done incrementally. Modern GPUs have hard voltage caps, automatic thermal throttling, and driver-level crash protection that prevent most catastrophic damage. The real risks are long-term wear from sustained high heat and occasional instability crashes. Keep temperatures under the low 80s, raise clocks in small steps, and stress-test thoroughly, and GPU overclocking is a genuinely low-risk activity.

How much performance does GPU overclocking give?

Realistically, expect a 5–12% improvement in framerate from a solid air-cooled overclock, with most cards landing around 7–10%. Unlocking the power limit alone can deliver a few percent for free. Memory-heavy games benefit more from a good memory overclock. Gains vary by card, cooling, and the “silicon lottery,” so your baseline benchmark is the only honest way to measure your specific result.

Is undervolting better than overclocking?

It depends on your priority. Overclocking maximizes raw performance at the cost of more heat, noise, and power. Undervolting prioritizes cooler, quieter, more efficient operation while usually holding stock-level performance — and it is essentially risk-free since you lower voltage rather than raise it. For most everyday gamers in 2026, a mild undervolt (optionally paired with a small clock offset) is the smarter, longer-lasting choice.

Will overclocking void my warranty?

In most regions, using software like MSI Afterburner to overclock does not void your GPU warranty, and many manufacturers even market overclocking headroom. What can void a warranty is flashing a custom BIOS or physically modifying the card (hardware voltage mods, aftermarket coolers). Software overclocking through official tools is generally accepted, but always check your specific manufacturer’s warranty terms, as policies vary by brand and country.