linear-subagent-guide
Guides optimal Linear operations usage with caching, performance patterns, and error handling. Auto-activates when implementing CCPM commands that interact with Linear. Prevents usage of non-existent Linear MCP tools.
hook-optimization
Provides guidance on optimizing CCPM hooks for performance and token efficiency. Auto-activates when developing, debugging, or benchmarking hooks. Includes caching strategies, token budgets, performance benchmarking, and best practices for maintaining sub-5-second hook execution times.
planning-strategy-guide
Guides intelligent planning strategies with automatic phase detection and complexity assessment. Auto-activates when users mention epic breakdown, feature decomposition, scope estimation, dependency analysis, risk identification, or ask "how do I plan this complex task", "break down this feature", "what's the scope", "estimate effort", "identify dependencies", or "planning strategy". Provides interactive planning mode with 6 planning phases (complexity assessment, scope definition, dependency analysis, risk identification, task breakdown, effort estimation). Works with sequential-thinking for complex decomposition, docs-seeker for research, pm-workflow-guide for command suggestions, and linear-subagent-guide for Linear integration.
git-reference-manager
Safely introduce external Git repositories as reference materials. Responsible for managing the `_reference` directory, ensuring external code is read-only and does not pollute the project's version control.
task-expert
'Task as Code' management expert. Responsible for maintaining task files in the todos/ directory, ensuring continuous task IDs, clear statuses, and adherence to specifications.
typedown-expert
Expert guidance on writing correct Typedown code, focusing on syntax, best practices, and common pitfalls.
architecture-design
Generate comprehensive software architecture documentation (ARCHITECTURE.md) with C4 diagrams, OpenAPI specs, and technology-specific guidance. This skill should be used when creating architecture documentation for new projects, documenting existing systems, or updating architectural specifications.
ideation
Creative ideation for new project concepts. USE WHEN user says "new idea", "what if we built", "I want to create", "brainstorm a project", or discusses ideas without an existing project. Creates IDEA.md and project structure. Not for in-project exploration—use exploration skill for that.
exploration
Technical exploration within existing projects. USE WHEN user says "think through", "explore options", "investigate", "how should we approach", or needs to evaluate approaches before implementation. Creates exploration documents in project's explorations/ folder. Not for new project ideas—use ideation skill for that.
syncing-knowledge-garden
Syncs the sb-knowledge-base Obsidian vault to the knowledge-garden Quartz site. Use after reorganizing content in Obsidian or when the vault has been updated and the Quartz site needs to match.
vscode-theme
Generate VSCode color themes, package them as .vsix files, and install to VSCode. Use when creating custom VSCode themes, designing color schemes, or when the user mentions VSCode theme, color theme, dark theme, or light theme.
update-auto-approve
Analyze PermissionRequest decision logs and improve auto-approve configuration across all layers. Covers settings.json patterns, static rule engine, LLM evaluator prompt, and tests. Use when asked to "update auto-approve", "improve permissions", "reduce unnecessary asks", or "optimize permission rules".
task-enrich
Verify and enrich task descriptions to ensure each is independently executable with sufficient context. Use when "enriching tasks", "preparing handoff", "verifying task quality", or before running /task-handoff.
setup-claude-skills-for-web
Setup Claude Code skills from berlysia/dotfiles for web version in other projects. Creates .claude/settings.json with auto-update hook. Use when setting up skills for web version or when user asks to configure, install, or setup external Claude Code skills for web.
session-memo
Save current session's problem context as a memo file for cross-session reference. Uses sub-agent to minimize context consumption. Supports two modes - summarize current session or read a past session by ID.
update-docs
Update documentation to match code changes. Triggered by: 'update docs', 'sync documentation', 'README outdated', 'docs更新', 'ドキュメント直して'. Delegates to subagent to protect context.
verify-doc
Verify document self-containedness by having a context-free sub-agent explain its understanding. Use after writing specs, handoff docs, or any document that must be understood without conversation context.
scope-guard
Analyze task scope and recommend execution strategy (sub-agent, multi-session, or scope cut). Orchestrates existing skills like /decompose, /task-enrich, and /task-handoff.
renovate-github-action-guide
Apply the "GitHub Actions and Renovate Guide" to configure repo settings, branch protection, GitHub App/PAT secrets, and renovate.json5 for personal or team GitHub projects. Use when asked to introduce Renovate, enable dependency auto-updates, or align settings with the guide.
refine-skill
Analyze and refine existing Claude Code Skills for conciseness and effectiveness. Use when asked to "review", "refine", "improve", "optimize" Skills, or when user mentions "skill quality", "skill refinement", "too verbose", "skill doesn't trigger", "description quality", or wants to make a Skill more concise. Do NOT use for creating new skills from scratch (use skill-creator instead).
react-hooks
This skill should be used when the user asks to "review React hooks", "check useEffect usage", "optimize hooks performance", "design custom hooks", "refactor to use hooks", "remove unnecessary useEffect", "simplify useMemo usage", or discusses React hooks patterns. Provides guidance on writing minimal, effective React hooks code.
optimize-claude-md
Analyze and optimize CLAUDE.md files for quality improvements and token reduction. Supports analysis-only, simplification-only, or full optimization modes. Use when asked to "review", "optimize", "simplify", "improve", "check", or "reduce tokens" in CLAUDE.md.
logic-validation
Validate logical consistency of decisions and claims through context forking. Use proactively when judgment validity is unclear, but prefer direct tools (Read, Bash) for simple verifications like file contents or test results.
japanese-tech-writing
日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
intent-alignment-triage
Re-evaluate auto-review findings against the original order's intent. Filters out findings that bend the intent to reduce scope. Use after Document Workflow auto-review completes (step 5→6), or when review feedback feels like it's distorting the original goal.
insight-digest
Read the periodic Insight digest distilled from session logs and decide which entries to promote into skills, ~/.claude/rules/, or CLAUDE.md. Also supports manual regeneration (force) and acknowledgement (ack). Use when a SessionStart notice points to a new digest, or when reviewing accumulated insights.
task-handoff
Identify current session's task list and generate commands to start a new Claude session sharing the same tasks. Use when "handing off", "continuing later", "resuming tasks", or preparing work for next session.
test-design
Design test viewpoints and test cases from code changes using ISO 25010. Use when writing test plans for plan.md, reviewing PR test coverage, or when asked to 'テスト設計', 'テスト観点洗い出し', 'design test cases'. Do NOT use for writing test code or TDD workflows (use /bugfix).
apply-harness-practices
Analyze a project's harness maturity and guide staged adoption of Harness Engineering best practices (quality loops, safety gates, linters, CLAUDE.md optimization).
bugfix
Standardized bug fix workflow using TDD (Red-Green-Refactor). Use when fixing bugs, resolving issues, or when the user invokes /bugfix. Ensures root cause analysis, failing test first, then minimal fix.
clarify
Create detailed specifications by iteratively clarifying unclear points for Plan mode. Use when: After completing a plan when detailed requirements need clarification before implementation.
claude-action-bootstrap
Policy-enforcing installer that deploys hardened Claude Code Action workflows (`@claude` manual mention + dependency-bot auto-fix) into a personal GitHub repository the user administers. Use when asked to introduce Claude Code Action, apply `@claude` mention support, or set up automated CI auto-fix for dependency bot PRs, using the security-hardened templates shipped with this skill.
adr-session
Start or resume an ADR session. Without number: show status overview and recommend next actionable ADR. With number: provide phase-specific guidance. Trigger: /adr-session, /adr-session NNN, /adr-session new
adr-migrate
Migrate existing ADRs to YAML frontmatter format. Scans docs/decisions/ for ADRs without frontmatter, infers status from body text, shows dry-run for approval. Trigger: /adr-migrate
execute-plan
Execute a pre-existing plan file by implementing tasks sequentially with test verification after each step. Use when plan/tasks are already decomposed and ready for implementation.
docs-audit
Comprehensive documentation audit and refresh. Checks code-documentation drift, generates prioritized report, then updates with approval. Use for: 'ドキュメント監査', 'docs audit', 'ドキュメント棚卸し', 'README全体見直し', 'documentation health check'.
decompose
Decompose complex tasks into detailed, actionable todos. Each todo has a rich description that is executable from the description alone.
decision-quality-review
Evaluate plan.md design decisions for dominant-axis misalignment using the Decision Quality framework. Detects when a plan optimizes for the wrong evaluation axis given the nature of the change. Use during plan review alongside logic-validator and scope-justification-reviewer.
cognitive-rhythm-writing
説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替（観察→逡巡→断定→再観察）と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。
skill-validator
|
skill-creator-pro
|
writing-dockerfile
Generates secure, production-ready Dockerfiles with multi-stage builds and security hardening. Use when Claude needs to write Dockerfiles for containerized applications.
minikube-deploy
Zero-shot deployment of ANY containerized application to local Kubernetes using Minikube. Use when Claude needs to: (1) Deploy any project to Minikube without prior setup, (2) Auto-detect services from Dockerfiles or docker-compose.yml, (3) Generate Helm charts dynamically for detected services, (4) Build and deploy multiple services automatically, (5) Enable optional Dapr for event-driven architecture, (6) Migrate any docker-compose project to Kubernetes. Works with monorepos, single apps, any number of services. Cross-platform (Linux, macOS, Windows). Triggers: 'deploy to minikube', 'run on kubernetes locally', 'local k8s', 'minikube deployment'.
mcp-chatkit-integration
|
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
containerize-apps
Containerizes applications with impact-aware Dockerfiles and docker-compose configurations. This skill should be used when containerizing projects for Docker, creating Dockerfiles, docker-compose files, or preparing applications for Kubernetes deployment. It performs impact analysis first (env vars, network topology, auth/CORS), then generates properly configured container configs. Invokes the impact-analyzer subagent for comprehensive project scanning.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
fetch-library-docs
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
discovering-intent
|
creating-chatgpt-widgets
Create production-grade widgets for ChatGPT Apps using the OpenAI Apps SDK. Use when users ask to build widgets, UI components, or visual interfaces for ChatGPT applications. Supports any widget type including progress trackers, quiz interfaces, content viewers, data cards, carousels, forms, charts, dashboards, maps, video players, or custom interactive elements. IMPORTANT - Always clarify requirements before building. Creates complete implementations following official OpenAI UX/UI guidelines with window.openai integration, theme support, and accessibility.
Page 1137 of 1712 · 85561 results
