Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Comprehensive overview of Claude Code features, architecture, and capabilities. Learn about hooks, skills, commands, permissions, and best practices for configuring Claude Code as your AI development assistant. This is about the TOOL itself, not project code.
Enforce measure-first discipline for code optimization using a 7-step gated decision tree and 40-item checklist. Use when code is too slow, has performance issues, timeouts, OOM errors, high CPU/memory, or doesn't scale. Triggers on: profiler hot spots, latency complaints, unresponsive UI, memory allocation slow, needs optimization. Produce violation/warning/pass table with evidence.
Detect and eliminate generic AI-generated patterns ("slop") across natural language, code, and design.
Automatically discover cryptography skills when working with encryption, TLS, certificates, PKI, and security
Automatically discover database skills when working with SQL, PostgreSQL, MongoDB, Redis, database schema design, query optimization, migrations, connection pooling, ORMs, or database selection. Activates for database design, optimization, and implementation tasks.
Automatically discover frontend development skills when working with React, Next.js, UI components, state management, data fetching, forms, accessibility, performance optimization, or SEO. Activates for frontend web development tasks.
Automatically discover Modal platform skills when working with Modal. Activates for modal development tasks.
Automatically discover observability and monitoring skills when working with monitoring. Activates for observability development tasks.
Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint propagation, and continuous validation. Use when refactoring existing code, optimizing architecture, or consolidating technical debt through systematic hole-driven development.
Execute quality checklists (112+ items) for code review, testing strategy, and debugging. CHECKER mode audits QA practices with evidence tables. APPLIER mode generates test cases (5:1 dirty ratio), runs Scientific Debugging Method (STABILIZE-HYPOTHESIZE-EXPERIMENT-FIX-VERIFY-SEARCH), or sets up inspection procedures. Use when planning QA, choosing review methods, designing tests, or debugging fails. Triggers on: defects found late, tests pass but production bugs, coverage disputes, review ineffective, spending excessive time debugging.
Guide safe refactoring with research-backed discipline and small-change rigor. Produce refactoring approach, step sequence, and risk assessment. Use when modifying existing code, improving structure without changing behavior, or deciding between refactor, rewrite, or fix-first. Triggers on: code smells, technical debt, just cleaning while I fix, small change treated casually, regression from trivial change, one-line change errors, production down with cleanup urge.
Evaluate routine and class design quality using Code Complete checklists (43 items). Use when designing routines or classes, reviewing class interfaces, choosing between inheritance and containment, or evaluating routine cohesion. Also trigger when tempted to use inheritance as a quick fix under deadline pressure, or when rationalizing 'but it works' for code with deep inheritance or many parameters. Produce severity-tagged reviews (VIOLATION/WARNING/PASS) in CHECKER mode or design decisions in APPLIER mode. Symptoms: vague routine names, >7 parameters, deep inheritance, mixed abstraction levels.
Complete guide for separating meta-configurations (Claude Code tool configuration) from domain configurations (project implementation). Learn how to avoid conflicts when working with multiple projects, especially those using agent SDKs/ADKs like Google ADK, LangChain, or Anthropic SDK. Covers namespace isolation, prefixing conventions, CLAUDE.md hierarchy, scope declaration, and conflict detection strategies.
Specialized guidance for developing cc-sessions API commands and subsystems for state management, task operations, configuration, and protocol execution
Provide comprehensive guidance for developing and maintaining the cc-sessions framework core functionality - primary skill for hooks, sessions, tasks, middleware, route handlers, and API endpoints
Specialized guidance for creating, modifying, and debugging cc-sessions hooks that enforce DAIC discipline, write-gating, and framework integrity
Project Guidelines Skill (Example)
Expert skill for analyzing Claude Code primitive structures (skills, commands, hooks) in projects. Performs deep quality analysis, detects naming conflicts, validates best practices, identifies missing configurations, and provides actionable recommendations for improving Claude Code setup. This is about analyzing the TOOL configuration itself, not project code.
Replace complex conditional logic with table lookups. CHECKER mode identifies opportunities where if/else chains or inheritance hierarchies should become tables. APPLIER mode designs table structure, access method (direct/indexed/stair-step), and key transformations. Use when writing 4+ if/else branches, switch statements keep growing, subclasses differ only in data not behavior, or data changes without code changes. Triggers on: too many if statements, switch growing, subclass per type, customer-controlled format, data-driven behavior, lookup table, mapping data to actions.
Interactive assistant for intercepting, debugging, analyzing and reviewing Claude Code API requests using mitmproxy. Guides setup, certificate configuration, and active traffic inspection via web or CLI interface. Supports learning Claude Code internals, debugging issues, and optimizing API usage.
Use when troubleshooting skill issues, understanding CC platform limitations, or reviewing skills for CC-specific gotchas. For skill creation tutorials, use plugin-dev:skill-development.
cc10x-router
Use this skill for multi-step development tasks. Latent Chain Mode reduces token usage by 70-80% through hidden-state reasoning with 4-phase workflow: analysis → plan → impl → review.
Structured code review workflow integrated with CCPM's Linear-based project management system. Enforces "no completion claims without verification evidence" principle.
Systematic debugging with Linear integration and structured troubleshooting workflow.
MCP server discovery, configuration, and troubleshooting for CCPM workflows.
Meta-skill for creating new CCPM skills with proper structure and conventions.
>-
CCXT cryptocurrency exchange library for C# and .NET developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in .NET projects. Use when working with crypto exchanges in C# applications, trading systems, or financial software. Supports .NET Standard 2.0+.
CCXT cryptocurrency exchange library for Go developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Go projects. Use when working with crypto exchanges in Go applications, microservices, or trading systems.
CCXT cryptocurrency exchange library for PHP developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in PHP 8.1+. Use when working with crypto exchanges in PHP projects, trading bots, or web applications. Supports both sync and async (ReactPHP) usage.
CCXT cryptocurrency exchange library for Python developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Python. Use when working with crypto exchanges in Python projects, trading bots, data analysis, or portfolio management. Supports both sync and async (asyncio) usage.
CCXT cryptocurrency exchange library for TypeScript and JavaScript developers (Node.js and browser). Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors. Use when working with crypto exchanges in TypeScript/JavaScript projects, trading bots, arbitrage systems, or portfolio management tools. Includes both REST and WebSocket examples.
Context Driven Development pipeline for release workflows
Use when designing content delivery networks, caching strategies, or global content distribution. Covers CDN architecture, cache hierarchies, origin shielding, cache invalidation, and edge optimization.
Use when configuring CDN for media delivery, implementing cache invalidation, or designing signed URL patterns. Covers CDN configuration, edge caching, origin shielding, and secure media access for headless CMS.
Cluster TCR/BCR clones by CDR3 sequences using GIANA or ClusTCR (both Faiss-based). Adds `CDR3_Cluster` column to metadata for clonotype analysis.
Context Engineering 101 curriculum slide generation. Use this skill when working on CE101 curriculum to: (1) Generate styled PowerPoint presentations from markdown, (2) Create PNG previews of slides, (3) Update master presentation from curriculum modules
This skill generates self-contained p5.js celebration animations for educational MicroSims. Use this skill when users request creating new celebration animations, particle effects, reward animations, or visual feedback for student achievements. The skill creates a new animation JavaScript file in /docs/sims/shared/animations/ and integrates it with the animation-lib-tester MicroSim for testing.
Celery configuration templates for all frameworks (Django, Flask, FastAPI, standalone). Use when configuring Celery, setting up task queues, creating Celery apps, integrating with frameworks, or when user mentions Celery configuration, task queue setup, broker configuration, or framework integration.
Expert Celery distributed task queue engineer specializing in async task processing, workflow orchestration, broker configuration (Redis/RabbitMQ), Celery Beat scheduling, and production monitoring. Deep expertise in task patterns (chains, groups, chords), retries, rate limiting, Flower monitoring, and security best practices. Use when designing distributed task systems, implementing background job processing, building workflow orchestration, or optimizing task queue performance.
>
Annotates cell clusters with biological cell type labels using multiple methods: direct assignment, ScType, scCATCH, hitype, or CellTypist. This process is essential for interpreting clustering results by assigning meaningful biological identities to each cluster.
Provide guidance on completion certificates. Use when a customer asks for a course certificate or LinkedIn certificate details.
Formal verification using Certora Prover with CVL specification language. Supports invariant rules, parametric verification, ghost variables, and counterexample analysis for mathematical proof of contract correctness.
FAST code generation via Z.ai glm-4.6 model. Use for rapid test generation, boilerplate code, repetitive patterns, and bulk file creation. Ideal when speed matters more than nuance. Do NOT use for complex architectural decisions or security-critical code.
FAST code generation via mcp__cerebras-mcp__write tool using Z.ai glm-4.6. Use for rapid test generation, boilerplate creation, and bulk code tasks in main chat. Prompt must be SHORTER than output. Ideal for tests, CRUD, migrations, and repetitive patterns.
Two-phase compilation error fixer for Rust and TypeScript using Cerebras LLM bulk processing + dedicated agent cleanup. Use when you have 20+ compilation errors that need fast bulk reduction, or when errors are mostly mechanical (type mismatches, missing imports, syntax issues).
Task dependency extraction and context ingestion. Use when you need to parse task criteria, identify dependencies, generate execution order, or inject context for complex multi-step tasks.
Update CFN system expert agent with relevant git commits and project changes