为 Claude Code 会话提供的正式评测框架，实现了评测驱动开发（Eval-Driven Development，EDD）原则

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Create handoff document for transferring work to another session

Project histories, changelogs, developer interviews, open source

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

System health check (MOT) for skills, agents, hooks, and memory

Document codebase as-is with thoughts directory for historical context

Album release coordination, QA, distribution, platform uploads

Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern,...

Subject's own words - tweets, blogs, forums, chat logs

CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety...

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting...

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting...

Add rules or skills adapters for a new AI tool and wire config, CLI, completion, and tests.

PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification...

Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration

Initialize a repository by analyzing its structure and generating `AGENTS.md` and structured `docs/`, enabling AI coding agents (Claude Code, Codex, Cursor, etc.) to operate safely,...

Implement static code analysis with linters, formatters, and security scanners to catch bugs early. Use when enforcing code standards, detecting security vulnerabilities, or automating code review.

Use when writing, reviewing, or refactoring code. Apply when naming variables or functions, structuring classes, handling errors, writing tests, or when code feels complex or hard to understand....

Code quality guide for Rust. USE WHEN: writing Rust code, reviewing code, or ensuring code quality.