Explore skills

专门用于深度分析和解读本地或 GitHub 源代码仓库的技能。自动 clone 仓库（可选）、生成中文分析报告、翻译 README、添加中文注释。全自动运行，无需中间交互。当用户说"帮我分析这个 GitHub 仓库"或"分析当前目录的代码"时使用此技能。

Guided walkthrough of the JTBD skills. Takes a new user from "what is this?" to "I understand the four forces and know what to do next" in about 5 minutes. Uses existing example data, no real interview required. Use when: "demo", "tutorial", "how does this work", "show me", "getting started".

Automated code review → fix → re-review loop. Runs until score >9 or max 3 rounds. Fixes Critical/Major/Warnings only — Suggestions are deferred.

Sync documentation with code changes. Auto-detects scope from git diff, updates tier 1-4 docs (core, architecture, journey, config), verifies stats. Phase D of /ship pipeline.

Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.

Debug issues through structured investigation, failing test creation, and targeted fixes. Use when the user provides an error message, traceback, steps-to-reproduce, or describes unexpected behavior.

Generate comprehensive architecture documentation for complex code modules with Graphviz diagrams and examples. Use when user asks to "explain this code", "document the architecture", or wants to understand how a module/system works.

Run the full JTBD analysis pipeline on a batch of interview transcripts. Analyzes each transcript into a Switch analysis, then finds cross-interview patterns. Accepts a directory of transcript files or Fireflies meeting IDs. Use when: "analyze all interviews", "jtbd pipeline", "batch analysis", "process transcripts".

Lint a BDK agent file for best practices and portability. Use when reviewing, creating, or editing an agent (agents/*.md) to verify it meets BDK conventions. Trigger on phrases like "check this agent", "verify agent", "lint agent", or when about to commit a new agent.

Tool-tier guidance for impact analysis (blast radius, affected flows). Preloaded into agents that reason about change impact; not user-facing.

Rigid TDD process for writing and verifying tests before implementation. Use when implementing any feature or bugfix. Receives test case bullet points from the plan and enforces red-green cycle.

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"