Use when user provides exported chat history (WeChat / Telegram / iMessage / QQ exports as .md / .txt / .json) and asks "我和 X 聊了啥"、"看完整个 md"、"细说 XX"、"是不是有 Y"、"what did I and X talk about", wants topical breakdown, requests detail on specific themes (relationships / work / health / events), or seeks honest…
Use when asked whether a codebase's size is justified — "is 800k lines reasonable?", "audit our LOC", "are we bloated?", "值不值" — or when a LOC number is being used in an argument and nobody agrees what it measures. Produces a defensible per-sub-product accounting: strict line counts, a product-surface inventory, every…
Generate a DESIGN.md file for any brand or website by analyzing its visual design system. Use when the user asks to "generate a DESIGN.md for [brand/URL]", "create a design system doc for [site]", "extract the design tokens from [URL]", or "make a DESIGN.md like [brand]". Triggers on any request to document a…
Use when delivering analysis, assessment, or diagnosis to the person whose work/behavior/decisions are being analyzed, and they push back emotionally, contradict conclusions, or express discomfort — prevents flipping the conclusion to match their mood while staying open to new factual evidence. Covers code review…
A read-only assistant for finding and examining information in Slack, a workplace messaging service. It can work with messages, threads, channels, users, and shared files when the required Slack access is available.
Use when writing, modifying, or running live E2E test scenarios in src/e2e/live/ for the kagura project. Triggers on Slack bot integration testing, live scenario creation, Codex/Claude provider live tests, status probe assertions, database assertions, and requests to run or debug live E2E tests.