菜单
When something that should work doesn't, suspect the environment before rewriting the code — wrong directory, stale build, missing env var, version mismatch, dirty state. Use when a command fails unexpectedly, tests fail that "can't" fail, or behavior contradicts the code you're reading.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | environment-first |
| description | When something that should work doesn't, suspect the environment before rewriting the code — wrong directory, stale build, missing env var, version mismatch, dirty state. Use when a command fails unexpectedly, tests fail that "can't" fail, or behavior contradicts the code you're reading. |
Weaker debugging assumes the code is wrong and starts editing. Often the code is fine and the world is misconfigured — and code edits made while the environment lies will be wrong edits.
pwd — right directory/repo/branch? git status — unexpected local modifications? runtime version (node -v, python --version) vs what the project expects? env vars/config the code reads — set, and set to what you think? is the dependency install current (lockfile newer than last install)?Heuristic: if the failure message doesn't mention your code's names at all (import errors, command-not-found, connection refused), it's environment until proven otherwise.
Resolve ambiguous requests by investigating, choosing the best-supported reading, and stating the interpretation — instead of guessing silently or blocking on questions. Use whenever a request has multiple plausible readings or an unstated parameter (which file, which env, how thorough, what format).
Treat any change to a public or shared interface — exported functions, HTTP endpoints, CLI flags, config formats, event/message schemas, DB schemas — as a contract change with consumers you can't see. Use before modifying anything other code depends on.
When recommending between options, match the strength of the claim to the strength of the evidence — commit when evidence is clear, say it's a coin flip when it is. Use whenever the user asks "which should I use", "what's the best way", "A or B?", or you're proposing a design choice.
Fast recon before changing unfamiliar code — instructions → manifest → tree → trace one flow end-to-end → git archaeology → imitate the newest precedent. Use when starting in a repo or module you haven't touched this session, or before designing against an existing architecture.
Async/concurrent/streaming discipline — five questions (overlapping runs, check-then-act, mutation across await, response ordering, cancellation), idempotent retries, shared-state audit, race amplification. Use for async fan-out, streams/SSE, jobs, caches, or flaky timing-smell bugs.
Externalize working state to files so long tasks survive context compaction and interruption. Use at the start of any task likely to exceed ~30 minutes or span many files, and again whenever a major phase completes or the plan changes.