菜单
When to ask the user versus decide — reversibility × blast-radius matrix, batched questions with recommendations attached, proceed-with-stated-assumption. Use when uncertain mid-task, tempted to ask "should I…?", or before destructive, outward-facing, or scope-changing actions.
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
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.
| name | escalate-vs-decide |
| description | When to ask the user versus decide — reversibility × blast-radius matrix, batched questions with recommendations attached, proceed-with-stated-assumption. Use when uncertain mid-task, tempted to ask "should I…?", or before destructive, outward-facing, or scope-changing actions. |
Two symmetric failures: asking about things you could resolve yourself (wastes the user's attention, stalls work), and unilaterally deciding things that were the user's call (destroys trust). The line between them is mostly mechanical.
When deciding under mild uncertainty: state the assumption in your report ("I assumed X because Y — say the word if you wanted Z"). This converts a silent gamble into a reviewable decision without blocking.
When operating unattended: take the reversible path, prefer read-only over mutation, default to the safe/test scope, and leave decisions-with-rationale in your report rather than blocking. Destructive actions without standing authorization simply don't happen unattended — leave them as a proposed next step.
