菜单
Catch the algorithmic and I/O performance classics before shipping — O(n²) on unbounded input, N+1 queries, sync calls in hot/async paths, unbounded memory. Use when writing loops over data of unknown size, database access in loops, or anything on a request path.
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 | perf-sanity |
| description | Catch the algorithmic and I/O performance classics before shipping — O(n²) on unbounded input, N+1 queries, sync calls in hot/async paths, unbounded memory. Use when writing loops over data of unknown size, database access in loops, or anything on a request path. |
Not optimization — just refusing to ship the five classics that account for most real slowdowns:
for x in items: if y in items) is O(n²); fine at 100 items, dead at 100k. If the input size is unbounded (user data, DB rows, log lines), use a set/map lookup. Know which of your inputs are unbounded.for row in rows turns one round-trip into a thousand. Batch it: WHERE id IN (...), a join, or the API's bulk endpoint. Same for file opens and subprocess spawns in loops.sleep inside an async handler stalls the event loop for everyone. Use the async client or move it off-path.Calibration: don't micro-optimize (that's scope creep — see scope-discipline); a readable O(n) beats a clever O(n log n) hack. The bar is "no complexity-class surprises on realistic input sizes." When unsure what's realistic, check the actual data: SELECT COUNT(*), wc -l.