菜单
Use during hands-on execution of any coding or agent task — especially when following multi-item instructions, deciding how much to deliberate, about to claim something is done, or producing output at risk of reading as generic AI slop.
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
Use when orchestrating multi-agent or long-running work — spawning sub-agents, fanning out parallel tasks, delegating subtasks, running build-then-review loops, or deciding which model tier should do a piece of work.
Use when building a self-contained shippable artifact from scratch or a major rev — an MCP server, a CLI, a library/SDK, a skills pack, a plugin — anything that gets packaged and released rather than merged into an existing app.
Use when maintaining project state across sessions — writing or reading a STATE.md / MEMORY.md, recording what was learned, resuming interrupted work, or deciding what to persist for future sessions.
Use when building or redesigning a product UI/visual system — creating a design system, writing or following a DESIGN.md contract, generating screens in a design tool (Stitch/Figma) then porting to code, or doing a branded visual redesign.
Use when building or running an automated measurement/audit/reporting pipeline that scores many subjects on a recurring basis and reports to stakeholders — a compliance monitor, a benchmark matrix, a metrics dashboard, a scheduled scan-and-report.
Use when planning, building, or reviewing a software milestone/release/version — any task framed as "ship vX", "build the next milestone", "plan and execute a feature set", "do a research + build pass", or "review what we shipped".
| name | execution-rules |
| description | Use during hands-on execution of any coding or agent task — especially when following multi-item instructions, deciding how much to deliberate, about to claim something is done, or producing output at risk of reading as generic AI slop. |
Per-task execution discipline that keeps an agent fast where it should be fast and careful where it should be careful. Complements the orchestration and workflow skills.
This shapes procedure, not capability. Coherence over long tasks and genuine self-correction live in the model's weights, not in a prompt — these rules can't raise a model's reasoning ceiling. On a capable model they reinforce good habits; on a weaker one they impose structure it would otherwise skip, but neither turns the model into a better reasoner. Treat this as a checklist, not a fix for a model that's getting the reasoning wrong. If a task genuinely fits in one direct pass, skip the ceremony and just do it.
When an instruction says "every", "all", "for each", "the N files" — apply it to EVERY case, not the first one. Never silently narrow a batch instruction to a sample. If you do cap scope (top-N, sampling, no-retry), say so explicitly — silent truncation reads as "covered everything" when it didn't.
Extended deliberation pays off ONLY on genuine multi-step reasoning — architecture decisions, subtle bug chains, ambiguous trade-offs. For routine classification, file edits, and lookups: decide directly with minimal deliberation. When in doubt, act and verify with a tool — a cheap tool call beats a long internal debate.
You can hold more context than you need. Once you can act correctly, ACT — don't launch another search wave or re-verify what you already confirmed. Over- exploration is as much a failure as under-exploration. (But "act" includes verifying the result — see below.)
A successful tool call is not proof the change is correct. After a change, run
the smallest meaningful check that validates it, and read the result, before
claiming done. Evidence before assertions, always. Don't re-run a check you've
already seen pass; do run the one you haven't. And when a change misbehaves or
a bug is reported, don't iterate fixes blind — switch to the diagnostic-loop
skill.
Write code and prose that read like a careful human wrote them: match the surrounding code's naming, comment density, and idioms. No robotic headers, no obvious-restatement comments, no padding. Lead with the answer or action; skip preamble. Say what's done plainly when it's verified — and say plainly when it isn't.
See PROVENANCE.md for sources.
