菜单
Prove a change works before calling it done — build, test, lint, smoke-check, and report pass/fail. Use after any code change, before any commit/PR, and as the self-verify step inside an autonomous loop. Trigger whenever the agent is about to claim a task is complete.
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
Capture a durable lesson every time the human corrects the agent, so the same mistake doesn't recur. Use immediately after any user correction, course-correction, or "no, do it this way". Also use at session start to load relevant past lessons. Trigger on corrections and on session start.
Turn a feature request or task into a written spec before any code is written. Use whenever the user asks to build, add, or implement something non-trivial (3+ steps or an architectural decision), or says "let's design", "write the spec", or "plan this". Produces the spec the human approves and the agent executes against.
Write a failing test first, then the minimum code to pass it. Use for any bug fix or new behavior.
Choose the cheapest sufficient retrieval strategy for a query before answering. Use whenever the system has multiple retrievers (vector, hybrid, graph, metadata, summary) and needs to decide how to fetch evidence for a question. Trigger on any retrieval/QA task where query types are mixed.
Keep a long agent session inside its context window without losing the plot. Use when a session is getting long, tool outputs are large, the agent starts "going off the rails" late in a task, or context usage is high. Trigger on big logs, long transcripts, or before a context-heavy step.
Incrementally compile messy source documents into a persistent, cross-linked Markdown knowledge base instead of re-reading raw docs every time. Use when the user has a pile of documents/notes/tickets and wants durable understanding, a project wiki, an onboarding doc, or asks "summarize everything we know about X" across many sources.
| name | verify-loop |
| description | Prove a change works before calling it done — build, test, lint, smoke-check, and report pass/fail. Use after any code change, before any commit/PR, and as the self-verify step inside an autonomous loop. Trigger whenever the agent is about to claim a task is complete. |
"Done" is a claim, not a proof. An open loop that writes code with no feedback is a machine for generating confident mistakes. This skill is the feedback.
AGENTS.md ## Project → Build). If it fails, fix the cause and repeat.→ Test). For a bug fix, ensure a test reproduces the bug and now passes.→ Lint).main and the change.primitives/subagents/.self_verify() every loop in harness/ and loops/ depends on.