菜单
Classify the task, identify risk, choose a strategy, and set a proof plan before non-trivial work. Use for architecture, migrations, auth, billing, concurrency, large refactors, or whenever failure would be costly.
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
Synchronize the Obsidian vault (Meta-YGN/) with the current codebase state. Use after releases, major changes, or when vault docs may be stale.
Run a minimal metacognitive evaluation pass over the current task or repository change. Use to assess quality, calibration, and overhead.
Pressure-test the current plan or conclusion. Use when reasoning may be too linear, confidence seems too high, or there are plausible counter-hypotheses.
Compact the session into goal, verified facts, dead ends, open risks, and next actions. Use before long sessions, handoffs, context limits, or after repeated failed attempts.
Escalate when uncertainty is too high, risk exceeds agent capability, or human judgment is required. Use when verification fails, threats are found, or the agent is stuck.
Build a proof packet before finalizing work. Use for risky edits, architecture claims, dependency changes, security-sensitive work, and any answer that could mislead a reviewer.
| name | metacog-preflight |
| description | Classify the task, identify risk, choose a strategy, and set a proof plan before non-trivial work. Use for architecture, migrations, auth, billing, concurrency, large refactors, or whenever failure would be costly. |
| user-invocable | true |
| argument-hint | [task description] |
| allowed-tools | Read, Grep, Glob, Bash |
Before acting, produce a compact preflight for $ARGUMENTS:
Task type
Risk level
Failure cost
Strategy (pick one)
Proof plan Name the smallest checks that would prove or falsify success (tests, grep, type check, build, manual inspection).
Tool plan Explicitly state which tools are truly necessary and which can be skipped.
Risk: {level}
Strategy: {chosen}
Proof plan: {checks}
First action: {next step}