القائمة
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.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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.
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.
| name | metacog-proof |
| description | 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. |
| user-invocable | true |
| context | fork |
| agent | general-purpose |
| allowed-tools | Read, Grep, Glob, Bash |
Build the smallest proof packet that a skeptical reviewer would trust.
Separate the result into:
State the task in one sentence.
What is being asserted (code works, design is sound, migration is safe, etc.).
List concrete evidence: files read, patterns found, docs checked.
List verification commands executed and their results:
Honestly list what could not be checked with available tools.
The single smallest action that would increase confidence or reduce risk.
Rules:
[confirmed], [experimental], or [unverified].