agent-fault-retrospectivelisted

# Agent Fault Retrospective This skill turns a user-identified agent mistake into durable operating rules. The canonical fault history is the skill's `references/fault.md` file. The goal is not to write a long apology. The goal is to extract the user's judgment, identify the failure mechanism, and maintain short, executable guardrails that future agents can consult. ## Use This Skill When Use this skill when the user says or implies any of the following: - the agent made a mistake, overstepped, or violated instructions - the agent should reflect, review, inspect, postmortem, or do a retrospective - the agent should remember a mistake, record a fault, or update an agent instruction file - the user wants keywords or trigger phrases added so future similar cases automatically invoke this skill - the task mentions fault keywords already recorded in `agent-fault-retrospective/references/fault.md` Trigger examples include: `过失`, `失误`, `错误`, `检讨`, `复盘`, `越权`, `记住这次`, `写进 agents.md`, `写进 claude.md`, `写进 cursor rules`, `自动调用该 skill`, `mistake`, `fault`, `postmortem`, `retrospective`. ## Non-Negotiable Boundaries - Do not defend, debate, or dilute the user's claim that a fault occurred. - After the skill triggers, both Codex and Claude must read the skill's `references/fault.md` before analyzing the fault or editing files. - Treat `agent-fault-retrospective/references/fault.md` as the canonical store for historical fault rules; do not use the global `AGENTS.md` or `CLAUDE.md` a