菜单
Handle unexpected situations where things are not working as expected. Use when you encounter errors, confusing state, or behavior that contradicts your docs and prompts.
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
Run the background harden pass for one artifact -- crystallize, update, or heal a skill, a service, or the system interface in an isolated worktree, then report back. Invoke when your task file hands you an artifact to harden; it names the operation and artifact to compose.
Promote the just-finished work into a new, reusable, committed, tested skill. Use when that process would recur with new inputs -- especially something you figured out through research or debugging -- or when the user says 'crystallize this'.
Fetch data from somewhere (an external service, an API, a third-party source), process it, and show it to the user -- the "go get all this stuff, do something to it, and put it in front of me" task. Use when the ask is to retrieve real data, transform/summarize/classify it, and surface the result. Validates auth first, confirms a real sample covering every data shape, then crystallizes the pipeline in the background while building surfaces.
Use when writing or reasoning about code that calls Claude -- an AI-driven service, an AI integration, or a skill's scripted model step. Covers the three scenarios (one-shot completion, one-shot agentic task, full agent) and the cost / credentialing model.
Fix an existing artifact that errored or delivered a wrong result. This applies to skills or web services. Invoke at turn-end, after you worked around the failure to satisfy the user's request.
Create a sub-agent to perform a larger task. Use when work is large enough to warrant a separate context, involves multi-file changes, or benefits from isolation.
| name | dealing-with-the-unexpected |
| description | Handle unexpected situations where things are not working as expected. Use when you encounter errors, confusing state, or behavior that contradicts your docs and prompts. |
When something unexpected happens, follow this procedure:
Before doing anything, understand what is actually happening:
tmux list-windows -t $(tmux display-message -p '#S')supervisorctl status (compare against the programs defined in supervisord.conf)cat runtime/wait_counter 2>/dev/null || echo "no counter"Common issues and their causes:
supervisorctl status and read the service's logs under /var/log/supervisor/<name>-stderr.log (or supervisorctl tail -f <name> stderr). The bootstrap tmux window shows supervisord's own output. Verify supervisord.conf is valid, then supervisorctl reread && supervisorctl update.runtime/wait_counter contents. Delete it to reset: rm -f runtime/wait_counterIf you can fix the issue yourself (edit a config, restart a service, etc.), do so and commit the fix.
If you cannot fix the issue, tell the user:
You are a persistent agent. Even if something is broken, you will keep running. Focus on what you can do, communicate clearly with the user, and wait for help if needed.