基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill aget-check-health命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
| name | aget-check-health |
| description | Run AGET health inspection and housekeeping checks |
| allowed-tools | ["Bash","Read","Glob"] |
Run health inspection on an AGET agent. This skill performs sanity checks, validates structure, and reports agent health status.
When this skill is invoked:
Run the housekeeping script:
python3 scripts/aget_housekeeping_protocol.py
The script checks:
.aget/ directory structureversion.json validityidentity.json validity (if exists)governance/ directory contentsReport the health status:
Present the health report:
Sanity Check: [HEALTHY/WARNINGS/ERRORS]
Checks:
- Structure: [PASS/WARN/FAIL]
- Version: [PASS/WARN/FAIL]
- Identity: [PASS/WARN/FAIL]
- Governance: [PASS/WARN/FAIL]
[If warnings/errors, list specific issues]
Recommendations:
- [Action items if any]
--json: Machine-readable output--fix: Attempt auto-fixes for known issues--dir /path: Run on specific agent directory