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 hooks-authoring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。
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。
基于 SOC 职业分类
正在显示 SKILL.md
| name | hooks-authoring |
| description | Author AgentOps runtime hooks. |
Purpose: create or review AgentOps runtime hooks with portable behavior, clear matchers, deterministic tests, and CI-compatible validation.
Execute this workflow. Do not only describe it.
Use this skill when work touches hooks/hooks.json, hooks/*.sh,
lib/hook-helpers.sh, hook schemas, or tests that exercise runtime hooks.
hooks/hooks.jsonhooks/*.shlib/hook-helpers.shschemas/hooks-manifest.v1.schema.jsontests/, scripts/validate-hooks-doc-parity.shset -euo pipefail in shell hooks.eval, backticks, unquoted variables, and implicit globbing.scripts/test-hooks-output.sh.bash scripts/validate-hooks-doc-parity.sh.bash scripts/test-hooks-output.sh when output changes.hooks/, lib/hook-helpers.sh, or
skills/standards/references/ changed, run cd cli && make sync-hooks.$scope.