Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计提醒

hooks-development钩子开发

Agent Skill

hooks-development 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,081

周安装

85

GitHub Stars

38

下载量

673
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hooks-development(钩子开发)
来源仓库:https://github.com/terrylica/cc-skills
仓库路径:skills/hooks-development
安装命令:
npx skills add https://github.com/terrylica/cc-skills --skill hooks-development
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/terrylica/cc-skills --skill hooks-development

简介

用于根据关键词或线索快速查找、检索和筛选相关信息。

  • 适用于需要从大量数据中定位候选结果的研究或开发场景。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装。
  • 支持 Codex、Claude、Cursor、Gemini CLI,安装方式为 github。
  • hooks-development 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Hooks Development

Guide for developing Claude Code hooks with proper output visibility patterns.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

When to Use This Skill

  • Creating a new PostToolUse or PreToolUse hook
  • Hook output is not visible to Claude (most common issue)
  • User asks about decision: block pattern
  • Debugging why hook messages don't appear
  • User mentions "Claude Code hooks" or "hook visibility"

Quick Reference: Visibility Patterns

Critical insight: PostToolUse hook stdout is only visible to Claude when JSON contains "decision": "block".

Output FormatClaude Visibility
Plain textNot visible
JSON without decision: blockNot visible
JSON with decision: blockVisible

Exit code behavior:

Exit Codestdout BehaviorClaude Visibility
0JSON parsed, shown in verbose mode onlyOnly if "decision": "block"
2Ignored, uses stderr insteadstderr shown to Claude
Otherstderr shown in verbose modeNot shown to Claude

Minimal Working Pattern

/usr/bin/env bash << 'SKILL_SCRIPT_EOF'
#!/usr/bin/env bash
set -euo pipefail

# Read hook payload from stdin
PAYLOAD=$(cat)
FILE_PATH=$(echo "$PAYLOAD" | jq -r '.tool_input.file_path // empty')

[[ -z "$FILE_PATH" ]] && exit 0

# Your condition here
if [[ condition_met ]]; then
    jq -n \
        --arg reason "[HOOK] Your message to Claude" \
        '{decision: "block", reason: $reason}'
fi

exit 0
SKILL_SCRIPT_EOF

Key points:

  1. Use jq -n to generate valid JSON
  2. Include "decision": "block" for visibility
  3. Exit with code 0
  4. The "blocking error" label is cosmetic - operation continues

TodoWrite Templates

Creating a PostToolUse Hook

1. [pending] Create hook script with shebang and set -euo pipefail
2. [pending] Parse PAYLOAD from stdin with jq
3. [pending] Add condition check for when to trigger
4. [pending] Output JSON with decision:block pattern
5. [pending] Register hook in hooks.json with matcher
6. [pending] Test by editing a matching file
7. [pending] Verify Claude sees the message in system-reminder

Debugging Invisible Hook Output

1. [pending] Verify hook executes (add debug log to /tmp)
2. [pending] Check JSON format is valid (pipe to jq .)
3. [pending] Confirm decision:block is present in output
4. [pending] Verify exit code is 0
5. [pending] Check hooks.json matcher pattern
6. [pending] Restart Claude Code session

Reference Documentation


Post-Change Checklist (Self-Evolution)

When this skill is updated:


Related Resources


Troubleshooting

IssueCauseSolution
Hook output not visibleMissing decision:block in JSONAdd "decision": "block" to JSON output
JSON parse error in hookInvalid JSON syntaxUse jq -n to generate valid JSON
Hook not executingWrong matcher patternCheck hooks.json matcher regex matches tool name
Plain text output ignoredOnly JSON parsedWrap output in JSON with decision:block
Exit code 2 behaviorstderr used instead of stdoutUse exit 0 with JSON, or exit 2 for stderr messages
Session not seeing changesHooks cachedRestart Claude Code session after hook changes
Verbose mode not showingDisabled by defaultEnable verbose mode in Claude Code settings
jq command not foundjq not installedbrew install jq

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the command succeed? — If not, fix the instruction or error table that caused the failure.
  2. Did parameters or output change? — If the underlying tool's interface drifted, update Usage examples and Parameters table to match.
  3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.

Only update if the issue is real and reproducible — not speculative.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

28.83%
按下载量换算194

Gemini CLI

22.36%
按下载量换算150

Antigravity

17.25%
按下载量换算116

OpenCode

11.17%
按下载量换算75

windsurf

7.11%
按下载量换算48

trae

3.59%
按下载量换算24

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills