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/akillness/oh-my-skills --skill git-guardrails-claude-code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。
One-shot installer for the akillness/oh-my-gods agent skill bundle (80+ skills spanning agent-browser, agent-workflow, ai-research-skills, api-design, and the full god-skills catalog). Use when the user asks to add the oh-my-gods skill pack, bring in the AgenticSkills bundle, or wants every god-skill copied into Claude Code, Codex CLI, Antigravity/Gemini, and OpenCode in one step. Triggers on: AgenticSkills, agenticskills, oh-my-gods, god-skills, install oh-my-gods, bring in agentic skills bundle, install gods skills, add god skills.
Make any software agent-native with HKUDS CLI-Anything — route between four modes: install ready-made CLI harnesses via the CLI-Hub package manager (`pip install cli-anything-hub`, then `cli-hub list/search/info/install/launch`), give agents the autonomous discovery meta-skill (`npx skills add HKUDS/CLI-Anything --skill cli-hub-meta-skill`), generate a new harness from any codebase or GitHub repo via the 7-phase pipeline (`/plugin install cli-anything` → `/cli-anything <path>`), or iterate with `/cli-anything:refine`, `:test`, `:validate`. 40+ production harnesses (GIMP, Blender, LibreOffice, OBS, ComfyUI, Ollama, Godot, QGIS, …), 2,461 passing tests, Click CLIs with REPL + `--json` output. Use when agents must drive real desktop/server software without GUI automation. Triggers on: cli-anything, cli-hub, cli-anything-hub, agent-native cli, make software agent-native, cli harness generation, /cli-anything, harness refine, HKUDS cli.
Run Comet's Opik — open-source LLM observability, evaluation, and optimization — from one routing-first skill: install the Python/TypeScript SDK, stand up a server (Comet.com cloud, Docker Compose via `./opik.sh`, or Kubernetes/Helm), wire tracing through `@opik.track` or one of 50+ framework integrations (OpenAI, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, DSPy, Ollama, Bedrock, Vercel AI SDK, …), score outputs with LLM-as-a-judge metrics (Hallucination, Moderation, Answer Relevance, Context Precision), and run Datasets/Experiments evaluations including PyTest CI gates. Use when the user wants LLM tracing, prompt evaluation, production LLM monitoring, agent optimization, or guardrails with Opik. Triggers on: opik, comet opik, opik configure, opik.sh, llm observability, llm tracing, llm as a judge, hallucination metric, prompt evaluation, opik dashboard, opik guardrails, agent optimizer.
基于 SOC 职业分类
正在显示 SKILL.md
| name | git-guardrails-claude-code |
| description | Use this skill when > |
Prevent Claude Code from executing destructive git operations via PreToolUse hooks.
git-workflowThe guardrail blocks:
git push --force / git push -fgit reset --hardgit clean -f / git clean -fdgit branch -Dgit checkout -- . / git checkout -- <file>git restore (destructive forms)Project-level (recommended for critical repos):
mkdir -p .claude/hooks
Global (for all Claude Code sessions):
mkdir -p ~/.claude/hooks
Save as .claude/hooks/git-guardrails.sh (or ~/.claude/hooks/git-guardrails.sh):
#!/bin/bash
# Blocks destructive git operations
COMMAND="$1"
if echo "$COMMAND" | grep -qE 'git (push --force|push -f|reset --hard|clean -f|clean -fd|branch -D|checkout -- |restore )'; then
echo "BLOCKED: Claude does not have authority to run destructive git operations."
echo "Command attempted: $COMMAND"
echo "If you need this operation, run it yourself in the terminal."
exit 2
fi
exit 0
chmod +x .claude/hooks/git-guardrails.sh
Add to .claude/settings.json (project) or ~/.claude/settings.json (global):
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/git-guardrails.sh"
}
]
}
]
}
}
For global installation, use the full path: ~/.claude/hooks/git-guardrails.sh
echo "git reset --hard" | .claude/hooks/git-guardrails.sh
# Should exit with status 2 and print BLOCKED message
Edit the regex pattern in the script to add or remove blocked operations:
# Add git tag -d to blocked list:
grep -qE 'git (push --force|push -f|reset --hard|clean -f|clean -fd|branch -D|checkout -- |restore |tag -d)'
.agent-skills/skill-standardization/SKILL.md.agent-skills/skill-standardization/scripts/validate_skill.sh