Skip to content

mhrsdev/AI-Agent-Skills-Library / organized-skills/code-quality-testing/mattpocock-skills/skills/misc/git-guardrails-claude-code

git-guardrails-claude-code

Verified

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

FileKindSize
README.mdmarkdown2.6 KB
SKILL.mdskill md2.3 KB
scripts/block-dangerous-git.shscript507 B
# git-guardrails-claude-code

## Purpose
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

## When to Use
Use this skill when a task matches the purpose above, when the original `SKILL.md` trigger language applies, or when an agent needs the preserved behavior from `mattpocock-skills/skills/misc/git-guardrails-claude-code`.

## Inputs
- User request, task brief, codebase context, content brief, design brief, issue/PRD, or files relevant to this skill.
- Any additional inputs, commands, scripts, API keys, assets, or references named in the preserved `SKILL.md`.

## Outputs
- The concrete artifact requested by the skill: code, analysis, design guidance, documentation, issue plan, review, generated content, or operational instructions.
- Any files, reports, scripts, checklists, or structured decisions required by the original skill instructions.

## Core Behavior
1. Read and follow the preserved `SKILL.md` as the source of truth.
2. Use the related files copied with this skill for references, templates, scripts, and data.
3. Preserve the original behavior, constraints, safety notes, edge cases, and workflow ordering.
4. When the skill references another skill or tool, use the dependency list and the original documentation to decide whether to invoke or adapt that behavior.
5. Do not remove or simplify technical details that affect correctness.

## Files
- `mattpocock-skills/skills/misc/git-guardrails-claude-code/SKILL.md`
- `mattpocock-skills/skills/misc/git-guardrails-claude-code/scripts/block-dangerous-git.sh`

## Dependencies
- No explicit cross-skill dependency was detected. Preserve any tools, scripts, APIs, or environment requirements documented in `SKILL.md` and related files.

## Notes
- This README was generated from the migration manifest and is intentionally descriptive rather than replacing `SKILL.md`.
- The copied `SKILL.md` remains the authoritative operational prompt for the skill.
- Original folder contents were preserved before old paths were removed.
- If a referenced external command, package, API, or environment variable is mentioned in the skill files, treat it as required for that specific workflow.

## Original Sources
- Original skill path: `mattpocock-skills/skills/misc/git-guardrails-claude-code`
- Original skill file: `mattpocock-skills/skills/misc/git-guardrails-claude-code/SKILL.md`
- Organized skill path: `organized-skills/code-quality-testing/mattpocock-skills/skills/misc/git-guardrails-claude-code`
- Category: `code-quality-testing`
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall