CtrlK
BlogDocsLog inGet started
Tessl Logo

git-guardrails-claude-code

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.

97

1.19x
Quality

96%

Does it follow best practices?

Impact

100%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is git-guardrails-claude-code in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, actionable skill that efficiently guides Claude through setting up git guardrails. The workflow is clear with proper sequencing and a verification step. The only minor weakness is the reference to a bundle script that isn't provided, making it hard to fully assess progressive disclosure, though the overall organization is sound.

DimensionReasoningScore

Conciseness

The content is lean and efficient. Every section serves a clear purpose—no unnecessary explanations of what git commands do or how hooks work conceptually. It assumes Claude knows git and JSON configuration.

3 / 3

Actionability

Provides fully concrete, copy-paste ready JSON configurations for both project and global scope, exact file paths, chmod command, and a specific verification command with expected output behavior. The merge instruction for existing settings is a valuable specific detail.

3 / 3

Workflow Clarity

Clear 5-step sequential workflow with explicit verification at the end (step 5 tests the hook with expected exit code and output). The sequence is logical: scope → copy → configure → customize → verify, with a validation checkpoint before completion.

3 / 3

Progressive Disclosure

References the bundled script at `scripts/block-dangerous-git.sh` which is appropriate, but no bundle files were provided to verify the reference. The inline JSON configs are appropriately placed since they're short, but the skill could benefit from clearer signaling if the bundle script contains customizable patterns.

2 / 3

Total

11

/

12

Passed

Description

100%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly communicates what the skill does (sets up hooks to block dangerous git commands), provides specific examples of the commands it targets, and explicitly states when to use it with natural trigger terms. It is concise, uses third person voice, and occupies a distinct niche that minimizes conflict risk with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'block dangerous git commands' with explicit examples '(push, reset --hard, clean, branch -D, etc.)' and specifies the context 'Claude Code hooks' and timing 'before they execute'.

3 / 3

Completeness

Clearly answers both what ('Set up Claude Code hooks to block dangerous git commands before they execute') and when ('Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'dangerous git commands', 'git push', 'reset --hard', 'git safety hooks', 'block git push/reset', 'destructive git operations', 'Claude Code hooks'. Good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche combining Claude Code hooks + git safety/blocking. Unlikely to conflict with general git skills or general hooks skills due to the specific focus on blocking dangerous git commands.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
SnowingFox/ai-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.