git-guardrails-claude-code

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%Weight 40%Scale 1-5

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

An excellent, lean instruction body: concrete steps, complete configuration snippets, a real referenced bundle script, and an explicit verification step. The only gap is the absence of failure-path guidance after the verification test.

Dimension	Reasoning	Score
Conciseness	Lean and fully operational: every section (blocked list, copy target, chmod, settings JSON, verify test) earns its place with no explanation of concepts Claude already knows, matching the anchor-5 example.	5 / 5
Actionability	Fully executable guidance: exact destination paths for both scopes, chmod +x, two complete copy-paste JSON hook configs, and a concrete verification command with the expected exit code 2 and stderr BLOCKED message.	5 / 5
Workflow Clarity	A clear 5-step sequence with an explicit validation step ("应以 code 2 退出，并向 stderr 打印 BLOCKED message"), but it stops short of anchor 5 because there is no error-recovery feedback loop (e.g., what to do if the test fails, or how to confirm the hook actually fires inside Claude Code).	4 / 5
Progressive Disclosure	Well-organized sections with a single, clearly-signaled, one-level-deep reference to scripts/block-dangerous-git.sh, which exists in the bundle and behaves exactly as the body claims; script content is appropriately kept out of SKILL.md.	5 / 5
	Total	19 / 20 Passed

Description

83%Weight 40%Scale 1-5

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

A strong description that clearly states what the skill does and when to use it, with concrete command names and natural trigger phrases in both Chinese and English. Keyword coverage is good but not exhaustive, and a few natural synonyms are missing.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete blocking targets ("push、reset --hard、clean、branch -D"), but the trailing "等" (etc.) leaves minor coverage gaps and the core action is a single one (setting up hooks), matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both: what it does ("设置 Claude Code hooks，在危险 git commands...执行前阻止它们") and when to use it, with an explicit 适用...时 clause listing concrete trigger scenarios, matching the anchor-5 pattern.	5 / 5
Trigger Term Quality	Good natural keyword coverage including "防止破坏性 git 操作", "git safety hooks", and "阻止 git push/reset", but misses common synonyms users might say such as force push, git guardrails, or protecting branches.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Claude Code git-safety hooks) with distinct triggers scoped to Claude Code, but phrases like "防止破坏性 git 操作" carry minor overlap risk with general git-workflow or git-safety skills, fitting anchor 4.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vinvcn/mattpocock-skills-zh-CN
Path: skills/misc/git-guardrails-claude-code/SKILL.md
Commit: 3f92a83

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.