CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured, actionable skill body with a clear sequenced workflow, a verification checkpoint, and a cleanly signaled reference to its bundled script. Strengthening the verify feedback loop and replacing prose/placeholder commands with literal ones would round it out.

Suggestions

Make the error-recovery loop explicit in Step 5: 'if the test does not exit with code 2 or prints no BLOCKED message, review the script and settings, then re-run the test.'

Replace the prose '用 chmod +x 让它可执行' with a literal command (e.g. `chmod +x .claude/hooks/block-dangerous-git.sh`) for each scope.

In the Verify step, give the concrete script path per scope instead of the <path-to-script> placeholder so the test is fully copy-paste runnable.

DimensionReasoningScore

Conciseness

Mostly lean and free of padding, with concrete steps and config blocks rather than explanations of concepts Claude already knows; a few lines ('用 chmod +x 让它可执行', the blocked-message note) could be tightened into direct commands.

4 / 5

Actionability

Provides copy-paste-ready JSON config for both project and global scopes plus a concrete verify command with expected exit code, but chmod is described in prose and the verify step uses a <path-to-script> placeholder, leaving minor gaps.

4 / 5

Workflow Clarity

Five clearly sequenced steps include an explicit Verify checkpoint with expected output (exit code 2, BLOCKED message), satisfying the destructive-operation validation requirement; the error-recovery feedback loop (fix and re-verify on failure) is only implicit rather than spelled out.

4 / 5

Progressive Disclosure

The body is a concise overview that points to the bundled implementation via a clearly signaled one-level-deep markdown link ([scripts/block-dangerous-git.sh](scripts/block-dangerous-git.sh)), with content appropriately split between inline essentials and the external script.

5 / 5

Total

17

/

20

Passed

Description

87%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, specific description that clearly answers both what the skill does and when to use it, with natural trigger phrasing and low conflict risk. Minor additional synonyms could push trigger coverage to fully comprehensive.

DimensionReasoningScore

Specificity

Names concrete actions ('设置 Claude Code hooks', '在危险 git commands...执行前阻止它们') and enumerates specific commands (push, reset --hard, clean, branch -D), giving specific guidance for a focused single-purpose skill rather than vague abstraction.

4 / 5

Completeness

Explicitly states both what it does ('设置...hooks...阻止它们') and when to use it ('适用于用户想防止...添加...或...阻止...时') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say — '防止破坏性 git 操作', '添加 git safety hooks', '阻止 git push/reset' — with good synonym coverage, though a few natural variants (e.g. 'guardrails', 'protect') are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code git safety hooks blocking destructive commands) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vinvcn/mattpocock-skills-zh-CN
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.