CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

git-hooks-automation

Master Git hooks setup with Husky, lint-staged, pre-commit framework, and commitlint. Automate code quality gates, formatting, linting, and commit message enforcement before code reaches CI.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/git-hooks-automation/SKILL.md

The canonical home for this skill is git-hooks-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

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.

Highly actionable, executable content with clear per-framework sequences and useful troubleshooting, slightly held back by a monolithic structure that inlines framework-specific detail instead of splitting it into reference files. Minor trimming of known-concept explanations and explicit post-setup verification steps would lift it further.

Suggestions

Split framework-specific detail into one-level-deep reference files (e.g., references/husky.md, references/pre-commit-framework.md, references/custom-hooks.md) and keep SKILL.md as a decision-oriented overview linking to them.

Add an explicit post-setup verification step to each workflow (e.g., make a test commit and confirm the hook fires) to close the validation gap.

Trim the "Git Hooks Fundamentals" prose and hook-types table, which restate concepts Claude already knows, down to the one non-obvious fact (hooks are local-only and unversioned).

DimensionReasoningScore

Conciseness

The body is dominated by executable configs and commands with almost no padding; only minor known-concept explanation ("Git hooks are scripts that run automatically at specific points..." and the hook-types table) could be trimmed. Not 5 because the fundamentals prose and the directory-structure recap restate what Claude already knows.

4 / 5

Actionability

Fully copy-paste-ready bash, JSON, and YAML covering Husky v9 init, lint-staged config, commitlint, the pre-commit framework, custom hook scripts, core.hooksPath sharing, CI workflows, and migration. Specific executable examples cover the common cases across all three approaches.

5 / 5

Workflow Clarity

Each framework's setup is a clear ordered sequence, the pitfalls table provides error-recovery guidance, and "pre-commit run --all-files" acts as a first-run validation. Not 5 because most setups lack an explicit checkpoint verifying the hook actually fires (e.g., a test commit); not 3 because sequences and recovery paths are otherwise present.

4 / 5

Progressive Disclosure

The single ~410-line file is well-sectioned but monolithic: per-framework detail (the full pre-commit YAML, CI workflow YAML, migration guide) is inline content that belongs in one-level-deep reference files, and no bundle references exist. Not 4 because nothing is split out and navigation is by scroll rather than signaled references.

3 / 5

Total

16

/

20

Passed

Description

66%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, tool-specific description with concrete actions and good trigger keywords, undermined by the complete absence of a "Use when..." trigger clause, which caps completeness. Adding explicit usage triggers and a few more natural synonyms would round it out.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to set up git hooks, pre-commit checks, or commit message linting, or mentions Husky, lint-staged, pre-commit, or commitlint."

Include additional natural trigger terms like "pre-push", "githooks", and file paths (.husky/, .pre-commit-config.yaml) to broaden keyword coverage.

Mention pre-push test automation in the capability list so the description matches the skill's full scope.

DimensionReasoningScore

Specificity

"Automate code quality gates, formatting, linting, and commit message enforcement" lists several specific actions backed by named tools (Husky, lint-staged, pre-commit, commitlint). It falls short of 5 because testing/pre-push test automation covered in the body is missing from the description.

4 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. Not 4 because the "when" is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "Git hooks", "Husky", "lint-staged", "pre-commit framework", "commitlint". Not 5 because common variations like "pre-push", "githooks", and file extensions (.husky, .pre-commit-config.yaml) are absent.

4 / 5

Distinctiveness Conflict Risk

Named tools (Husky, lint-staged, commitlint) create a clear git-hooks niche with minimal conflict risk. Not 5 because "before code reaches CI" and commit-message enforcement create minor overlap with generic CI/CD and commit-message-writing skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/git-hooks-automation/SKILL.md

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.