CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

Quality

86%

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

The canonical home for this skill is setup-pre-commit in mattpocock/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.

A tight, executable runbook with literal file contents, a clear step sequence, and built-in verification. The small gaps are a duplicated note, an install command left as package names rather than a concrete invocation, and no feedback loop for failed checks at commit time.

Suggestions

Drop the duplicated shebang note from either step 4 or the Notes section, keeping it in one place.

Replace the package-name-only install step with concrete per-package-manager commands (e.g., npm i -D husky lint-staged prettier / pnpm add -D ...), mirroring the package-manager detection in step 1.

Add a short feedback loop for step 8: if the pre-commit run fails on typecheck/tests, fix the reported errors and re-commit rather than bypassing the hook with --no-verify.

DimensionReasoningScore

Conciseness

The body is lean, well-sectioned, and assumes Claude's competence (no explanations of what Husky or Prettier are), but the shebang fact is stated twice — in step 4 "(no shebang needed for Husky v9+)" and again in Notes "Husky v9+ doesn't need shebangs in hook files" — a minor instance of trimming-able redundancy that keeps it below the 5 anchor.

4 / 5

Actionability

Exact file contents are given for .husky/pre-commit, .lintstagedrc, and .prettierrc, plus concrete commands (npx husky init, lockfile-based package-manager detection, verify checklist). It falls just short of the 5 anchor because the install step lists only the package names ("husky lint-staged prettier") rather than a copy-paste-ready command per package manager.

4 / 5

Workflow Clarity

An explicit 1–8 sequence with a verification checklist (step 7) and a commit-as-smoke-test (step 8), plus adaptation instructions. It misses the 5 anchor because there is no error-recovery feedback loop (e.g., what to do when typecheck or tests fail during the smoke-test commit), while the sequence itself is clearly better defined than the 3 anchor's bare step list.

4 / 5

Progressive Disclosure

The skill is a short, single-purpose setup guide (~85 lines) with no references/, scripts/, or assets/ bundle; nothing that belongs in a separate file is inlined and the sections are well-organized, so per the simple-skill guidance it earns the top score on structure alone.

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 description: explicit what and when, tool-specific triggers, and concrete component enumeration. The only weakness is trigger coverage stopping short of common synonyms like 'git hooks' and of extension/config-file names.

DimensionReasoningScore

Specificity

"Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests" names the domain and several concrete components (Husky, lint-staged, Prettier, type checking, tests). It does not reach a 5 because the coverage hangs off a single 'set up' verb rather than enumerating multiple distinct actions like the 5 anchor, and it is a notch above the 4 anchor only in list length, not in action breadth.

4 / 5

Completeness

Both what ("Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo") and when ("Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing") are explicitly stated with concrete trigger phrases, matching the 5 anchor almost exactly. Neither a missing 'when' (cap at 3) nor a weakly implied one (4) applies.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: "add pre-commit hooks", "set up Husky", "configure lint-staged", "commit-time formatting/typechecking/testing". Common synonyms like "git hooks" are missing, so it does not reach the 5 anchor's comprehensive coverage including synonyms/extensions, but it is clearly above the 3 anchor's 'some relevant keywords missing variations'.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (JavaScript repo pre-commit tooling with Husky/lint-staged) and its triggers are tool-specific, so it is unlikely to fire for unrelated skills, matching the 5 anchor's 'clear niche with distinct triggers; minimal conflict risk'.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tonykay/transcriber

Path

.agents/skills/setup-pre-commit/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.