CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit-conventions

Use when the user asks for a commit message or wants help summarizing staged changes, e.g. "write a commit" or "git commit message". Reads the staged diff, picks the Conventional Commits type (feat, fix, refactor, docs, test, perf, chore), and writes an imperative subject of at most 72 characters, adding a body only for breaking changes, migrations or security fixes.

75

Quality

94%

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 commit-conventions in chandler767/WorkJournal

SKILL.md
Quality
Evals
Security

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 exemplary compact skill body: lean, immediately actionable, and unambiguous. The only improvement is an explicit verification step in the workflow, such as confirming the subject fits the 72-character limit before presenting the message.

Suggestions

Add a final checklist step, e.g., 'Verify the subject, including the type prefix, is at most 72 characters before presenting the message.'

DimensionReasoningScore

Conciseness

Every section earns its place: a 5-step procedure, a 7-row decision table, and four subject rules — no explanations of concepts Claude already knows and no padding. This matches the level-5 'lean and efficient' anchor; the level-4 anchor would require over-explanation that could be trimmed, and none is present.

5 / 5

Actionability

Fully executable guidance: the exact command 'git diff --cached', the message template '<type>(<optional scope>): <subject>', a decision table with concrete criteria (e.g., 'Adds behavior a user or caller can now use. Empty files and stubs don't count'), and precise subject rules. Per the scoring notes, an instruction-only skill with this level of concrete guidance merits the top anchor.

5 / 5

Workflow Clarity

A clear, well-sequenced 5-step workflow with an explicit safety note ('Do not commit, just suggest it to the user'), but no validation checkpoint (e.g., verify the subject fits 72 characters including the type prefix, or confirm the chosen type covers all staged files). This sits between the level-4 'minor validation gaps' and level-5 'explicit validation steps' anchors; since the operation is non-destructive the hard cap does not apply, but the missing checkpoint keeps it at 4 rather than 5.

4 / 5

Progressive Disclosure

This is a sub-50-line, single-purpose skill with no bundle files and no need for external references; the body is well-organized into clearly headed sections ('When you're triggered', 'What to do', 'Type table', 'Subject line rules'). Per the rubric's simple-skill guidance, that merits the top score.

5 / 5

Total

19

/

20

Passed

Description

92%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: third-person, concrete, and explicit about both capability and triggers, with example user phrasings. The only minor gap is trigger synonym coverage beyond 'commit message' phrasings.

Suggestions

Add one or two more natural trigger variations such as 'make a commit' or 'commit these changes' to broaden the match surface for users who don't use the word 'message'.

DimensionReasoningScore

Specificity

Multiple concrete, specific actions are listed — 'Reads the staged diff', 'picks the Conventional Commits type (feat, fix, refactor, docs, test, perf, chore)', 'writes an imperative subject of at most 72 characters, adding a body only for breaking changes, migrations or security fixes' — with concrete constraints rather than generic verbs. This matches the top anchor for comprehensive, concrete coverage; the level-4 anchor would imply gaps in coverage, but the description covers read, classify, write, and body-policy.

5 / 5

Completeness

It explicitly answers both questions: what ('Reads the staged diff, picks the Conventional Commits type... and writes an imperative subject of at most 72 characters') and when ('Use when the user asks for a commit message or wants help summarizing staged changes, e.g. "write a commit"'), with concrete example trigger phrases. This is a direct match to the level-5 anchor; the level-4 anchor would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are present — 'commit message', 'git commit message', 'write a commit', 'summarizing staged changes' — giving good coverage. Falls short of the level-5 anchor's comprehensive synonym coverage (e.g., 'make a commit', 'commit these changes', 'finish the commit') which could be added as variations.

4 / 5

Distinctiveness Conflict Risk

A clear niche — Conventional Commits message drafting for staged changes — with distinct triggers that would not fire for general git help or other skills. Minimal overlap risk; matches the level-5 anchor of a clear niche with distinct triggers.

5 / 5

Total

19

/

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

chandler767/WorkJournal

Path

plugins/git-hygiene/skills/commit-conventions/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.