CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Stage and create a Conventional Commits message for the current change

63

Quality

73%

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 ./.claude/skills/commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The content is a tight, well-structured operational guide with concrete commands, a format template, and a meaningful error-recovery loop. Its only real gap is the absence of a fully worked commit-message example.

Suggestions

Add one concrete worked example of a complete Conventional Commits message (with scope and a body) to make the template copy-paste ready.

Promote the pre-commit feedback loop into an explicit numbered validation checkpoint (e.g. a "Verify" step) so the sequence reads as validate -> fix -> retry.

Optionally note the gitlint enforcement point as the validation gate so the recovery loop is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's git/Conventional Commits competence: no padding, no explaining what git is, just a compact format template, a type table, and focused notes — every token earns its place.

5 / 5

Actionability

Concrete commands (git status/diff/log, git add -p) and a precise format template give mostly executable guidance, but there is no worked example of a complete commit message to copy-paste, a minor gap.

4 / 5

Workflow Clarity

A clear six-step sequence includes a feedback loop ("If pre-commit hooks fail, fix the cause and re-commit") and a guardrail against committing secrets to main; it stops short of an explicit numbered validation checkpoint, leaving a minor gap.

4 / 5

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines with no bundle files, yet it is cleanly sectioned (Steps, Types, Notes) and well-organized, meeting the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

61%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.

The description is concise and names a concrete, distinctive capability, but it lacks an explicit "Use when..." trigger clause, which caps completeness and leaves the activation context implicit.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to commit changes, write a commit message, or stage and commit the current change."

Broaden trigger-term coverage with synonyms users naturally say ("git commit", "make a commit", "commit my changes").

Consider naming the scope/breaking-change handling to round out the specificity of capabilities.

DimensionReasoningScore

Specificity

Names the Conventional Commits domain and two concrete actions ("Stage and create a Conventional Commits message"), but the action set is not comprehensive — it omits scope/breaking-change handling and the actual type taxonomy present in the body.

3 / 5

Completeness

It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("commit", "commit message", "stage", "Conventional Commits"); a few common variations like "git commit" or "make a commit" are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The Conventional Commits framing carves a clear niche distinct from a generic git skill, with only minor overlap risk against a broader version-control helper.

4 / 5

Total

14

/

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
EverMind-AI/EverOS
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.