CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit

Stage and create a Conventional Commits message for the current change

Quality

78%

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

92%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 body is a strong, tight instruction skill: concrete git commands, an explicit commit-message template, safety rules, and a validation feedback loop. Its only weakness is the conventional-types table, which largely re-teaches standard knowledge Claude already has.

DimensionReasoningScore

Conciseness

The body is command-first and lean with no padding, but the 11-row Types table restates the standard Conventional Commits type taxonomy Claude already knows. Fits anchor 4 (efficient, minor trimmable over-explanation) rather than 5, where every token must earn its place.

4 / 5

Actionability

Concrete, executable commands throughout ("git status", "git diff --staged", "git log --oneline -10", "git add -p"), a fill-in message template, and hard rules like "Never use `--no-verify`". Fully executable guidance covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Six clearly sequenced steps with an explicit feedback loop ("If pre-commit hooks fail, fix the cause and re-commit") and validation guardrails (no secrets, protected `main` branch). Matches anchor 5's clear sequence with explicit validation and error-recovery loop.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references; the body is well-organized into Steps, Types, and Notes sections, and no bundle files exist that should be split out. Per the rubric's simple-skill guidance this earns anchor 5 on well-organized sections alone.

5 / 5

Total

19

/

20

Passed

Description

53%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 states a clear, concrete "what" but entirely lacks a "when to use" trigger clause, which caps both completeness and trigger coverage. It is short and specific, yet misses the natural phrases and explicit invocation cues that would make it reliably surfaced.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to commit changes, write a commit message, or stage a diff."

Include natural keyword variations users actually say ("git commit", "make a commit", "commit this change") to improve trigger term coverage.

Name one or two more concrete capabilities (e.g. reviewing diff/history for style, splitting mixed working trees into focused commits) to round out specificity.

DimensionReasoningScore

Specificity

"Stage" and "create a Conventional Commits message" name the domain with two concrete actions, but coverage is not comprehensive (no mention of reviewing history, hook handling, or selective staging). This matches anchor 3 (domain + 1-2 concrete actions) rather than 4, which expects several specific actions.

3 / 5

Completeness

The "what" is clear (stage changes and write a Conventional Commits message), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2, because the "what" half is concrete rather than vague.

3 / 5

Trigger Term Quality

"commit", "Conventional Commits", and "stage" are relevant keywords, but common natural variations users would say ("git commit", "make a commit", "commit this change") are missing. Fits anchor 3 (some relevant keywords, missing common variations) rather than 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

"Conventional Commits message for the current change" carves a mostly distinct niche with minor overlap risk against generic git-staging or release skills. Not 5, because without explicit trigger phrases the distinction rests on the format mention alone.

4 / 5

Total

13

/

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

EverMind-AI/EverOS

Path

.claude/skills/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.