CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Write conventional commit messages with type, scope, and subject when the user wants to commit changes or save work.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 well-structured, highly actionable skill body with executable examples and a clear verified workflow, appropriately offloading extended examples to a single real reference file. Minor opportunities exist to tighten speculative sections and move the merge-commit example into the reference.

Suggestions

Move the long 'gh pr create' merge-commit heredoc into references/commit_examples.md and keep only a brief pointer inline, improving both conciseness and progressive_disclosure.

Trim or drop the 'Integration with Other Skills' section, which reads as speculative cross-skill marketing rather than commit-authoring guidance.

Add a brief feedback loop after the Verify step (e.g., 'if the message is wrong, git commit --amend and re-verify') to strengthen workflow_clarity for a destructive operation.

DimensionReasoningScore

Conciseness

Mostly lean — tables of types/scopes and executable bash snippets with no explaining of basic git concepts — but the speculative 'Integration with Other Skills' section and the long merge-commit heredoc could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready examples covering simple and complex commits, plus a types table, scope examples, and good/bad contrast pairs — concrete guidance across common cases.

5 / 5

Workflow Clarity

Clear 4-step sequence (Review → Stage → Commit → Verify) with an explicit verification step, but it lacks an explicit error-recovery/feedback loop (e.g., amend if verification reveals a problem), leaving a minor validation gap.

4 / 5

Progressive Disclosure

Well-organized overview with a real one-level-deep reference (references/commit_examples.md, signaled twice); however the lengthy gh pr create heredoc is arguably material that belongs in that reference file.

4 / 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, third-person description that concretely states the capability and an explicit trigger condition, scoring well across all dimensions. The only slight gap is keyword synonym coverage (e.g., 'git commit').

DimensionReasoningScore

Specificity

Lists several concrete actions — composing commit messages with 'type, scope, and subject' — but does not enumerate the broader workflow (bodies, trailers, breaking changes), leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (write conventional commit messages with type, scope, and subject) and 'when' (when the user wants to commit changes or save work) with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say ('commit changes', 'save work') alongside 'conventional commit messages'; good coverage, though synonyms like 'git commit' or 'commit message' are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — conventional commit message authoring — with distinct triggers and minimal overlap with other skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
marchatton/agent-skills
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.