CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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.

A tight, fully actionable single-file skill: every step has an executable git command, validation checkpoints and hook-failure recovery are explicit, and nothing explains concepts Claude already knows. The only trims available are the intro paragraph restating the description and minor redundant phrasing in step 4.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's git competence — no explanation of what commits or hooks are, every guideline is a guardrail. Two minor instances could be trimmed: the opening paragraph restates the frontmatter description, and 'Construct the git commit command with the generated message. Execute the commit:' is redundant phrasing. That matches the 'minor instances of over-explanation' anchor rather than perfect leanness.

4 / 5

Actionability

Fully executable, copy-paste-ready commands at every step: 'git log --oneline -20', 'git status --short', 'git diff --cached', 'git commit -m "<subject>" -m "<body>"', plus explicit handling rules for staged vs unstaged changes and hook outcomes. Specific and complete for the common cases.

5 / 5

Workflow Clarity

A clearly sequenced 5-step workflow with explicit validation checkpoints: the stop condition on a clean tree, post-commit verification via 'git status --short' and 'git log --oneline -1', and an explicit error-recovery path for pre-commit hooks ('do not amend automatically. Tell the user what changed and ask...'). Feedback loops are present, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), and none are needed: this is a single-purpose skill whose content fits comfortably in one file, organized into a Guidelines section and a numbered Workflow with clear headers. Structure and placement are appropriate with no buried or inlined-overflow content.

5 / 5

Total

19

/

20

Passed

Description

95%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 about what it does, and paired with an explicit 'Use when' clause listing five natural trigger phrases including synonyms. Only minor coverage gaps in the what (convention detection, diff analysis) keep specificity from the top anchor.

DimensionReasoningScore

Specificity

Concrete actions are stated in third person — 'Commit staged or unstaged changes', 'AI-generated commit message', 'matches the repository's existing commit style' — giving several specific actions with minor coverage gaps (no mention of convention detection or diff analysis). It exceeds the 1-2-action anchor below but falls short of comprehensive coverage.

4 / 5

Completeness

Explicitly answers both: what ('Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style') and when ('Use when the user asks to...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Five natural quoted phrases users would actually say — 'commit', 'commit changes', 'create a commit', 'save my work', 'check in code' — including non-obvious synonyms. Coverage is comprehensive for this domain; there are no natural variants missing (file extensions don't apply).

5 / 5

Distinctiveness Conflict Risk

Clear niche (git commit operation) with distinct trigger phrases; overlaps minimally with adjacent skills (e.g. commit-message drafting), mirroring the rubric's own good commit-related example.

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
posit-dev/positron
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.