CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Read this skill before making git commits

55

Quality

69%

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 ./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 body is an exemplary compact instruction skill: lean, fully concrete commands, a precise format spec, and a well-sequenced workflow with an ask-before-commit checkpoint. Its only weaknesses are the absence of a worked example subject and any post-commit verification step.

DimensionReasoningScore

Conciseness

The body is ~30 lean lines with zero padding: no explanation of what git is, no commit-message theory, and every line is a constraint or command ("<= 72 chars, no trailing period", "git commit -m \"<subject>\""). This matches anchor 5 ("Lean and efficient; assumes Claude's competence; every token earns its place") — nothing could be cut without losing guidance.

5 / 5

Actionability

Guidance is concrete and near-executable: the exact format `<type>(<scope>): <summary>` with required/optional fields, permitted types, and copy-runnable commands (`git status`, `git diff`, `git log -n 50 --pretty=format:%s`, `git commit -m "<subject>"`). It stops short of anchor 5 ("specific examples cover the common cases") because no example subject or full example commit is shown, leaving a minor gap.

4 / 5

Workflow Clarity

The six steps form a clear, ordered sequence with a genuine checkpoint (step 4: "ask the user for clarification before committing" on ambiguous files) and pre-flight review (steps 2–3). It fits anchor 4 ("Clear sequence with most checkpoints present; minor validation gaps") — the missing piece is any post-commit verification that the commit succeeded as intended, which keeps it below anchor 5.

4 / 5

Progressive Disclosure

This is a sub-50-line single-purpose skill with no external references needed, and it uses clear sections (## Format, ## Notes, ## Steps) with a one-line purpose statement up top. Per the rubric's simple-skill rule, well-organized sections alone justify anchor 5 ("Clear overview with... easy navigation").

5 / 5

Total

18

/

20

Passed

Description

36%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 functions purely as a trigger ("Read this skill before making git commits") with zero capability content: no what, no concrete actions, and only one keyword phrase. It reads like an internal instruction to Claude rather than a description, and it caps out well below what the rubric treats as effective.

Suggestions

State what the skill does in third person, e.g. "Creates git commits with concise Conventional Commits-style subjects, staging only the intended files" — this fixes the missing 'what' that caps completeness.

Expand trigger coverage with natural variations users actually say: "Use when the user asks to commit, check in, save, or record changes, or mentions a commit message."

Add distinguishing detail (Conventional Commits format, argument-driven file staging) so the description cannot be confused with commit-message-writing or hook-related skills.

DimensionReasoningScore

Specificity

The description names the domain ("making git commits") but performs no capability listing — it only says "Read this skill before", which is an access instruction, not an action. This matches anchor 2 ("Names the domain but actions are minimal or generic", e.g. "Processes PDF files"); it is above anchor 1 because the domain is concrete, and below anchor 3 because no concrete actions (e.g., writing Conventional Commits subjects, staging files) are stated.

2 / 5

Completeness

Only the "when" is present ("before making git commits") with no "what" — the description never says what the skill does. This is exactly anchor 2's pattern ("only 'when' is present without 'what'", e.g. "Use when working with documents"); it cannot reach anchor 3 because there is no clear 'what' at all.

2 / 5

Trigger Term Quality

"making git commits" is a genuinely natural phrase users would say, so this is above anchor 2's generic keywords ("Works with files"). It stays at anchor 3, however, because common variations and synonyms are missing: "commit message", "commit these changes", "stage", "check in", "checkin".

3 / 5

Distinctiveness Conflict Risk

"git commits" carves out a real niche, but the bare description gives nothing to distinguish this commit skill from closely related ones (commit-message generation, pre-commit hooks, PR-creation skills), so overlap risk remains. It is above anchor 2 ("Helps with document files" — broad overlap with many skills) but below anchor 4, which requires mostly-distinct triggers, because no scope detail is given.

3 / 5

Total

10

/

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
mitsuhiko/agent-stuff
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.