CtrlK
BlogDocsLog inGet started
Tessl Logo

git-commit

Use when creating git commits to ensure commit messages follow project standards. Applies the 7 rules for great commit messages with focus on conciseness and imperative mood.

68

Quality

83%

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

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 tight, example-driven rule set: every section instructs rather than explains, the heredoc snippet is directly executable, and the good/bad examples with stated problems are the strongest teaching device. The only waste is the checklist duplicating the 7 rules, a small token cost.

DimensionReasoningScore

Conciseness

The body is efficient — it states the 7 rules as terse imperatives without explaining git basics, and the principles add genuinely new guidance ('never reference review feedback', 'avoid bullet points'). It falls short of 5 because the 'Checklist Before Committing' section restates rules 2-7 almost verbatim, a minor duplication that could be trimmed.

4 / 5

Actionability

Fully executable guidance: a copy-paste-ready heredoc git commit command, paired good/bad example messages with the failure mode named ('Problem: Vague subject', 'Problem: Over-explains implementation details'), and a concrete pre-flight checklist. This matches the anchor 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

For this single-task skill the action is unambiguous — apply the rules, use the given heredoc format, then run the explicit 'Checklist Before Committing' as a validation checkpoint before executing. The checklist provides the verification step, so it sits above anchor 4; there is no multi-step sequence to gap, and commits are not a destructive/batch operation that would demand a stronger feedback loop.

5 / 5

Progressive Disclosure

A single self-contained file with no references/scripts/assets bundle; all content (rules, format, examples, checklist) appropriately lives inline at this size, and the section headers make navigation trivial. This matches the simple-skill pattern of well-organized sections earning the top anchor; nothing is inlined that belongs in a separate file.

5 / 5

Total

19

/

20

Passed

Description

73%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 well-formed third-person description with an explicit 'Use when' trigger and a distinct niche. Its main limitation is that the 'what' references a rule set by name without listing concrete capabilities, leaving specificity and completeness just below the top anchors.

Suggestions

Replace the abstract 'follow project standards' with one or two concrete outcomes, e.g. 'Enforce a ≤50-char imperative subject, 72-char wrapped body, and heredoc-safe commit format'.

Add common trigger phrasings such as 'committing changes' or 'writing commit messages' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('commit messages') and references concrete anchors ('Applies the 7 rules for great commit messages with focus on conciseness and imperative mood'), but does not enumerate the actual capabilities (subject-line limits, body wrapping, heredoc format), matching the anchor 'names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because no several specific actions are listed, and not a 2 because the actions named are concrete rather than generic.

3 / 5

Completeness

Both halves are explicit: 'Use when creating git commits' (when) and 'Applies the 7 rules for great commit messages with focus on conciseness and imperative mood' (what). It does not reach 5 because the 'what' stays at the level of named rules rather than concrete trigger-phrase-level detail of what the skill does, matching the anchor 'both what and when; when could be more explicit or specific' — here it is the 'what' that could be more specific.

4 / 5

Trigger Term Quality

'Use when creating git commits' and 'commit messages' are exactly the natural phrases a user would say, giving good keyword coverage. It is short of 5 because common variations like 'committing changes', 'write a commit message', or 'git commit' phrasing are not covered, and above 3 because the core natural terms are present rather than merely relevant.

4 / 5

Distinctiveness Conflict Risk

'Git commits' and 'commit messages' form a clear niche with distinct triggers and minimal overlap with other skills (e.g., code review or PR skills). No generic phrasing that would fire for the wrong skill, matching the anchor 'clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

16

/

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
cloudflare/sandbox-sdk
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.