CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

writing-commit-messages

Writes Git commit messages. Activates when the user asks to write a commit message, draft a commit message, or similar.

Quality

84%

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

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 a lean, well-structured, project-specific instruction set with concrete rules and a clear workflow. Its only gaps are the absence of a worked example commit message and of explicit validation steps in the workflow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no explanation of what git or commits are, only project-specific rules ("Use nested subsystems with `/` when helpful", "Wrap lines at ~72 characters", "If `.jj` is present, use `jj` instead of `git"). Every token carries information Claude could not infer, matching 'Lean and efficient; every token earns its place'.

5 / 5

Actionability

Guidance is concrete and executable: an exact format template, specific rules (lowercase imperative subject under 60 chars, references as `#1234` on their own lines, ~72-char wrap), and a workflow with commands ("Run a diff", "use `jj` instead of `git`"). It falls short of a 5 only because there is no worked example commit message showing the style end-to-end.

4 / 5

Workflow Clarity

The Workflow section gives a clear, ordered sequence (check for `.jj`, run a diff, identify subsystem, identify references, draft, apply, "Don't push the commit") with a safety boundary at the end. It lacks explicit validation checkpoints (e.g., verifying the subject length or that the subsystem matches the diff), so it does not reach the explicit validate-and-recover level of a 5; a single commit is not a destructive/batch operation, so no cap applies.

4 / 5

Progressive Disclosure

This is a simple single-task skill with no bundle files (references/, scripts/, assets/ are absent) and no need for external references; all ~50 lines belong inline. Sections (Format, Rules with subsections, Workflow) are well-organized and easy to navigate, which per the simple-skill guidance earns a 5 with just well-organized sections.

5 / 5

Total

18

/

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.

The description explicitly covers both what the skill does and when it activates, with natural trigger phrases and a distinct niche. Its main weakness is a thin 'what' — a single action with no detail on the skill's actual capabilities — plus the vague 'or similar' tail.

Suggestions

Expand the 'what' with 2-3 concrete capabilities, e.g., 'Writes Git commit messages by analyzing the diff, inferring the subsystem prefix, and following the project's commit style guidelines.'

Replace 'or similar' with additional concrete triggers such as 'commit', 'git commit', or 'message for this commit' to broaden natural keyword coverage.

State the full behavior in the 'what', including that the skill applies the commit locally but never pushes.

DimensionReasoningScore

Specificity

"Writes Git commit messages" names the domain and a single concrete action, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It does not list several actions (e.g., analyzing diffs, following project style, applying the commit), so it is not a 4.

3 / 5

Completeness

Both parts are present: 'what' ("Writes Git commit messages") and an explicit 'when' ("Activates when the user asks to write a commit message, draft a commit message, or similar"). The 'when' is explicit, but the 'what' is minimal (it omits that messages follow project style and that the skill applies the commit) and "or similar" is a vague catch-all, so it falls just short of the fully concrete what+when of a 5.

4 / 5

Trigger Term Quality

"write a commit message, draft a commit message" are natural phrases users would say, giving good keyword coverage. A few natural variants are missing (e.g., 'commit', 'git commit', 'commit msg'), which keeps it below the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"Git commit messages" is a clear niche with distinct, specific triggers ('write a commit message', 'draft a commit message'), giving minimal conflict risk with other skills. It is far more specific than the 'minor overlap risk with closely related skills' of a 4.

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

KennethJefferson/HerdrPlus

Path

__references/herdr/vendor/libghostty-vt/.agents/skills/writing-commit-messages/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.