CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

generate-commit-message

Review staged git changes, then draft a commit message and commit after approval. Intended for an agent that did not write the changes (e.g., a fresh session); the session that wrote them should use `review-and-commit` instead. Accepts optional arguments specifying the model name (e.g., `/generate-commit-message Gemini Flash 3.8 (Medium)`). Use this when the user wants a reviewed commit message for the staged changes.

Quality

91%

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 an exemplary routing skill: it delegates to a canonical operation by exact skill and file name, maps its two parameter overrides to specific steps of that operation, states a guardrail against duplicating the process, and defines scope boundaries. Its only weakness is slight redundancy between the opening line, the description, and the closing purpose statement. All four dimensions land at or near the top of the scale.

DimensionReasoningScore

Conciseness

The body is lean routing guidance with no concept explanations, but two spots could be trimmed: the opener "Use this skill for requests that are specifically about reviewing staged changes and drafting a commit message for them" duplicates the frontmatter description, and "This skill exists to make the trigger explicit, request the review, forward any specified model name, and route the task into the canonical git workflow" restates the workflow's purpose. Matches anchor 4 (efficient, minor over-explanation); not 5 because of this redundancy, not 3 because there is no padding or explanation of things Claude already knows.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: it names the exact resource ("Load the `git-workflows` skill and read its `references/op_commit_message.md`"), maps inputs to specific operation steps ("Perform step 2 (\"Review\") inline", "during step 4 (\"Draft the commit message\")"), gives the exact footer template ("Commit message generated by <harness name> (<model name>)"), and specifies the fallback ("If no argument is provided, follow the default footer instructions"). Matches anchor 5; no key execution detail is missing.

5 / 5

Workflow Clarity

A simple single-purpose skill whose single action is unambiguous: a numbered sequence (load reference, follow it with the given inputs, don't fork the process) with checkpoints surfaced — "If nothing is staged, the operation's step 1 stops the process" and the description-level "commit after approval" guard. Per the simple-skill guidance this matches anchor 5; not 4 because the stop-condition and review/approval checkpoints are explicitly addressed.

5 / 5

Progressive Disclosure

The body is under 50 lines with clear sections (Arguments, Workflow, Trigger Examples, Scope) and a single clearly-signaled, one-level-deep reference ("read its `references/op_commit_message.md`"); no content that belongs in a separate file is inlined. There are no bundle files (references/, scripts/, assets/ do not exist) to misstructure, matching the simple-skill exception for anchor 5.

5 / 5

Total

19

/

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 description: it states a concrete three-action workflow, includes an explicit 'Use this when...' trigger clause, and proactively disambiguates from the sibling `review-and-commit` skill. The only deductions are minor — a few natural trigger synonyms are missing and some description budget goes to routing caveats rather than capability detail. It is written in third person with no fluff or over-claims.

DimensionReasoningScore

Specificity

"Review staged git changes, then draft a commit message and commit after approval" lists three concrete actions, and "Accepts optional arguments specifying the model name" adds a fourth capability. This matches anchor 4 (several specific actions, minor gaps) rather than 5 because a sizable share of the description is routing/meta guidance ("Intended for an agent that did not write the changes") instead of enumerated capabilities, and it does not say what the review step covers.

4 / 5

Completeness

Both questions are answered explicitly: what — "Review staged git changes, then draft a commit message and commit after approval"; when — "Use this when the user wants a reviewed commit message for the staged changes". This matches anchor 5 (clear, explicit what AND when with concrete trigger phrasing); it is above anchor 4 because the 'when' clause is already explicit and concrete, not merely implied or generic.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: "commit message", "staged git changes", "staged changes", "reviewed commit message". Good coverage matching anchor 4, but not 5 because common variations like "write a commit message", "git commit", "diff", or "conventional commit" (which the body's trigger examples do cover) are absent from the description itself; not 3 because the included keywords are natural and directly relevant.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow (staged changes only) and it actively disambiguates from the closest sibling: "the session that wrote them should use `review-and-commit` instead". This matches anchor 5 (clear niche with distinct triggers, minimal conflict risk) rather than 4 because the primary overlap risk is explicitly resolved rather than merely reduced.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

ceshine/ceshine-agent-skills

Path

generate-commit-message/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.