CtrlK
BlogDocsLog inGet started
Tessl Logo

git-workflows

Always invoke this skill for any git-related request (commit messages, staging review, history, PR descriptions, etc.) so git workflows are handled consistently.

69

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.

An exemplary operational skill body: concrete executable commands throughout, clearly sequenced workflows with explicit approval and validation checkpoints, and a clean one-level-deep reference structure with all bundled files present. The only defects are minor: some repetition of the repo-root guidance across sections and a couple of typographical slips.

DimensionReasoningScore

Conciseness

The body is dense and command-driven with no explanations of concepts Claude already knows, matching 'efficient; minor instances of over-explanation that could be trimmed'. Not 5 because the repo-root rationale is restated across several sections (lines 21, 65, 72, 80) and there are small typos ("the the next step", "The should be in the format").

4 / 5

Actionability

Every operation provides exact script invocations with arguments, env-var overrides, debug flags, a conventional-commit template, and a PR format example — copy-paste ready guidance covering the common cases, matching the top anchor. It is not 4-level because no operation relies on hints or pseudocode.

5 / 5

Workflow Clarity

All five operations are numbered with explicit validation checkpoints: user-approval gates in operations 3 and 5 ("Only move on... after an explicit approval"), a staged-changes precondition check in operation 5, script argument validation via git rev-parse, and a dedicated Error Handling section for recovery. The batch/destructive auto-commit operation does include validation, so the cap-3 rule does not apply; only operation 4's slightly loose 'Workflow Notes' keeps this from being beyond question, and it still fits the anchor-5 description better than anchor 4.

5 / 5

Progressive Disclosure

A clear overview with one-level-deep, well-signaled references: four language/workflow-specific files in references/ (all verified to exist on disk) with conditional read triggers, and script documentation kept to usage lines while implementation lives in scripts/. The auto-commit operation correctly summarizes inline and points to references/auto_commit_workflow.md for the full workflow, matching the top anchor exactly.

5 / 5

Total

19

/

20

Passed

Description

75%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 solid third-person description with an explicit trigger clause and natural task keywords in the git domain. Its main weakness is that the capability list is a hedged parenthetical of nouns rather than a direct statement of what the skill does, leaving minor gaps in coverage and a small risk of overlapping with more specialized git skills.

Suggestions

State the "what" as concrete actions up front, e.g. "Generates commit messages, reviews staged/unstaged diffs, and composes PR descriptions from git history", keeping the parenthetical list for trigger coverage.

Add missing natural trigger terms such as "diff", "pull request", "branch", and "code review" so users phrasing requests those ways also match.

Replace the vague "etc." with the two remaining operations (auto-committing unstaged changes, commit-history summaries) to close the coverage gap.

DimensionReasoningScore

Specificity

The parenthetical "commit messages, staging review, history, PR descriptions" names several concrete capabilities in the git domain, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because coverage is not comprehensive (auto-commit, diff review, and code review are missing) and the trailing "etc." hedges.

4 / 5

Completeness

The "when" is fully explicit ("Always invoke this skill for any git-related request") and the "what" is conveyed by the enumerated task list, matching the 'both present, one could be more specific' anchor. Not 5 because the what is only implied by nouns in a parenthetical rather than stated as actions, and "etc." is vague.

4 / 5

Trigger Term Quality

Phrases like "commit messages", "staging review", and "PR descriptions" are natural terms a user would say, giving good keyword coverage. Not 5 because common variations are missing ("diff", "pull request", "code review", "branch", ".git"); not 3 because coverage goes beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

A clear git-workflow niche with distinct triggers (commit messages, staging, history, PR descriptions), but the catch-all "Always invoke... any git-related request" creates minor overlap risk with a dedicated commit-message or PR-review skill, matching 'mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.

4 / 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
ceshine/ceshine-agent-skills
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.