CtrlK
BlogDocsLog inGet started
Tessl Logo

dev-commit

AI DevKit · Safe git commit workflow for AI coding agents. Use when the user asks to commit, prepare a commit, stage changes, create a PR-ready checkpoint, or finish work with a conventional commit while avoiding unrelated user changes.

72

Quality

90%

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 efficient, highly actionable skill body: concrete commands, a well-sequenced contract with real validation checkpoints and error-recovery loops, and disciplined brevity with no concept padding. The only gap is the absence of example commit messages and a concrete default validation command.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's git competence — every sentence adds operational guidance (commands, scope rules, failure handling) with zero concept explanation or padding, matching the anchor-5 example's economy.

5 / 5

Actionability

Concrete copy-paste commands appear throughout ('git status --short --branch', 'git diff --cached --stat', 'git add path/to/file') plus an explicit message format, but no example commit messages are shown and validation is delegated to 'the repo's targeted tests' without a concrete default command — minor gaps.

4 / 5

Workflow Clarity

The seven-step Commit Contract has a clear sequence with explicit validation before committing (step 3), re-check checkpoints (steps 1 and 5), and feedback loops for error recovery — validation failure stops the commit and reports output, and hook failures get an isolate-then-retry procedure.

5 / 5

Progressive Disclosure

A simple under-50-line, single-purpose skill with well-organized sections (Contract, Guardrails, Message Style) and no bundle files — nothing needs to be split out, so it fully meets the simple-skill standard for this dimension.

5 / 5

Total

19

/

20

Passed

Description

83%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 with an explicit trigger clause and concrete, natural trigger phrases that clearly separate it from generic git skills. The what-clause is specific but stops just short of covering message authoring and reporting, and the PR-checkpoint phrasing slightly widens its niche.

DimensionReasoningScore

Specificity

Names the domain ('Safe git commit workflow for AI coding agents') and lists several concrete actions ('commit, prepare a commit, stage changes, create a PR-ready checkpoint'), but coverage has minor gaps — message writing and post-commit reporting only surface indirectly through the trigger clause.

4 / 5

Completeness

Explicitly answers both what ('Safe git commit workflow... avoiding unrelated user changes') and when, with a fully explicit 'Use when' clause listing five concrete trigger phrases — matching the anchor-5 example's structure.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered ('asks to commit', 'stage changes', 'PR-ready checkpoint', 'conventional commit'), but a few common variants like 'check in my work' or 'save a checkpoint' are missing.

4 / 5

Distinctiveness Conflict Risk

A clear git-commit niche with distinct triggers keeps conflict risk low, but 'create a PR-ready checkpoint' slightly broadens scope into neighboring PR/branch workflows, giving minor overlap risk with closely related skills.

4 / 5

Total

17

/

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
codeaholicguy/ai-devkit
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.