CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

86%

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

77%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.

A well-structured, highly actionable commit workflow with explicit validation checkpoints and error-recovery loops. Its main weakness is token efficiency: the conventional-commit type list and verbose environmental hook guidance re-explain what Claude already knows.

Suggestions

Remove or drastically trim the conventional-commit type list — Claude already knows standard types; keep only repo-specific deviations from convention.

Compress the npm/worktree and hook-failure environmental guidance into one short line (e.g., "If hooks fail, rule out stale builds or missing install by re-running the package in isolation") instead of multi-clause parentheticals.

Add a single example commit message showing the expected type(scope): summary format in action, which would also strengthen actionability.

DimensionReasoningScore

Conciseness

Mostly efficient, but the conventional-commit type list (feat/fix/docs/test/refactor/chore with definitions) explains a concept Claude already knows, and the npm/worktree environmental parentheticals ("a fresh worktree with stale artifacts fails hooks for environmental reasons") are wordy. This goes beyond the "minor instances" of anchor 4 but is far from the heavy padding of anchor 2.

3 / 5

Actionability

Mostly executable guidance with copy-paste commands ("git status --short --branch", "git add path/to/file", "git diff --cached") and a message format template. It falls short of anchor 5 because no example commit message is provided and the actual commit command is left implicit.

4 / 5

Workflow Clarity

A clear 7-step numbered sequence with explicit validation checkpoints (validate before committing; re-check the staged diff) and error-recovery feedback loops (stop on validation failure, retry after isolating hook failures from environmental causes). Validation is present and explicit, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, needs no external references, and is organized into clear sections (Commit Contract, Guardrails, Message Style). Per the simple-skill exception, well-organized sections alone warrant anchor 5.

5 / 5

Total

17

/

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 with an explicit trigger-rich "Use when" clause and concrete, user-natural language in third-person style. The only weaknesses are minor: a few natural trigger variations are absent and the "what" side could cover message writing more explicitly.

DimensionReasoningScore

Specificity

Lists several concrete actions ("commit", "stage changes", "create a PR-ready checkpoint") with minor gaps in coverage — e.g., writing the commit message itself is only implied by "conventional commit". It exceeds the 1–2 concrete actions of anchor 3 but is not comprehensive enough for anchor 5.

4 / 5

Completeness

Explicitly answers both: what ("Safe git commit workflow... avoiding unrelated user changes") and when — an explicit "Use when" clause listing five concrete trigger scenarios. The when-clause is fully explicit with concrete triggers, matching anchor 5 rather than anchor 4 where the when could be more specific.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ("commit", "prepare a commit", "stage changes", "PR-ready checkpoint"), but common variations like "commit message", "make a commit", or "check in" are missing, so it falls short of the synonym-level comprehensiveness of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (safe, scoped git commits for AI agents) with distinct commit-specific triggers and minimal conflict risk; even the broadest phrase ("finish work") is bounded by "with a conventional commit". Triggers are not shared with adjacent skills like PR creation or message linting, so anchor 4's minor-overlap qualifier does not apply.

5 / 5

Total

18

/

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

Path

skills/dev-commit/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.