CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit

Create git commits with user approval and no Claude attribution

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a strong, lean, well-sequenced instruction skill: concrete git commands, an explicit user-approval checkpoint, and a hard safeguard against `git add -A`. The remaining gaps are minor — a couple of inferable explanatory lines, no example commit message, and no guidance for handling a failed commit.

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete steps, but lines like "The reasoning file helps future sessions understand past decisions" and "The user trusts your judgment - they asked you to commit" explain things Claude can infer. This is anchor 4 (efficient, minor over-explanation to trim) rather than anchor 5, where every token earns its place.

4 / 5

Actionability

Concrete commands appear throughout ("Run `git status`", "Use `git add` with specific files", "Show the result with `git log --oneline -n [number]`", and a verbatim script invocation). Placeholders like `-n [number]` and "[N] commit(s)" plus the absence of an example commit message leave minor gaps, matching anchor 4 rather than the copy-paste-complete anchor 5.

4 / 5

Workflow Clarity

The five-step process is clearly sequenced with an explicit checkpoint ("Ask: 'I plan to create [N] commit(s)... Shall I proceed?'") and a post-commit verification display via `git log`. There is no failure/recovery loop (e.g., what to do if a commit fails or a hook rejects it), so it fits anchor 4 (clear sequence, minor validation gaps) rather than anchor 5. The destructive/batch cap does not apply since committing is not destructive.

4 / 5

Progressive Disclosure

The body is under 50 lines, has no need for external references, and is well-organized into Process / Important / Remember sections. Per the rubric's simple-skill guidance, this earns anchor 5; there are no nested or buried references, and the one referenced script path is a concrete project script invocation rather than a navigational reference.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, distinctive capability with correct third-person voice, but it omits any "when to use" trigger guidance and carries only a single trigger keyword. Adding a "Use when..." clause with natural phrases users would say would lift both completeness and trigger term quality.

Suggestions

Add a trigger clause, e.g. "Use when the user asks to commit changes, make a commit, or save staged work."

Expand capability coverage slightly, e.g. "groups related changes into logical commits and drafts imperative-mood commit messages".

Include natural synonyms ("commit", "committing", "save changes") so the skill triggers on how users actually phrase the request.

DimensionReasoningScore

Specificity

"Create git commits" is a concrete action and "user approval and no Claude attribution" adds policy constraints, but the description stops at one action without covering related capabilities (grouping changes, drafting messages). It matches anchor 3 (1-2 concrete actions, not comprehensive) rather than 4, which requires several listed actions.

3 / 5

Completeness

The "what" is clear ("Create git commits with user approval and no Claude attribution") but there is no "when" clause at all. The rubric guideline explicitly caps completeness at 3 for a missing "Use when..." trigger, which also rules out anchor 4.

3 / 5

Trigger Term Quality

"git commits" is the one natural keyword users would say, but common variations and synonyms are absent ("commit changes", "make a commit", "save changes", "stage and commit"). This fits anchor 3 (some relevant keywords, missing common variations) rather than 4's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

"git commits" is a well-owned, distinct trigger and the no-attribution constraint carves a clear niche, so it is mostly distinguishable from other skills (anchor 4). It falls short of anchor 5 because the trigger phrasing is not comprehensive enough to guarantee minimal overlap with general git-workflow skills.

4 / 5

Total

13

/

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

parcadei/Continuous-Claude-v3

Path

.claude/skills/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.