CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

git-commits

Git Commit Rules

Quality

62%

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/git-commits/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 body is a tight, actionable orchestration skill: it defines triggers, forbids direct git commit, delegates to the /commit skill, and gives the exact follow-up script command and push step. Its only flaws are minor duplication of trigger terms, a slightly redundant rationale section, and reliance on the external /commit skill for sequencing rather than explicit validation checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and directive ("DO NOT run git commit directly", "Skill(\"commit\")"), but trigger terms are stated twice — in the intro line "commit, push, or save changes" and again in the full Trigger Words section — and "Why This Matters" partially restates the skill-effects list. These minor duplications could be trimmed, matching the efficient-with-minor-excess anchor rather than the fully lean anchor 5.

4 / 5

Actionability

Instructions are concrete and mostly executable: Skill("commit"), a bash command with a resolved project path ($CLAUDE_PROJECT_DIR/.claude/scripts/generate-reasoning.sh), and git push origin <branch>. Minor gaps — how to obtain the <hash> and <message> arguments, and what to do if the /commit skill is unavailable — keep it below the copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The sequence is clear: on trigger words, invoke the /commit skill, then run generate-reasoning.sh with the commit hash and message, then push if requested. Checkpoints are mostly implicit (the sequencing depends on the /commit skill's own prompt) and there is no verification of commit/push success, matching the clear-sequence-with-minor-validation-gaps anchor.

4 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist, and the body is under 50 lines with well-organized ## sections and no inline content that belongs in separate files. Per the rubric's simple-skill exception, this earns the top score on structure alone.

5 / 5

Total

17

/

20

Passed

Description

28%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 "Git Commit Rules" is a bare title: it names a domain but describes no actions, includes no use-when trigger guidance, and provides almost no keyword coverage. A user or skill router would have to guess what the skill actually does or when it applies.

Suggestions

Rewrite the description in third person stating concrete actions, e.g. "Routes git commit, push, and save-changes requests through the /commit skill, which strips Claude attribution lines, generates reasoning.md, and clears build attempts between features."

Add an explicit trigger clause such as "Use when the user asks to commit, push, save changes, or push to GitHub" so the description answers both what and when.

Include natural trigger variations and synonyms (commit and push, push changes, git commit) to improve keyword coverage and distinguish the skill from generic git or commit-message helpers.

DimensionReasoningScore

Specificity

The description is only "Git Commit Rules" — it names the domain (git commits) but contains no action verbs or concrete capabilities, functioning as a title rather than a capability description. It is above anchor 1 because the domain is concretely named, but it lists no actions, so it cannot reach anchor 3.

2 / 5

Completeness

There is no "Use when..." clause or equivalent trigger guidance (capping completeness at 3 per guidelines), and the "what" is only vaguely implied by the two-word title. It edges above anchor 1 because the domain is named, matching the vague-what/no-when anchor.

2 / 5

Trigger Term Quality

Only two bare keywords are present ("Git", "Commit") with no natural phrases or variations; terms like "push", "save changes", and "commit and push" — which the body itself identifies as triggers — are absent. This matches the anchor for one or two generic keywords missing the natural phrases users say.

2 / 5

Distinctiveness Conflict Risk

Git commit orchestration is a recognizable niche, but the description states no distinguishing triggers or capabilities, so it could still overlap with commit-message-generation or general git skills. Not anchor 4 because without any stated differentiators the overlap risk with closely related git skills is more than minor.

3 / 5

Total

9

/

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

description_field

'description' is very short (16 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/git-commits/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.