CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Create a git commit for the Vision-Agents repo.

55

Quality

61%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is exceptionally concise and well-organized with a genuine pre-commit validation feedback loop, but it lacks a concrete commit-message example and a sequenced step-by-step workflow. Adding an example and a numbered sequence would lift actionability and workflow clarity.

Suggestions

Add a concrete example commit message showing the conventional-commit format and ≤72-char subject line so the guidance is copy-paste ready.

Express the commit workflow as a numbered sequence (e.g. branch check → stage by name → commit → re-stage/retry on hook modifications) rather than scattered rules.

Optionally note how to verify the result (e.g. confirm hooks passed, show the final commit) as an explicit final checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and rule-driven with no concept explanations or padding; every line conveys repo-specific guidance Claude does not inherently know, matching 'lean and efficient; every token earns its place'.

3 / 3

Actionability

It gives concrete executable constraints (conventional commits, subject ≤72 chars, stage by name, never --no-verify) but no worked commit-message example or template to follow, so it stops short of 'fully executable ... copy-paste ready'.

2 / 3

Workflow Clarity

An explicit validation/recovery loop is present (re-stage and retry if hooks modify files; fix root cause if mypy fails), but the commit workflow itself is expressed as scattered rules rather than a clear numbered sequence with checkpoints.

2 / 3

Progressive Disclosure

This is a simple skill under 50 lines with no need for external references, and its two sections (## Rules, ## Pre-commit hooks) are well-organized, so per the simple-skills note progressive disclosure can score 3.

3 / 3

Total

10

/

12

Passed

Description

50%

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 is concise and uses a natural third-person action phrase, but it states only a single action and lacks any explicit 'when to use' trigger guidance. It is adequate but generic for a commit skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to commit changes in the Vision-Agents repo or asks for help writing a commit message.'

Broaden trigger-term coverage with natural variants like 'commit changes', 'make a commit', 'stage and commit', and 'write a commit message'.

Name a couple of concrete actions (e.g. stage files individually, run pre-commit hooks) to lift specificity beyond a single action.

DimensionReasoningScore

Specificity

"Create a git commit" names one concrete action but does not list multiple specific actions, matching the 'names domain and some actions' anchor rather than the multi-action anchor at 3.

2 / 3

Completeness

It clearly states what (create a git commit) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

"git commit" is a natural term a user would say, but coverage is narrow with no common variations like 'commit changes', 'write a commit message', or 'stage and commit', so it sits at 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Scoping to the 'Vision-Agents repo' adds some distinctiveness, but 'Create a git commit' still overlaps heavily with general commit skills and Claude's built-in commit capability, so it could conflict rather than occupying a clear niche.

2 / 3

Total

8

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
GetStream/Vision-Agents
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.