CtrlK
BlogDocsLog inGet started
Tessl Logo

generating-conventional-commits

Execute generates conventional commit messages using AI. It analyzes code changes and suggests a commit message adhering to the conventional commits specification. Use this skill when you need help writing clear, standardized commit messages, especially a... Use when managing version control. Trigger with phrases like 'commit', 'branch', or 'git'.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/packages/devops-automation-pack/skills/generating-conventional-commits/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The body reads as a generic product overview rather than an actionable skill: it describes the process instead of instructing Claude how to run it, and never wires up the provided scripts or template. It is concise enough but lacks concrete, executable guidance and validation steps.

Suggestions

Replace abstract descriptions with executable invocations of the bundled scripts, e.g. 'python scripts/suggest_commit_type.py --diff <file>' and 'python scripts/generate_commit_message.py --diff <file>', and link to assets/commit_message_template.txt for the format.

Add a concrete, ordered commit workflow with a validation checkpoint: run git diff --staged, generate the message, validate with scripts/validate_commit_message.py, only then present for user review.

Cut filler sections ('Output', 'Integration', 'Resources') that restate obvious behavior, and instead signpost the one-level-deep bundled references so the overview points to the real materials.

DimensionReasoningScore

Conciseness

The body is reasonably short but padded with sections that tell Claude what it already knows ('It saves you time and ensures consistency', 'Always review the generated commit message') and generic filler like 'The skill produces structured output relevant to the task' that earns few tokens.

2 / 3

Actionability

The body only describes behavior in the abstract ('analyzes the staged changes', 'uses AI to generate a commit message') and gives example outputs but provides no executable commands, no reference to the bundled scripts (generate_commit_message.py, suggest_commit_type.py, validate_commit_message.py) or the template asset, and no copy-paste-ready guidance.

1 / 3

Workflow Clarity

A sequenced 'How It Works' list exists (Analyze -> Generate -> Present) but there are no validation checkpoints, and the 'Instructions'/'Error Handling' sections are generic boilerplate ('Apply modifications as needed', 'Lists required components') rather than a concrete commit workflow.

2 / 3

Progressive Disclosure

Bundle files exist under scripts/ and assets/ (including a real commit_message_template.txt and example_code_diff.txt) but the body never links to or signals them, so the overview does not point clearly to its own bundled material despite the structure being available.

2 / 3

Total

7

/

12

Passed

Description

92%

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, mostly concrete description with both a clear 'what' and explicit 'when' triggers. The main weakness is the over-broad 'branch'/'git' trigger terms, which widen the trigger surface beyond conventional-commit messaging.

DimensionReasoningScore

Specificity

It lists concrete actions — 'generates conventional commit messages', 'analyzes code changes and suggests a commit message adhering to the conventional commits specification' — matching the anchor that lists multiple specific actions.

3 / 3

Completeness

It answers both 'what' (generates/suggests conventional commit messages by analyzing code changes) and 'when' via an explicit 'Use this skill when...' clause plus a 'Trigger with phrases like...' list, matching the top anchor.

3 / 3

Trigger Term Quality

It explicitly names natural trigger terms users would say ('commit', 'branch', 'git') plus 'writing clear, standardized commit messages' and 'version control', giving good coverage of natural phrasings.

3 / 3

Distinctiveness Conflict Risk

The conventional-commits niche is fairly distinct, but the broad triggers 'branch' and 'git' are generic and could match unrelated Git skills, so it risks overlap rather than being a clean niche.

2 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.