CtrlK
BlogDocsLog inGet started
Tessl Logo

commit-message-formatter

Commit Message Formatter - Auto-activating skill for DevOps Basics. Triggers on: commit message formatter, commit message formatter Part of the DevOps Basics skill category.

34

0.91x
Quality

3%

Does it follow best practices?

Impact

86%

0.91x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/01-devops-basics/commit-message-formatter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

7%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a placeholder that provides almost no useful information for skill selection. It repeats the skill name as its own trigger term, describes no concrete actions, and lacks any meaningful 'use when' guidance. It would be nearly impossible for Claude to reliably select this skill over alternatives based on this description alone.

Suggestions

Add concrete actions the skill performs, e.g., 'Formats commit messages following conventional commit standards, generates descriptive messages from git diffs, enforces prefix conventions (feat, fix, chore).'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for help writing commit messages, formatting git commits, reviewing staged changes, or mentions conventional commits.'

Remove the redundant duplicate trigger term and replace with diverse natural language variations users would actually say, such as 'commit message', 'git commit', 'write a commit', 'conventional commits', 'commit format'.

DimensionReasoningScore

Specificity

The description does not list any concrete actions. It only names itself ('Commit Message Formatter') and states it's part of 'DevOps Basics' without describing what it actually does—no mention of formatting rules, generating messages, analyzing diffs, or any specific capabilities.

1 / 3

Completeness

The description fails to answer 'what does this do' beyond the name, and the 'when' clause is just a redundant repetition of the skill name rather than meaningful trigger guidance. Both dimensions are very weak.

1 / 3

Trigger Term Quality

The only trigger term listed is 'commit message formatter' repeated twice. It misses natural variations users would say like 'commit message', 'git commit', 'write a commit', 'staged changes', 'git log', or 'conventional commits'.

1 / 3

Distinctiveness Conflict Risk

The term 'commit message formatter' is somewhat specific to a niche (formatting commit messages), which provides some distinctiveness. However, the lack of detail about what specifically it does versus other git/commit-related skills creates potential overlap.

2 / 3

Total

5

/

12

Passed

Implementation

0%

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

This skill is an empty shell with no actionable content whatsoever. It consists entirely of boilerplate meta-descriptions about what the skill would do, without ever providing any actual commit message formatting rules, examples, conventions (like Conventional Commits), or executable guidance. It fails on every dimension of the rubric.

Suggestions

Replace the meta-description sections with actual commit message formatting rules (e.g., Conventional Commits format: type(scope): description) and concrete before/after examples.

Add executable examples showing input (a description of changes) mapped to properly formatted output commit messages, similar to the rubric's good example.

Include specific format constraints such as subject line length limits, allowed types (feat, fix, chore, etc.), and body formatting rules.

Remove all 'When to Use', 'Example Triggers', and 'Capabilities' boilerplate sections—these waste tokens on information that doesn't help Claude perform the task.

DimensionReasoningScore

Conciseness

The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual instructions, commands, or commit message formatting rules. Every section restates the same vague idea.

1 / 3

Actionability

There is zero concrete guidance—no commit message format specification, no examples of good/bad commit messages, no executable code or commands. The skill describes rather than instructs.

1 / 3

Workflow Clarity

No workflow or steps are provided. The 'step-by-step guidance' is only claimed in a bullet point but never actually delivered. There are no sequences, validation steps, or checkpoints.

1 / 3

Progressive Disclosure

The content is a monolithic block of meta-descriptions with no meaningful structure. There are no references to detailed files, no quick-start section, and no navigational aids. The sections that exist (Purpose, When to Use, Capabilities, Example Triggers) are all boilerplate with no real content.

1 / 3

Total

4

/

12

Passed

Validation

81%

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

Validation9 / 11 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

9

/

11

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.