CtrlK
BlogDocsLog inGet started
Tessl Logo

conventional-commit

Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.

46

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/sdlc/skills/conventional-commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%Scale 1-5

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

This skill provides a functional but verbose guide to conventional commit messages wrapped in unnecessary XML structures that add complexity without value. The examples are the strongest element, providing clear concrete patterns. The workflow has logical gaps (contradictory steps 5-6, no error handling) and the XML formatting throughout is an anti-pattern that wastes tokens and obscures the actual instructions.

Suggestions

Remove all XML wrapper tags (commit-message, validation, examples, final-step) and present the content as plain markdown — the XML adds verbosity without actionable value for Claude.

Resolve the contradiction between steps 5 and 6 in the workflow, and clarify whether this skill is for Claude to auto-commit or to help construct a message for the user to run.

Add a validation checkpoint after constructing the commit message (e.g., verify the type is valid, description uses imperative mood) before executing the commit command.

Remove the description XML block at the top and the redundant 'Final Step' section — the workflow already covers the commit command.

DimensionReasoningScore

Conciseness

The XML wrapper tags add significant verbosity without value — Claude doesn't need XML structure to understand commit message formats. The description tag explaining what the file is, the redundant 'final step' section repeating the commit command, and the general over-structuring with XML bloat all waste tokens on things Claude already knows.

2 / 5

Actionability

The workflow provides a reasonable sequence of git commands and the examples are concrete and useful. However, the commit command template uses a placeholder ('type(scope): description') rather than showing how to programmatically construct the actual message, and the XML structure is not directly executable — it's a representational format that doesn't translate to actionable code. The guidance for multi-line commits with body/footer is vague ('Include body and footer if needed').

3 / 5

Workflow Clarity

Steps are listed in a reasonable sequence (status → diff → stage → construct → commit), but there are no validation checkpoints between steps. There's no feedback loop for when the commit message fails validation, no check that staging was successful, and the validation section is declarative rather than procedural. The mention of 'Copilot will automatically run' in step 5 contradicts step 6's instruction to 'just execute this prompt,' creating confusion.

3 / 5

Progressive Disclosure

The content is organized into logical sections (Instructions, Workflow, Structure, Examples, Validation, Final Step), which provides some structure. However, there are no bundle files and no references to external resources beyond a URL to the conventional commits spec. The content is all inline in a single file, which is acceptable for this skill's complexity, but the 'Final Step' section is redundant with the workflow and the XML description block adds no navigational value.

3 / 5

Total

11

/

20

Passed

Description

53%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 adequately identifies the domain and core purpose (generating conventional commit messages) but falls short on completeness by lacking an explicit 'Use when...' clause. It also uses somewhat formal/technical language rather than the natural trigger terms users would employ, and could benefit from listing more specific capabilities beyond 'generating' and 'validation'.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user asks for help writing commit messages, formatting git commits, or following the Conventional Commits spec.'

Include more natural trigger terms and synonyms users would say, such as 'git commit', 'commit format', 'staged changes', 'commit type', or 'breaking change'.

List more specific concrete actions such as 'analyzes diffs to suggest commit types and scopes, formats messages with body and footer sections, validates against Conventional Commits rules'.

DimensionReasoningScore

Specificity

Names the domain (conventional commit messages) and a couple of concrete actions (generating, validating), but lacks comprehensive coverage of specific capabilities like parsing diffs, suggesting types/scopes, or handling breaking changes.

3 / 5

Completeness

Has a clear 'what' (generating conventional commit messages with structured XML format, including instructions, examples, and validation) but lacks an explicit 'when' clause. There is no 'Use when...' guidance for Claude to know when to select this skill.

3 / 5

Trigger Term Quality

Includes relevant terms like 'commit messages', 'Conventional Commits', and 'validation', but misses natural user phrases like 'git commit', 'staged changes', 'commit format', or 'changelog'. Also missing common synonyms users would say.

3 / 5

Distinctiveness Conflict Risk

Fairly distinct due to the specific mention of 'conventional commit messages', 'structured XML format', and the Conventional Commits specification. Minor overlap risk with general git or code review skills, but the specificity of the commit message domain reduces conflict.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
whimzyLive/nightshift-ai
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.