CtrlK
BlogDocsLog inGet started
Tessl Logo

changelog

Create changelog files for important commits in a PR

69

1.58x
Quality

52%

Does it follow best practices?

Impact

100%

1.58x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/changelog/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

32%

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 brief and identifies a specific task domain (changelog creation for PRs) but lacks sufficient detail on concrete actions, trigger conditions, and keyword coverage. It would benefit from an explicit 'Use when...' clause and more specific capability descriptions to help Claude reliably select this skill from a large pool.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to generate a changelog, summarize PR changes, or document important commits in a pull request.'

Expand trigger terms to include natural variations like 'pull request', 'release notes', 'CHANGELOG.md', 'change log', and 'commit summary'.

Add more specific capability details, e.g., 'Analyzes commits in a pull request, identifies significant changes, and generates a formatted changelog entry summarizing new features, bug fixes, and breaking changes.'

DimensionReasoningScore

Specificity

Names the domain (changelog files, commits, PR) and one action (create), but lacks detail on what the changelog contains, how it's formatted, or what constitutes 'important commits'.

2 / 3

Completeness

Describes what it does (create changelog files) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also quite thin, bringing it to 1.

1 / 3

Trigger Term Quality

Includes relevant terms like 'changelog', 'commits', and 'PR' that users might naturally say, but misses common variations like 'pull request', 'release notes', 'CHANGELOG.md', or 'change log'.

2 / 3

Distinctiveness Conflict Risk

The combination of 'changelog' and 'PR' provides some distinctiveness, but could overlap with general PR review skills or release note generation skills. The scope is somewhat specific but not sharply delineated.

2 / 3

Total

7

/

12

Passed

Implementation

72%

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

This is a solid, actionable skill that clearly instructs how to create changelog files with specific naming conventions, formatting rules, and good/bad examples for tone. Minor weaknesses include some redundancy in listing changelog types and the absence of a validation step to confirm the created files are correct. Overall it's well-structured and practical.

Suggestions

Add a brief validation step (e.g., 'Verify: list changelog/ files and confirm each maps to a commit from the git log') to close the workflow loop.

Consolidate the allowed types list and the filename examples into a single presentation to reduce redundancy.

DimensionReasoningScore

Conciseness

Mostly efficient but has some redundancy — the allowed types are listed once as a list and then again as filename examples. The good/bad example section is valuable but slightly verbose. Overall reasonable but could be tightened.

2 / 3

Actionability

Provides concrete git commands, exact file naming conventions with examples, specific formatting rules (dash prefix, no line wrapping), and clear good/bad examples. A developer or Claude could follow this without ambiguity.

3 / 3

Workflow Clarity

Steps are clearly sequenced (check commits → determine significance → create files), but there's no validation checkpoint — no step to verify the changelog files were created correctly, check for naming conflicts, or confirm the files match the actual commits. For a file-creation workflow this is a minor gap but still notable.

2 / 3

Progressive Disclosure

For a skill under 50 lines with a single focused task, the content is well-organized with clear sections (Instructions, Example) and no need for external references. The structure is appropriate for the complexity level.

3 / 3

Total

10

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
pipecat-ai/pipecat
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.