Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.
74
61%
Does it follow best practices?
Impact
99%
1.30xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/changelog-automation/SKILL.mdQuality
Discovery
100%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 is a strong skill description that clearly communicates its purpose, uses natural trigger terms, and includes an explicit 'Use when' clause. It follows third-person voice, names a specific standard (Keep a Changelog), and covers the key scenarios where this skill should be selected. The description is concise yet comprehensive with minimal risk of conflicting with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'changelog generation from commits, PRs, and releases', 'setting up release workflows', 'generating release notes', 'standardizing commit conventions'. Also references a specific format standard (Keep a Changelog). | 3 / 3 |
Completeness | Clearly answers both 'what' (automate changelog generation from commits, PRs, and releases following Keep a Changelog format) and 'when' (explicit 'Use when' clause covering release workflows, release notes, and commit conventions). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'changelog', 'commits', 'PRs', 'releases', 'release notes', 'release workflows', 'commit conventions', 'Keep a Changelog'. These cover common variations of how users would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around changelog generation and release note automation. The specific mention of Keep a Changelog format, commits, PRs, and release workflows makes it highly distinguishable from general git or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no substantive content. It lacks any concrete guidance—no tool names (e.g., conventional-changelog, release-please), no commit format examples, no configuration snippets, and no executable commands. The entire actionable content is deferred to a referenced file, leaving the SKILL.md itself nearly useless as a standalone reference.
Suggestions
Add concrete, executable examples: include a conventional commit format template (e.g., 'feat(scope): description'), a sample tool configuration (e.g., release-please config or conventional-changelog CLI command), and an example generated changelog entry.
Provide a clear multi-step workflow with specific tool commands, e.g., '1. Install release-please: `npm install release-please` 2. Configure `.release-please-manifest.json` 3. Run: `release-please ...' with validation steps.
Include at least one concrete commit message example with input/output showing how a commit becomes a changelog entry, similar to the rubric's good example for commit message formatting.
Either inline the key patterns from `resources/implementation-playbook.md` as a quick-start section or provide a meaningful summary so the SKILL.md is useful without requiring the referenced file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Use this skill when' and 'Do not use this skill when' sections add moderate overhead without providing actionable value. The instructions themselves are lean but vague, so the content isn't padded with explanations of known concepts but does include some unnecessary framing. | 2 / 3 |
Actionability | The instructions are entirely abstract ('Select a changelog format', 'Enforce commit conventions', 'Configure tooling') with no concrete commands, code examples, tool names, configuration snippets, or specific commit format templates. Nothing is copy-paste ready or executable. | 1 / 3 |
Workflow Clarity | The steps are vague directives without specific sequencing, validation checkpoints, or feedback loops. There's no indication of what tools to run, how to verify output, or how to recover from errors. The workflow is essentially 'do the thing, then review it.' | 1 / 3 |
Progressive Disclosure | There is a reference to `resources/implementation-playbook.md` for detailed patterns, which is one-level deep and clearly signaled. However, the SKILL.md itself provides almost no substantive overview content, making it an empty shell that delegates nearly everything to the referenced file. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
43280f9
Table of Contents
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.