Content
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 actionable content. It provides abstract, high-level directives without any concrete examples, tool configurations, commit message formats, or executable commands. Nearly all value is deferred to an external resource file, leaving the SKILL.md itself almost useless as standalone guidance.
Suggestions
Add a concrete example of a conventional commit message format (e.g., `feat(auth): add JWT token validation`) and the corresponding changelog entry it would generate.
Include at least one executable code snippet or CLI command for a specific tool (e.g., `npx conventional-changelog -p angular -i CHANGELOG.md -s`) to make the instructions actionable.
Define a clear multi-step workflow with validation checkpoints, such as: configure tool → run generation → review output → fix issues → publish, with specific commands at each step.
Bring key patterns from the implementation playbook inline (e.g., Keep a Changelog format template, semantic versioning rules) so the SKILL.md provides standalone value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Use this skill when' and 'Do not use this skill when' sections add some value but are somewhat verbose for what they convey. The instructions section is lean but lacks substance, making the content feel padded with meta-information rather than actionable guidance. | 2 / 3 |
Actionability | The instructions are entirely vague and abstract — 'Select a changelog format,' 'Enforce commit conventions,' 'Configure tooling' — with no concrete code, commands, tool names, configuration examples, or commit message formats. There is nothing executable or copy-paste ready. | 1 / 3 |
Workflow Clarity | While steps are loosely listed, they are abstract directives rather than a clear workflow. There are no validation checkpoints, no specific tools or commands, and no feedback loops for verifying generated changelogs are correct. | 1 / 3 |
Progressive Disclosure | There is a reference to `resources/implementation-playbook.md` for detailed content, which is good progressive disclosure structure. However, the top-level SKILL.md provides almost no useful standalone content — it's essentially an empty shell pointing elsewhere, making the reference feel like a crutch rather than a complement. | 2 / 3 |
Total | 6 / 12 Passed |