Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-structured skill that clearly identifies the core problem (annotated tags vs lightweight tags in workflow_run contexts) and provides useful guidance. Its main weakness is the lack of a complete, executable workflow YAML example and an explicit step-by-step sequence with validation checkpoints, which would make it significantly more actionable.
Suggestions
Add a complete, copy-paste-ready GitHub Actions workflow YAML snippet showing the checkout, tag fetch, tag resolution, and retry loop steps together.
Convert the Patterns list into an explicit numbered workflow sequence with validation checkpoints (e.g., 'If tag list is empty after retries, fail with a clear error message explaining annotated tag resolution').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line adds value. No unnecessary explanations of what GitHub Actions or annotated tags are—assumes Claude knows these concepts. The patterns, examples, and anti-patterns are all tightly written. | 3 / 3 |
Actionability | Provides specific commands (e.g., `git tag --points-at "$HEAD_SHA" --sort=-version:refname`, `actions/checkout@v4` with `fetch-depth: 0`) but lacks a complete, copy-paste-ready workflow YAML snippet or executable script. The 'retry loop' is mentioned but not shown. | 2 / 3 |
Workflow Clarity | The patterns are listed in a logical order (checkout → fetch tags → resolve → retry → manual replay), but they are presented as a flat list of principles rather than a clearly sequenced workflow with explicit validation checkpoints or error recovery steps. | 2 / 3 |
Progressive Disclosure | This is a short, focused skill under 50 lines with no need for external references. The content is well-organized into clear sections (Context, Patterns, Examples, Anti-Patterns) that are easy to navigate. | 3 / 3 |
Total | 10 / 12 Passed |