Content
43%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is concise and sectioned but functions mainly as a catalogue pointer: it provides almost no executable guidance or sequenced workflow, and defers all real material to an external upstream repo rather than structuring it locally.
Suggestions
Replace the `open https://github.com/...` browser action with a concrete install command (e.g., a `git clone` + copy into the skills directory) so the body is directly actionable.
Add a short numbered workflow with an explicit verification step (e.g., confirm the skill appears in the agent's skill list before invoking).
Either vendor the key upstream reference locally (so references/ has real files) or clearly signal the single external reference as the sole source of detail, to make progressive disclosure one-level-deep.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and largely lean, but it restates the description and source URL already present in frontmatter, adding minor redundancy that keeps it just below the fully efficient anchor 5. | 4 / 5 |
Actionability | Concrete guidance is minimal — the only command is `open https://github.com/...` (a browser action) and it defers all real steps to 'inspect the upstream README for exact paths', leaving the specific install/run steps unspecified. | 2 / 5 |
Workflow Clarity | A rough sequence exists (inspect README, install bundle, invoke by name) but steps are poorly defined with no validation checkpoints, matching the anchor for a rough-but-gappy sequence. | 2 / 5 |
Progressive Disclosure | Sections are present and the skill is short, but no local bundle files exist (references/scripts/assets are empty) and the only navigation points two hops away to an external README, so disclosure is neither one-level-deep nor locally structured. | 3 / 5 |
Total | 11 / 20 Passed |