Content
57%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 body is a usable, command-rich catalog for discovering skills, but it reads as an all-in-one reference with repeated command boilerplate and generic advice that could be trimmed or split into sub-files. Workflow and progressive-disclosure structure are the weakest areas.
Suggestions
Collapse the repeated `npx clawhub search "<keyword>"` examples into a single example plus a keyword list to remove boilerplate and improve conciseness.
Split the Common Skill Categories and Troubleshooting content into a separate reference file (e.g., CATALOG.md) and link to it from SKILL.md to improve progressive disclosure.
Replace generic Best Practices advice ("Read documentation", "Test thoroughly") with skill-specific, concrete guidance or remove it to reduce padding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient but padded: the Search Strategies section repeats the same `npx clawhub search` command many times with different keywords, and Best Practices/Installation Tips offer generic advice Claude already knows. | 3 / 5 |
Actionability | Provides concrete executable commands (`npx clawhub search`, `npx clawhub browse`, `--sort installs/stars`) and real alternative URLs, with only minor gaps around what to do with returned results. | 4 / 5 |
Workflow Clarity | Presented as a catalog of sources rather than a crisp sequenced workflow; for a simple search skill the single action is unambiguous, but the implicit search-then-install flow has no explicit checkpoints. | 3 / 5 |
Progressive Disclosure | Sections are well-organized with headers, but the ~135-line body is monolithic with no one-level-deep reference files and inline catalog content (categories, troubleshooting) that could be split out. | 3 / 5 |
Total | 13 / 20 Passed |