Content
82%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 delivers fully executable CLI guidance with a clearly sequenced two-step workflow, explicit ordering rules, and error-recovery handling. Weaknesses are limited to minor redundancy (the sensitive-data warning repeated three times) and no verification step for the retrieved documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and skill-specific with no explanation of concepts Claude already knows, but the sensitive-information warning is repeated three times (in Resolve a Library, Writing good queries, and Common Mistakes) and query-quality advice recurs ~3 times — minor over-explanation that could be trimmed. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands throughout: `npm install -g ctx7@latest`, `npx ctx7@latest <command>`, `ctx7 library <name> <query>`, and `ctx7 docs <libraryId> <query>`, each illustrated with concrete real-world examples (e.g., `ctx7 docs /vercel/next.js/v14.3.0-canary.87 "How to set up app router"`). | 5 / 5 |
Workflow Clarity | Clear two-step sequence with an explicit ordering rule ("You MUST call `ctx7 library` first... UNLESS the user explicitly provides a library ID"), a 3-attempt retry bound, and a quota-error recovery loop; no validation checkpoint for confirming the retrieved results answer the question, which keeps it below a 5. | 4 / 5 |
Progressive Disclosure | Well-organized single-file skill with clear section headers and all content appropriately inline for a two-command CLI; at ~135 lines it exceeds the under-50-line simple-skill exception, so the absence of any external reference files prevents a 5. | 4 / 5 |
Total | 17 / 20 Passed |