Content
100%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.
An exemplary minimal skill body: fully executable commands with documented output schemas, zero padding, and clean section structure. It assumes Claude's competence throughout and delegates all machinery to the bundled script, which is present and consistent with the documented CLI.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section instructs rather than explains: a one-line intro, two-line requirements, four commented commands, terse output schemas, and two usage notes. No background on what Tavily or web search is; nothing to trim. Not a 4 because there are no instances of over-explanation at all. | 5 / 5 |
Actionability | Four copy-paste-ready invocations ('python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 [--include-answer] [--format brave|md]') cover the common cases, and the Output section documents the exact JSON schema for each format. '{baseDir}' is the platform's path-substitution convention, not pseudocode, and the referenced script exists and implements these flags. | 5 / 5 |
Workflow Clarity | A simple, single-purpose skill under 50 lines whose single action — run the script with a query — is unambiguous, including where to run it ('Run from the OpenClaw workspace') and how to supply the API key. The operation is read-only, so no validation checkpoint is required, and the simple-skill exception applies. | 5 / 5 |
Progressive Disclosure | Well-organized single-file overview with no content that belongs in separate reference files; the only bundle path referenced (scripts/tavily_search.py) exists and is one level deep. Under 50 lines with no need for external references, so well-organized sections suffice for the top anchor. | 5 / 5 |
Total | 20 / 20 Passed |