Content
92%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.
Excellent content for a simple script-based skill: fully executable quick-start examples, a complete and accurate CLI reference, and a correctly split bundle. The only improvement is trimming the script-internals section, which explains implementation details Claude does not need to use the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — quick-start commands, a flag table, an output schema, and a one-line cost note — with no explanations of concepts Claude already knows. Minor trimmable content exists: the 'How the Script Works' internals (pagination, numericFilters details) and the repeated 'No Apify token needed' note add tokens beyond what running the skill requires. This sits at 'efficient with minor over-explanation', below the every-token-earns-its-place anchor at 5. | 4 / 5 |
Actionability | Three copy-paste-ready commands cover the common cases (topic search, Show HN browse, comment search), the single dependency install is stated, and the CLI table documents every flag with defaults. All flags were verified against the actual script's argparse and match; the output example shows the exact returned schema. | 5 / 5 |
Workflow Clarity | A simple, single-purpose skill where the single action — run scripts/search_hn.py with the documented flags — is unambiguous, satisfying the simple-skill exception. The operation is read-only search, so the destructive/batch validation cap does not apply. | 5 / 5 |
Progressive Disclosure | The body is short and well-organized with clear sections; executable logic is appropriately split into scripts/search_hn.py, which exists in the bundle and is referenced with matching paths and accurate flag documentation. References are one level deep and clearly signaled, with no inlined content that belongs in a separate file. | 5 / 5 |
Total | 19 / 20 Passed |