Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a tight, actionable reference: executable CLI commands throughout, a clear precheck-to-action-to-error-recovery workflow with validation checkpoints, and clean sectioning. It assumes Claude's competence and avoids conceptual padding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence: a primitives table, concise code blocks, and a compact candidateSource enum with no over-explanation of concepts Claude already knows. It is not a 2 because there is no padded conceptual prose; the inline JSON sample directly serves execution. | 3 / 3 |
Actionability | Every action is a concrete, copy-paste-ready CLI command with flags and --json output (e.g. `bestblogs discover today --limit 20 --json`, `bestblogs discover search "AI coding" --type ARTICLE --sort score --limit 10 --json`), matching the 3-anchor for fully executable commands with specific examples. | 3 / 3 |
Workflow Clarity | Clear sequence from auth precheck (`bestblogs auth status --json`) to core action to an error-handling section with explicit feedback loops per status code (403→降级, 404→public_brief/following, 429→退避重试, empty candidates→建议 intake setup), matching the 3-anchor for a clear sequence with explicit validation/recovery checkpoints. | 3 / 3 |
Progressive Disclosure | No bundle files exist; the skill is a single self-contained SKILL.md cleanly sectioned (何时使用/原语/前置检查/核心动作/其它动作/错误处理/组合建议), and cross-skill references (bestblogs-read, bestblogs-capture, bestblogs-explain) are one-level and clearly signaled. Per the simple/inline skill scoring note, well-organized single-file content scores 3. | 3 / 3 |
Total | 12 / 12 Passed |