Content
90%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.
A dense, highly actionable routing and operations doc: exact commands, environment variables, and error-recovery guidance with no filler. The gaps are structural — no explicit step-sequence overview and detail references that live outside the skill bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean throughout: no concept explanations Claude already knows, every section carries non-inferable operational detail (exact script paths, env vars, error names, allowlist syntax). Even the '(not provided)' note earns its place by preventing misdiagnosis of normal data as a bug. | 5 / 5 |
Actionability | Fully executable guidance: a routing table with exact commands ("${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run matomo_report.py ...), a copy-paste allowlist export line, install steps, and an error-to-remedy map covering six failure classes (SSRF refusal, redirects, missing credentials, 401/403, result=error, network errors). | 5 / 5 |
Workflow Clarity | Checkpoints and feedback loops are present — the matomo_auth.py --check gate, exact error names to act on, and per-error recovery guidance — but the body is organized as lookup sections rather than an explicit end-to-end step sequence (check -> report -> handle errors -> format), which the top anchor expects. | 4 / 5 |
Progressive Disclosure | Well-organized sections with clearly signaled one-level references ("Details in extensions/matomo/docs/MATOMO-SETUP.md and SECURITY.md"), but no bundle files ship alongside the skill (no references/, scripts/, or assets/ directories), so the pointed-to detail lives outside the skill and the body must carry routing/error detail inline. | 4 / 5 |
Total | 18 / 20 Passed |