Content
85%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 well-organized task-triggered workflow skill: concise overview, executable lookup commands, a sequenced verification-oriented workflow, and clean one-level-deep references. Minor conciseness and in-body actionability trim could push it higher.
Suggestions
Tighten the 'Critical: Do Not Trust Internal Knowledge' section into a compact numbered checklist to reduce prose that restates general caution.
Inline a minimal copy-paste agent-or-workflow recipe in the body so the most common task is actionable without opening references.
Move the time-stamped version note ('v1.6.2 / core 1.27.0 as of 2026-04') into references/packages.md so stale date/version tokens don't bloat the overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and assumes Claude's competence, but sections like 'Critical: Do Not Trust Internal Knowledge' and the remote-fallback prose carry some over-explanation that could be trimmed. | 4 / 5 |
Actionability | Concrete, executable commands throughout (package detection, install, grep, jq SOURCE_MAP lookups); recipes are delegated to references rather than fully inlined, leaving minor gaps in the body itself. | 4 / 5 |
Workflow Clarity | Clear sequenced lookup flow with version resolution, typecheck after every change, an error-symptom grep fallback, and an explicit 'if docs cannot be found, say so' recovery checkpoint. | 5 / 5 |
Progressive Disclosure | Clear overview body with well-signaled, one-level-deep references to three real files (packages.md, agents-and-workflows.md, common-errors.md), each mapped to a distinct purpose; navigation is easy. | 5 / 5 |
Total | 18 / 20 Passed |