Content
96%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.
The body is lean, highly actionable, and workflow-sequenced with strong validation feedback loops. The only gap is that the one external reference (reference.md) is signaled but not actually shipped in the bundle.
Suggestions
Ship the referenced reference.md file (or remove the link to it) so the 'More symptoms, exact error strings and log stage names' pointer resolves.
Consider moving the large finding→action table to reference.md to keep SKILL.md as a tighter overview, since the table is the bulk of the token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and signal-rich, assumes Claude's competence throughout (no basic concept explanations), and every line carries diagnostic value; it respects the token budget without padding. | 5 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands (curl probes, claude plugin/mcp commands, node doctor script) and a concrete finding→meaning→action table covering the common cases. | 5 / 5 |
Workflow Clarity | Clear top-down sequence (run doctor → map findings top-down fixing the first ✗ and rerunning → targeted checks → Fixing) with explicit validation feedback loops ('rerun before chasing the next', 'Confirm the fix by rerunning the doctor, then by observing an <openviking-context> block'). | 5 / 5 |
Progressive Disclosure | Well-organized sections with a single clearly-signaled one-level-deep reference to reference.md, but that referenced file is not present in the bundle, which is a minor navigation gap that prevents a top score. | 4 / 5 |
Total | 19 / 20 Passed |