Content
82%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 a well-structured, highly actionable verification workflow with concrete commands, decision branches, degradation rules, and a defined output format. Its main weaknesses are the absence of feedback loops and a report template that could be slightly tightened.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and procedural with real commands, parsing rules, and output templates; only minor padding remains (repetitive "Recommendation:" scaffolding and restating obvious checks like "Check file naming, directory structure, coding style"). | 4 / 5 |
Actionability | Guidance is fully concrete: exact CLI commands ("openspec status --change \"<name>\" --json"), exact parsing rules ("- [ ] vs - [x]"), exact issue-message templates per priority tier, and a specified output format with file:line reference style — copy-paste-ready for an instruction-only skill. | 5 / 5 |
Workflow Clarity | A clear 8-step sequence with explicit conditionals at each step ("If tasks.md exists...", "If no design.md: skip and note"), a graceful-degradation matrix, and explicit final-assessment decision rules; not a 5 because no validate-and-retry feedback loops are specified. | 4 / 5 |
Progressive Disclosure | A single-file skill (no references/scripts/assets bundle exists) with well-organized numbered steps and headers; at ~160 lines it exceeds the simple-skill exception, but nothing inlined clearly belongs in a separate file, so structure is good with only minor organization gaps. | 4 / 5 |
Total | 17 / 20 Passed |