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.
A well-structured, highly actionable CLI-workflow skill with concrete commands, explicit branch handling, and useful guardrails. Minor improvements available: deduplicate the context/rules constraint reminder and add an explicit post-write validation/retry loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient imperative guidance with concrete commands and no filler explanations of concepts Claude already knows. The constraint that `context` and `rules` must not be copied into the artifact is repeated three times (in the steps, guidelines, and guardrails), which could be trimmed to one authoritative statement. | 4 / 5 |
Actionability | Commands are copy-paste ready (`openspec list --json`, `openspec status --change "<name>" --json`, `openspec instructions <artifact-id> --change "<name>" --json`) with the returned JSON fields explained, and all status branches (complete, ready, blocked) plus the no-name case are covered with concrete handling. Common cases are well covered. | 5 / 5 |
Workflow Clarity | A clear numbered sequence with explicit status-based branching, an error path for the all-blocked case, and a "verify the artifact file exists after writing" guardrail. It lacks an explicit validate-then-retry feedback loop after writing an artifact, keeping it below the top anchor. | 4 / 5 |
Progressive Disclosure | No bundle files exist, and all content lives inline in a single well-sectioned file (Input, Steps, Output, Artifact Creation Guidelines, Guardrails) at a length appropriate to a single CLI workflow. Organization is good, though the schema-specific artifact patterns could arguably live in a reference file if the skill grows. | 4 / 5 |
Total | 17 / 20 Passed |