Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is highly actionable with executable commands and a well-sequenced, validated workflow. Its only real weakness is mild redundancy between step 4 and the Artifact Creation Guidelines section, which slightly undercuts conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean and command-driven, but the "Artifact Creation Guidelines" section restates points already covered in step 4 (template usage, context/rules as constraints, reading dependencies), so it could be tightened — matching the score-2 anchor rather than the fully lean score-3. | 2 / 3 |
Actionability | It provides fully executable commands (`openspec new change`, `openspec status --json`, `openspec instructions --json`) plus the specific JSON fields to parse and tool usage (TodoWrite, AskUserQuestion), meeting the copy-paste-ready score-3 anchor. | 3 / 3 |
Workflow Clarity | The five-step sequence is clearly ordered with explicit checkpoints: re-run status after each artifact, confirm every `applyRequires` artifact is `done`, and "Verify each artifact file exists after writing before proceeding to next" — a validation feedback loop appropriate for this batch operation. | 3 / 3 |
Progressive Disclosure | The skill is self-contained with no bundle files and is organized into clearly labeled sections (Input, Steps, Output, Guidelines, Guardrails) with no nested references, so navigation is easy and progressive disclosure is appropriately handled within a single file. | 3 / 3 |
Total | 11 / 12 Passed |