Content
92%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-crafted, self-contained workflow skill: concrete executable commands, an explicit stop-and-wait checkpoint, and guardrails covering naming errors and duplicate changes. The only trimmable redundancy is the thrice-stated --schema handling.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is imperative and lean with zero concept-explanation padding, but schema handling ('--schema') is stated three times (step 2, the note in step 3, and a guardrail bullet). Minor instances of over-explanation that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands ('openspec new change "<name>"', 'openspec status --change "<name>"', 'openspec instructions <first-artifact-id> --change "<name>"'), a named interaction tool (AskUserQuestion), and a concrete kebab-case derivation example. Matches anchor 5: specific commands cover the common cases. | 5 / 5 |
Workflow Clarity | A clear numbered 1-6 sequence with an explicit STOP checkpoint (step 6), a status-driven decision point ('find the first artifact with status "ready"'), and error-recovery guardrails (invalid name -> ask for a valid one; existing change -> suggest continuing). No destructive or batch operations, so the feedback-loop cap does not apply; checkpoints and recovery guidance are explicit, matching anchor 5. | 5 / 5 |
Progressive Disclosure | No bundle files exist and none are needed: every section (Input, Steps, Output, Guardrails) is essential workflow instruction that belongs in SKILL.md, with nothing inlined that should be split out and trivially easy navigation. Per the simple-skill guidance this self-contained, well-sectioned structure matches anchor 5; not 4 because there are no organization gaps to point to. | 5 / 5 |
Total | 19 / 20 Passed |