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 strong example of an instruction-only skill: fully executable CLI commands, concrete edge-case handling, a clear sequence with an explicit stop point, and disciplined guardrails. Only minor trims and failure-path handling would improve it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and operational, with almost every line giving instructions or commands. Minor redundancy — "Pass --schema if using a non-default workflow" repeats steps 2-3 and the "IMPORTANT" line restates step 1 — keeps it at 'minor instances of over-explanation that could be trimmed' rather than anchor 5. | 4 / 5 |
Actionability | Commands are copy-paste ready with explicit placeholders ("openspec new change \"<name>\"", "openspec status --change \"<name>\"", "openspec instructions <first-artifact-id> --change \"<name>\""), and edge cases are handled concretely (kebab-case derivation example, schema selection rules, invalid-name and duplicate-change handling). | 5 / 5 |
Workflow Clarity | A clear numbered sequence with an explicit STOP checkpoint, error-recovery paths for invalid names and existing changes, and use of status output to determine the next step. It falls short of anchor 5 because there is no validation of command success (e.g., what to do if the openspec CLI is missing or a command fails). | 4 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the content is self-contained with well-organized Input/Steps/Output/Guardrails sections and nothing that belongs in a separate file. At roughly 72 lines it exceeds the under-50-line simple-skill exception, so 'good structure; minor organization gaps' is the best fit. | 4 / 5 |
Total | 17 / 20 Passed |