Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill body is highly actionable and clearly sequenced with strong validation checkpoints for a destructive move-to-archive operation. Its main weaknesses are mild redundancy in the Guardrails section and the absence of any progressive-disclosure structure.
Suggestions
Trim the Guardrails section to only net-new guidance not already covered in the numbered steps to improve conciseness.
Consider moving the output template and/or sync-assessment detail into a referenced reference file to establish a clearer overview-then-detail progressive-disclosure structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean and actionable with no concept-explanation fluff, but the trailing Guardrails section repeats guidance already stated in the steps (e.g., 'Always prompt for change selection'), so it could be tightened rather than earning the every-token-earns-its-place level 3. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout ('openspec list --json', 'openspec status --change --json', 'mkdir -p openspec/changes/archive', 'mv ...') with specific paths and a copy-paste-ready output template, matching the fully-executable level-3 anchor. | 3 / 3 |
Workflow Clarity | The six steps are clearly sequenced with explicit validation checkpoints (artifact status check, task completion count, sync-state assessment, and a target-exists guard that fails with an error), matching the clear-sequence-with-explicit-validation level-3 anchor. | 3 / 3 |
Progressive Disclosure | No bundle files exist and the body is well-sectioned (Input, Steps, Output, Guardrails) with only a one-level external skill reference, but it is a flat procedural document with no overview-then-deep-reference structure, so it does not reach the clear-progressive-disclosure level-3 anchor. | 2 / 3 |
Total | 10 / 12 Passed |