Content
96%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.
An exceptionally well-structured instruction skill: concise, concrete, and sequenced with validation checkpoints and feedback loops. The only weakness is progressive disclosure — the body references templates/ and prompts/ files that are not present in the bundle.
Suggestions
Ship the referenced templates/ files (case.md, report.md, issue.md, bundle-README.md) and prompts/ files (analyst-common.md, the seven analyst dimension files, scrub.md, scrub-audit.md, similar-session.md) so every inline reference resolves.
Alternatively, if any prompt/template is intentionally omitted from this bundle, note that explicitly at first reference so navigation expectations are clear.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient throughout — no padded explanation of concepts Claude already knows, and dense high-value artifacts like the Quick reference and Red Flags tables where every token earns its place. | 5 / 5 |
Actionability | Highly concrete guidance: exact paths ('~/.superpowers/diagnosing-superpowers/<session-id>/'), enumerated dispatch files, copy-ready commands ('zip -r', 'tar -czf', 'gh'), and named redaction levels (skeleton/evidence/full) with no vague direction. | 5 / 5 |
Workflow Clarity | Seven clearly numbered steps with explicit run conditions, approval gates, and a real feedback loop (scrub then scrub-audit, 'repeating both until the audit returns CLEAN') appropriate for sharing/exporting session data. | 5 / 5 |
Progressive Disclosure | SKILL.md is a well-structured overview with one-level-deep, clearly signaled references, but a large share of referenced bundle paths (templates/* and prompts/*) do not exist in the bundle, which is more than a minor navigation gap. | 4 / 5 |
Total | 19 / 20 Passed |