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.
An exemplary process skill body: terse, directive, and clearly sequenced with explicit validation gates and feedback loops woven through every phase. Its only weakness is minor — a couple of concrete examples (a sample predicate, a sample audit-trail row) would close the last actionability gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient with zero padding: every line is directive ('Inconclusive is not a pass. Don't hide a negative.', 'Ground first, then commit.') and no concepts Claude already knows are explained. Matches anchor 5 — every token earns its place. | 5 / 5 |
Actionability | Concrete, specific guidance throughout: falsifiable definition of done, riskiest-unknown-first sequencing, harness-before-work with pre-change baseline, worktrees per parallel worker, explicit verdict vocabulary, and a structured final reply. Not 5 because there are minor gaps — no example predicate or audit-trail row is shown (format details are delegated to referenced skills); not 3 because the guidance is specific and executable, not pseudocode. | 4 / 5 |
Workflow Clarity | Phases A-E are clearly sequenced with explicit validation checkpoints (measure each unit against the predicate, keep-or-revert, Phase E whole-product check) and feedback loops for error recovery (revert if not advanced, 'reset and harden the contract', 'fix the gate in its own change'). Matches anchor 5. | 5 / 5 |
Progressive Disclosure | Under 50 lines with no need for external bundle files; sections (Start, Phases A-E) are well-organized and all cross-references to sibling skills (poteto-mode, prove-it-works, show-me-your-work, etc.) are clearly signaled in bold. Per the rubric's simple-skill guideline this scores 5. | 5 / 5 |
Total | 19 / 20 Passed |