Content
85%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.
Highly actionable and well-sequenced content with a concrete output contract, undermined only by progressive-disclosure gaps where referenced bundle files are not actually present.
Suggestions
Ship the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) under a references/ or examples/ directory so the cited paths resolve.
Trim rhetorical flourishes (e.g. "telegraphs a move upmarket", "detonates in a live deal") to tighten token efficiency.
Confirm the sibling-skill links (../autonomous-investigation/SKILL.md, etc.) resolve from this skill's installed location, or mark them as optional cross-references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean, assumes Claude's competence, and avoids explaining basics, but carries occasional rhetorical flourishes ("telegraphs", "detonates") that could be trimmed. | 4 / 5 |
Actionability | A copy-paste output schema, a four-step application sequence, explicit Fact/Inference/Assumption labeling, and four concrete Final Step options give fully executable, instruction-ready guidance. | 5 / 5 |
Workflow Clarity | The process is clearly sequenced (determine mode → credit inline context → capture → emit schema) with mode selection, a 2-question budget, and a stable schema contract as checkpoints. | 5 / 5 |
Progressive Disclosure | The body signals one-level-deep references (template.md, examples/sample.md, examples/sample-industrial.md) but no references/scripts/assets bundle directories exist, so those referenced files are not present to verify. | 3 / 5 |
Total | 17 / 20 Passed |