Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured skill body: a clear multi-step method with verification boundaries, concrete tool usage, format-specific anatomies, and a clean reference structure where every cited file exists. It adds only domain-specific guidance Claude would not already know.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~80-line body is dense with domain-specific, non-obvious guidance (procedural-timing framing, the rule that web research never verifies law, Midpage tool-usage constraints) and avoids explaining concepts Claude already knows; length is justified by a genuinely complex process rather than padding. | 3 / 3 |
Actionability | Gives concrete, executable guidance throughout — named tools and fields (analyzeOpinion, supportedPropositions, deeplinkURL, doesNotAddress), specific word-count targets per format, and verbatim disclaimer/byline text — making the instructions copy-paste ready despite being instruction-only. | 3 / 3 |
Workflow Clarity | An 8-step Method is clearly sequenced with an explicit steering check-in (step 5) and layered verification rules (analyzeOpinion is what permits a citation; check doesNotAddress before citing; never invent dates), satisfying the explicit-checkpoint anchor. | 3 / 3 |
Progressive Disclosure | The body is an overview that signals one-level-deep references at the right moments (litigation-writing.md, citations.md, court-rules.md, legal-docx.md), all of which exist as real bundle files, with detail appropriately split out rather than inlined. | 3 / 3 |
Total | 12 / 12 Passed |