Content
86%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.
A strong, well-structured skill body: executable commands with explicit thresholds, a clearly phased workflow with meaningful guardrails, and exemplary progressive disclosure verified against the real bundle. The only weaknesses are minor redundancy with the frontmatter description in the trigger section and the lack of an explicit error-recovery loop for API failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and teaches genuinely non-obvious domain knowledge (Shapiro's fade-the-speculators thesis, the Friday 3:30pm ET / prior-Tuesday publication lag), but the 'When to Use This Skill' trigger lists (English and Japanese) and the step-1-of-5 boundary sentence duplicate the frontmatter description and could be trimmed. It sits above the 3 anchor (some unnecessary explanation) because there is no generic padding of concepts Claude already knows. | 4 / 5 |
Actionability | Commands are copy-paste ready across the common cases (--core, --symbols, full universe), thresholds are explicit (COT Index >= 90 / <= 10), output artifacts are precisely named (reports/cot_crowding_<date>.json/.md with described sections), and manual steps 2-5 include concrete tools (WebSearch, weekly chart, stop placement). | 5 / 5 |
Workflow Clarity | Phases 1-3 are clearly sequenced with real checkpoints (skipped markets are listed with reasons and never silently dropped; 'Never recommend an entry from crowding alone - steps 2 and 3 must both confirm first'), but there is no explicit error-recovery feedback loop in the body (e.g., what to do on API/auth failure beyond the Premium+ prerequisite note), which keeps it below the 5 anchor's 'feedback loops for error recovery'. | 4 / 5 |
Progressive Disclosure | Verified against the actual bundle: all three referenced files (shapiro-methodology.md, cot-index-calculation.md, output-contract.md) exist, references are one level deep (only peer cross-references, no nested chains), the Resources section describes each file's contents, and 'When to Load References' gives explicit load/skip-per-situation guidance. | 5 / 5 |
Total | 18 / 20 Passed |