Content
57%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.
The content is dense with genuinely valuable market-specific knowledge and mostly actionable guidance, including concrete tool calls and fully priced examples. Its weaknesses are padding from textbook Greeks definitions, no explicit top-level analysis workflow, and a monolithic single-file structure that inlines material better split into references.
Suggestions
Trim the first-order/second-order Greeks definition tables and the 'intrinsic + time value' primer — Claude already knows these; keep only the market-specific management guidance (hedge frequencies, Zakamouline trigger).
Add a numbered top-level workflow (1. fetch and validate the option chain, 2. build the vol surface via quantlib_call, 3. assess skew/term-structure percentile vs history, 4. select strategy from the framework, 5. set Greeks limits and monitor) so the analysis sequence is explicit.
Move the per-strategy detail (calendar spread, vol arbitrage, skew trades, market-making) into references/ files one level deep, keeping SKILL.md as an overview with clearly signaled links, and remove the unused pandas/numpy/scipy dependency block or add code that uses it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body inlines textbook definitions Claude already knows ('Delta (Δ) | Sensitivity to underlying price', 'Gamma | Rate of change of Delta', 'option price = intrinsic value + time value'), though much of the rest is genuinely non-obvious market-specific knowledge (A-share skew, liquidity concentration, Zakamouline hedge trigger). Fits anchor 3 (mostly efficient with some unnecessary explanation); not 4 because the basic Greeks tables and overview padding could be trimmed. | 3 / 5 |
Actionability | Provides a concrete copy-paste tool call (quantlib_call with implied_volatility_surface kwargs), numeric entry conditions ('20-30 days before near-month expiry'), fully priced 50ETF trade examples, explicit position limits, and an output report template. Not 5 because SABR calibration and quoting strategy remain conceptual, and the listed pip dependencies (pandas/numpy/scipy) are never used by any code in the skill. | 4 / 5 |
Workflow Clarity | Each strategy carries entry conditions and risk-control checkpoints ('stop loss if loss exceeds 50% of net debit', 'close when term-structure inverts'), but there is no explicit end-to-end sequence (fetch chain -> build surface -> diagnose skew/term structure -> select strategy -> monitor Greeks); the overall process must be inferred. Anchor 3 (sequence present but implicit/fragmented); not 4 because the top-level analysis workflow is never laid out as ordered steps. | 3 / 5 |
Progressive Disclosure | The file is well-sectioned with clear headers, but ~185 lines of dense strategy detail (four full strategies, SABR parameter tables, market-making specifics) are all inlined with no reference files at all, exceeding the simple-skill threshold where sections alone would suffice. Anchor 3 (content that should be separate is inline); not 2 because structure and navigation within the file are good. | 3 / 5 |
Total | 13 / 20 Passed |