Content
47%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 body is a comprehensive, mostly actionable API reference, but it fails on structure and workflow safety: a huge API surface is inlined rather than progressively disclosed, and high-risk financial operations lack any validation or feedback-loop guidance.
Suggestions
Move the per-exchange API reference (Binance, Bybit, Hyperliquid, MEXC) into separate files under references/ and keep SKILL.md as a concise overview with one-level-deep links.
Add a sequenced trading workflow with validation checkpoints (e.g. check balance → set leverage/margin → place order → verify position → set TP/SL), including a validate-then-proceed feedback loop for close-all and batch operations.
Trim redundant or rarely-used method listings to reduce token load, or gate them behind clearly signaled reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body avoids explaining concepts Claude already knows and stays dense, but ~850 lines of inlined method listings is a heavy token load that could be trimmed or relocated. | 3 / 5 |
Actionability | Concrete, copy-paste-ready TypeScript examples with real parameters cover the common cases, with only minor gaps where identifiers like orderId, walletAddress, startTime, or endTime are used without being obtained. | 4 / 5 |
Workflow Clarity | This is a destructive/batch operation skill (real-money leveraged trading, close-all, batch orders) with no multi-step workflow, validation checkpoints, or feedback loops; the destructive-ops cap applies and the rough category grouping does not constitute a real sequence. | 2 / 5 |
Progressive Disclosure | No bundle files exist and the entire 200+ method per-exchange API reference is inlined in SKILL.md — content that clearly belongs in separate per-exchange reference files is monolithically inlined despite section headers providing minimal structure. | 2 / 5 |
Total | 11 / 20 Passed |