Content
87%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 lean, well-structured, and provides fully executable commands, but it lacks any workflow sequencing and validation checkpoints for destructive financial operations, which caps workflow clarity.
Suggestions
Add a brief recommended workflow with validation, e.g. check `/percolator status` before opening a position and confirm size/collateral before `/percolator long`.
Include a verification step after deposits/withdrawals (re-check `/percolator positions` or status) to form a validate-feedback loop.
Note risk guardrails (e.g. confirm leverage and sufficient collateral) before destructive commands like long/short/withdraw.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | A one-line summary plus a compact command table with no padding or explanation of concepts Claude already knows (perps, funding, OI); every token earns its place, matching the 'lean and efficient' anchor. | 5 / 5 |
Actionability | The Commands block lists concrete, copy-paste-ready slash commands with arguments and per-command descriptions covering the common cases (status, positions, long, short, deposit, withdraw, help), matching 'fully executable; copy-paste ready'. | 5 / 5 |
Workflow Clarity | The body is a flat command menu with no multi-step sequence and no validation/verification for risky operations like opening leveraged positions or withdrawing collateral; the destructive-operations cap limits this to 3 even though individual commands are unambiguous. | 3 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references and well-organized into a description plus a Commands section, matching the simple-skill exception allowing 5 with just well-organized sections. | 5 / 5 |
Total | 18 / 20 Passed |