Content
82%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 dense, highly actionable reference with executable code, mapping tables, and clear workflows backed by a real bundle file. Minor gains are available by trimming marketing-style asides and adding an explicit error-recovery feedback loop.
Suggestions
Remove the 'most widely-used open-source quant framework in mainland China (39k+ GitHub stars)' marketing line; it adds tokens without aiding execution.
Add an explicit validate→fix→retry loop in the workflow (e.g. run the vnpy backtester on the generated file, and if it errors, re-read signal_engine.py and regenerate).
Move the bulk of the inline canonical template fully into scripts/cta_template.py and keep only a trimmed skeleton inline, tightening the main body further.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and dense with high-value reference tables, executable templates, and mapping tables; a few minor over-explanations (the '39k+ GitHub stars' framing and the 'faster and avoids look-ahead bias' aside) could be trimmed. | 4 / 5 |
Actionability | Provides a full canonical CtaTemplate skeleton, an ArrayManager indicator-mapping table, a signal→order mapping table, a multi-timeframe example, and a copy-paste backtester snippet, all executable with justified placeholders. | 5 / 5 |
Workflow Clarity | Two clearly sequenced numbered workflows plus a pre-save Quality Checklist that acts as a verification checkpoint; lacks an explicit validate→fix→retry feedback loop, leaving a minor validation gap. | 4 / 5 |
Progressive Disclosure | Well-organized sections with a clearly signaled one-level-deep reference to the real bundle file scripts/cta_template.py and a References block; the inlined canonical template is somewhat long but justified, so structure is good rather than exemplary. | 4 / 5 |
Total | 17 / 20 Passed |