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 body is well-organized and concise with sensible use/do-not-use and safety sections, but its instructions are abstract rather than executable and the sole referenced detail file is missing from the bundle.
Suggestions
Add a concrete code skeleton or a sample backtest config so the Instructions are executable rather than purely directive.
Insert an explicit validation step in the workflow (e.g., 'After building the simulator, run it on a known strategy and confirm metrics match expected values before proceeding').
Create the referenced 'resources/implementation-playbook.md' so the progressive-disclosure pointer resolves, or remove the reference if no detail file will be bundled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence with no concept over-explanation; the only minor redundancy is the description sentence repeated as the opening line and the resource reference stated twice. | 4 / 5 |
Actionability | Instructions give concrete directives ('Define hypothesis, universe, timeframe, and evaluation criteria', 'Use train/validation/test splits and walk-forward testing') but contain no executable code or commands, leaving the implementation specifics to be inferred. | 3 / 5 |
Workflow Clarity | A rough sequence is present (define → build pipelines → implement simulation → split/walk-forward), but there are no explicit validation checkpoints or feedback loops to verify the backtest's correctness at each stage. | 3 / 5 |
Progressive Disclosure | Structure is good with a one-level-deep, clearly signaled reference to 'resources/implementation-playbook.md', but the referenced file does not exist in the bundle, making the navigation pointer a dead end. | 3 / 5 |
Total | 13 / 20 Passed |