Content
27%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a high-level outline rather than actionable guidance. It lacks any concrete code, specific libraries, executable examples, or validation steps. The referenced resource file (`resources/implementation-playbook.md`) is missing from the bundle, leaving the skill hollow — the body delegates to a file that doesn't exist, and what remains is too abstract to be useful.
Suggestions
Add concrete, executable code examples for at least one backtesting pattern (e.g., a minimal event-driven backtest loop using a specific library like backtrader or vectorbt).
Include explicit validation checkpoints in the workflow, such as verifying data integrity before simulation, checking for look-ahead bias, and validating output metrics against known benchmarks.
Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the essential patterns and examples directly in the SKILL.md body.
Replace vague instructions like 'Build point-in-time data pipelines' with specific, actionable steps including code snippets or concrete commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but includes some unnecessary sections like 'Use this skill when' / 'Do not use this skill when' which are somewhat boilerplate and don't add much actionable value. The 'Limitations' section is generic filler that Claude already knows. | 2 / 3 |
Actionability | The instructions are vague and abstract — 'Build point-in-time data pipelines and realistic cost models' and 'Implement event-driven simulation and execution logic' describe rather than instruct. There are no concrete code examples, commands, specific libraries, or executable guidance. The skill delegates to a resource file that doesn't exist in the bundle. | 1 / 3 |
Workflow Clarity | There is a rough sequence implied in the instructions (define hypothesis → build pipelines → implement simulation → use splits), but there are no validation checkpoints, no feedback loops, and no explicit verification steps for what is inherently a multi-step, error-prone process. | 2 / 3 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` for detailed patterns and examples, but this file is not provided in the bundle. The main content is too thin to stand alone, and the referenced resource doesn't exist, making the progressive disclosure structure broken. | 1 / 3 |
Total | 6 / 12 Passed |