Content
32%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a reference manual or encyclopedia entry on weight loss metrics than an actionable skill for Claude. It is bloated with classification tables and lengthy output templates that Claude could generate on its own, while lacking executable code, clear workflows, and proper file structure. The safety boundaries are present but not integrated into a validation workflow.
Suggestions
Remove or drastically condense the BMI/body fat/waist classification tables and output report templates—Claude already knows these standards and can generate formatted reports. Focus the skill body on the specific calculation pipeline and decision logic unique to this system.
Add a clear numbered workflow showing the end-to-end process: gather inputs → calculate metrics → check safety boundaries → generate recommendation, with explicit validation steps (e.g., 'If calculated intake < minimum threshold, cap at minimum and warn user').
Move the four lengthy output format examples to a separate TEMPLATES.md or EXAMPLES.md file and reference them from the main skill, keeping only a brief example inline.
Provide actual JSON schemas for the referenced data files (fitness-tracker.json, nutrition-tracker.json, health-logs) or include them as bundle files, so Claude knows the exact data structures to read and write.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is heavily verbose with extensive reference tables (BMI classifications, body fat ranges, waist circumference standards) that Claude already knows, and four full-length example reports that bloat the content significantly. The formulas themselves are useful but the surrounding explanations and lengthy output templates could be drastically condensed. | 2 / 5 |
Actionability | The skill provides concrete formulas and classification thresholds, but lacks executable code. The 'example commands' at the end reference slash commands that aren't defined anywhere. The output format examples are detailed but are templates rather than executable guidance—there's no actual implementation showing how to read data files, perform calculations, or generate reports. | 3 / 5 |
Workflow Clarity | There is no clear multi-step workflow or sequencing. The skill lists capabilities (body composition, metabolic rate, energy gap, phase management) as independent sections without showing how they connect or what order to follow. There are no validation checkpoints—for example, no step to verify calorie calculations against safety boundaries before recommending a plan, despite the safety section existing separately. | 2 / 5 |
Progressive Disclosure | The content is a monolithic wall of text at ~250+ lines with no references to external files despite referencing data paths like `data/fitness-tracker.json` and `data/nutrition-tracker.json` without providing their schemas. The four lengthy output format examples should be in a separate file. No bundle files are provided to support the referenced paths. | 2 / 5 |
Total | 9 / 20 Passed |