Content
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but bloated reference document that reads more like a career advice blog post than a concise skill instruction. While it contains useful templates (compensation calculator, side-by-side comparison, weighted matrix), it's buried under excessive explanatory content that Claude already knows. The lack of any progressive disclosure structure and the absence of validation steps in the workflow significantly reduce its effectiveness as a skill file.
Suggestions
Cut the content by 60%+ by removing sections Claude already knows: 'The Comparison Challenge', 'Questions to Ask Yourself', 'Red Flags to Watch', and general career advice. Focus on the templates and calculation methodology.
Split into multiple files: keep SKILL.md as a concise overview with the core workflow and output format, then reference separate files like TEMPLATES.md (calculation templates), FACTORS.md (non-monetary scoring framework), and RED_FLAGS.md.
Add an explicit workflow sequence with validation: Step 1: Gather offer details (list required inputs), Step 2: Calculate total comp (verify all components accounted for), Step 3: Score non-monetary factors (confirm weights with user), Step 4: Present comparison and recommendation.
Remove filler phrases like 'The Problem:', 'The Solution:', and rhetorical questions. Replace with direct instructions like 'Always calculate Year 1 and Ongoing totals separately because signing bonuses are one-time.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Explains concepts Claude already knows well (what makes comparing offers hard, gut check questions, Monday morning test). Sections like 'The Comparison Challenge' and 'Questions to Ask Yourself' are padded filler that don't add actionable value. Red flags lists and self-reflection questions are general knowledge Claude doesn't need spelled out. | 1 / 3 |
Actionability | Provides concrete templates and calculation examples which are useful, but these are static markdown templates rather than executable code. The weighted decision matrix walkthrough is a good example but is more of a manual process description than something Claude can directly execute. No actual computation scripts or tools are referenced. | 2 / 3 |
Workflow Clarity | The weighted decision matrix has a clear 3-step process, and the output format provides a structured template. However, there are no validation checkpoints or feedback loops — no guidance on verifying calculations, confirming data completeness with the user, or handling missing information. The overall flow from input gathering to recommendation is implicit rather than explicitly sequenced. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. No references to external files, no separation of the detailed templates from the overview. The compensation calculator, comparison templates, non-monetary frameworks, red flags, and self-reflection questions could all be separate reference files, but instead everything is dumped into one massive document. | 1 / 3 |
Total | 6 / 12 Passed |