Content
10%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 like a persona description or job posting rather than an actionable skill file. It spends hundreds of tokens describing what the analyst should know and how it should behave, but provides zero concrete tools, formulas, templates, or executable guidance. The content is severely verbose, repeating similar concepts across multiple sections (behavioral traits, capabilities, knowledge base, quality standards) without adding actionable value.
Suggestions
Replace the descriptive capability lists with concrete, executable artifacts: actual TAM calculation templates with formulas, specific financial model structures with example numbers, and worked examples showing input → output for common tasks.
Cut the content by 70%+ by removing sections that describe Claude's personality traits, general knowledge areas, and abstract capabilities. Focus only on what Claude wouldn't already know: specific frameworks, formulas, benchmark numbers, and decision trees.
Add concrete workflow sequences for the core tasks (e.g., 'Market Sizing Workflow: 1. Identify target segment → 2. Calculate bottom-up using [formula] → 3. Validate with top-down → 4. Cross-check against [benchmark source]') with specific validation checkpoints.
Move detailed reference material (metrics benchmarks, compensation data, industry-specific templates) into separate bundle files and reference them clearly from a concise SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Extensively explains concepts Claude already knows (what market sizing is, what Porter's Five Forces is, what SaaS metrics are, behavioral traits Claude should exhibit). The vast majority of content is descriptive padding—listing capabilities, knowledge areas, and behavioral traits rather than providing actionable instructions. Multiple sections repeat the same ideas (e.g., quality standards, behavioral traits, and response approach all overlap significantly). | 1 / 5 |
Actionability | Despite its length, the skill contains zero executable code, no concrete commands, no specific formulas, no templates, and no copy-paste-ready artifacts. Everything is abstract description ('Apply relevant best practices', 'Use proven methodologies', 'Calculate and analyze'). The 'Example Interactions' section lists questions but provides no answers or worked examples. References to commands like `/market-opportunity` and skills like 'market-sizing-analysis' have no concrete implementation details. | 1 / 5 |
Workflow Clarity | The 'Response Approach' section lists 10 high-level steps but they are generic and vague ('Understand context', 'Activate relevant skills', 'Apply frameworks'). No validation checkpoints, no feedback loops, no concrete sequencing for any specific analytical task. The steps could apply to virtually any analytical task and provide no startup-analyst-specific workflow guidance. | 2 / 5 |
Progressive Disclosure | References `resources/implementation-playbook.md` and several skills/commands but no bundle files are provided, making these references unverifiable dead ends. The massive amount of content inlined in SKILL.md (core expertise, knowledge base, special considerations) should clearly be split into separate reference files. The structure has headers but the content within them is bloated and poorly organized for discovery. | 2 / 5 |
Total | 6 / 20 Passed |