Content
42%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 provides a comprehensive conceptual framework for market sizing but suffers from significant verbosity, explaining many concepts Claude already knows and repeating information across sections. The content is more of a business textbook chapter than an actionable skill—it lacks executable artifacts, concrete tool usage, and tight workflow checkpoints. The progressive disclosure structure is partially present but undermined by inlining too much content that should live in the referenced files.
Suggestions
Reduce the body to ~100 lines by removing explanations of basic concepts (what TAM/SAM/SOM are, what industry reports are) and moving industry-specific templates, presentation guidance, and common mistakes into the referenced files.
Add concrete, executable artifacts: a spreadsheet formula template, a structured JSON/markdown output format for the analysis, or a checklist that Claude can fill in and return to the user.
Add explicit validation checkpoints with decision logic, e.g., 'If top-down and bottom-up differ by >30%, investigate the discrepancy by checking X before proceeding.'
Consolidate the duplicated Quick Start and Step-by-Step sections into a single workflow, and move the detailed methodology descriptions into the referenced `references/methodology-deep-dive.md` file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is severely verbose for an AI audience. It explains basic concepts Claude already knows (what TAM/SAM/SOM are, what industry reports are, what a marketplace is), repeats the same formulas and examples multiple times across sections (e.g., the email marketing example appears repeatedly), and includes extensive lists of common mistakes and presentation advice that are general business knowledge rather than novel instruction. | 2 / 5 |
Actionability | The skill provides formulas and a structured process, but everything remains at the conceptual/framework level with no executable code, no concrete data lookup commands, no spreadsheet templates, and no actual tool usage. The formulas are pseudocode-level arithmetic rather than executable guidance. The examples use illustrative numbers but don't constitute copy-paste-ready artifacts. | 3 / 5 |
Workflow Clarity | There is a clear 6-step process (Define → Gather → Calculate TAM → Calculate SAM → Calculate SOM → Validate) and a Quick Start summary. However, validation is mentioned but lacks concrete checkpoints or feedback loops—Step 6 says 'compare top-down and bottom-up results (should be within 30%)' but doesn't specify what to do if they diverge beyond that. The workflow is sequential but lacks explicit decision points and error recovery. | 3 / 5 |
Progressive Disclosure | The skill references external files in `references/` and `examples/` directories with clear descriptions, which is good structure. However, no bundle files are provided, so these references are unverifiable. More importantly, the SKILL.md itself is a monolithic ~300-line document that inlines extensive content (industry-specific considerations, presentation guidance, common mistakes) that would be better placed in the referenced files, undermining the progressive disclosure pattern. | 3 / 5 |
Total | 11 / 20 Passed |