Content
52%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body delivers genuinely actionable market-sizing guidance with concrete formulas, thresholds, and a worked example, and the six-step workflow is clearly sequenced with a validation step. However, it is padded with boilerplate and explanations of concepts Claude already knows, and its progressive disclosure is largely broken: five of the six referenced files do not exist in the bundle, leaving the reader stranded at nearly every "see file" pointer.
Suggestions
Fix the dangling references: either create the advertised files (`references/methodology-deep-dive.md`, `references/industry-templates.md`, the three `examples/` files) or remove the pointers — and correct the `resources/implementation-playbook.md` path to the actual `references/` directory.
Cut the boilerplate sections ("Use this skill when", "Do not use this skill when", generic "Instructions") and the restated "When to Use Each Methodology" section, and delete the verbatim repetition of the frontmatter description at the top of the body.
Move the industry-specific TAM formulas and the investor/strategy presentation structures into real reference files, keeping SKILL.md as a lean overview with one-level-deep, verified links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 420-line body contains several padded or redundant sections: generic boilerplate ("Use this skill when... working on market sizing analysis tasks", "Clarify goals, constraints, and required inputs"), a verbatim repeat of the frontmatter description, and explanations of standard business concepts Claude already knows (what TAM/SAM/SOM are, definitions of top-down vs bottom-up). The "When to Use Each Methodology" section is then restated nearly in full inside "Three-Methodology Framework". This matches the "noticeably verbose; several unnecessary explanations or padded sections" anchor rather than the mostly-efficient anchor 3. | 2 / 5 |
Actionability | For an instruction-only skill the guidance is concrete: explicit formulas ("SAM = TAM × 0.40 × 0.30 × 0.60 = $720M"), a fully worked numeric example, named data sources per methodology, and quantified heuristics (2-5% capture rate, 30% triangulation tolerance, red-flag thresholds). This lands on the "mostly executable guidance with minor gaps" anchor; it stops short of anchor 5 only because some guidance remains directional (e.g., "Review with industry experts") without a concrete procedure. | 4 / 5 |
Workflow Clarity | Steps 1-6 (plus Quick Start) form a clear, well-sequenced process, and Step 6 "Validate and Triangulate" provides explicit checkpoints ("should be within 30%", "SOM > 10% in 5 years" red flags). It sits at anchor 4 rather than 5 because validation signals are listed but there is no explicit feedback loop instructing what to revise and re-check when a red flag triggers. | 4 / 5 |
Progressive Disclosure | Scored against the actual bundle: of the six files referenced in the body (`resources/implementation-playbook.md`, `references/methodology-deep-dive.md`, `references/industry-templates.md`, and three `examples/` files), only `references/data-sources.md` exists — five references are dangling, and the directory is even misnamed (`resources/` vs `references/`). Additionally, substantial content that belongs in those files (industry-specific templates, presentation structures, worked examples) is inlined in the monolithic body. This matches anchor 2 (minimal effective structure, content inlined that belongs in separate files) rather than anchor 3, because most advertised navigation points are broken. | 2 / 5 |
Total | 12 / 20 Passed |