Conciseness

The body is lean and directive with zero padding — no explanations of concepts Claude already knows ('Produce research that supports decisions, not research theater'). Every line prescribes behavior, matching the 'lean and efficient; every token earns its place' anchor.

Actionability

Concrete collection checklists per mode ('fund size, stage, and typical check size', 'top-down estimates... bottom-up sanity checks') and a fully specified six-part output structure give mostly executable guidance. It falls short of 5 because execution details are missing — no source-citation format, no numeric sizing method, no example output — but it is above 3 since the guidance is specific and directly actionable rather than vague.

Workflow Clarity

The implied sequence (choose mode → collect → structure output → gate) ends in an explicit validation checklist ('## Quality Gate / Before delivering: all numbers are sourced...'), so most checkpoints are present. It is not 5 because the research process itself (search → verify → resolve conflicting sources → synthesize) is not explicitly sequenced with feedback loops, leaving minor validation gaps.

Progressive Disclosure

No bundle files exist and none are needed at this size; the content is self-contained, well-sectioned (When to Activate, Research Standards, Modes, Output Format, Quality Gate), and nothing that belongs in a separate file is inlined or buried. Matches the well-organized, easy-navigation anchor for a compact skill.

Specificity

The description lists multiple specific concrete actions with comprehensive coverage — 'Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries' — matching the top anchor; it goes beyond the 'several specific actions; minor gaps' level 4 example.

Completeness

It explicitly answers both parts: what ('Conduct market research, competitive analysis, investor due diligence... with source attribution and decision-oriented summaries') and when ('Use when the user wants market sizing, competitor comparisons, fund research, technology scans...') with concrete trigger phrases — a direct match to the level 5 anchor example.

Trigger Term Quality

'market sizing, competitor comparisons, fund research, technology scans' are natural phrases users would say, giving good keyword coverage. Not 5 because common synonyms and variations are missing — e.g., TAM, due diligence, competitive landscape — while still noticeably above the 'some relevant keywords' level 3.

Distinctiveness Conflict Risk

The niche is mostly distinct with domain-specific triggers (market sizing, fund research, technology scans), but the trailing catch-all 'or research that informs business decisions' is broad and creates minor overlap risk with general research skills — matching 'mostly distinct; minor overlap risk' rather than the minimal-conflict level 5.