Dense, domain-specific methodology with no padding of concepts Claude already knows; every line carries methodology, guardrails, or a concrete instruction. Length reflects a genuinely complex multi-step skill, not verbosity.

Provides executable commands with concrete file arguments (e.g. 'python3 scripts/validate_evidence_ledger.py data/source_ledger.csv') and explicit TAM/SAM/SOM formulas in copy-ready text blocks.

A clearly sequenced 10-step workflow with explicit validation checkpoints (ledger validation, competitor-matrix validation, unit-consistency check) and a final 'Release gate' checklist with error-recovery guidance for risky batch operations.

SKILL.md is an overview with well-signaled one-level-deep references; every referenced path resolves to a real bundled file, and a dedicated 'Bundled resources' section maps each reference, template, and script to its purpose.

Lists multiple concrete capabilities — 'Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios' plus 'market definition, industry and customer evidence, competitive landscapes, TAM/SAM/SOM reconciliation, forecast sensitivity, and auditable report scaffolds.'

Explicitly answers both what ('Build evidence-traceable market research reports...') and when via an explicit 'Use for...' trigger clause enumerating the triggering situations.

Covers natural terms a target user would say — 'market research reports', 'market sizing', 'forecast', 'competitive landscapes', 'TAM/SAM/SOM' — with good variation rather than jargon.

The evidence-traceable, auditable-report niche with TAM/SAM/SOM and forecast-sensitivity triggers is distinct and unlikely to fire for unrelated skills.