Conciseness

Sections are individually tight and imperative, but rules are stated three times: Core Principles, per-phase Rules ('Never use the word hypothesis' appears in both Phase 1 context and Phase 3 rules; tone rules appear in Core Principles, Phase 2 Tone, Phase 3 Rules, and the summary table), and a Cross-Cutting Rules Summary table that restates ~9 rules verbatim. Mostly efficient but with clear duplication that could be tightened — matching anchor 3, not 4 (the repetition exceeds 'minor instances') and not 2 (no educational padding of concepts Claude already knows).

Actionability

Copy-paste-ready guidance throughout: exact output templates (assumption tables, map-feedback headers, experiment-brief structure), exact quoted transition prompts, an exact fallback response for the no-idea case, fixed counts (3 assumptions per category), and defined scales (short/medium/long, light/medium/strong). This fully matches the top anchor — specific, executable instructions covering the common cases.

Workflow Clarity

Three phases are explicitly sequenced ('Run phases in sequence. Do not skip ahead') with per-phase Trigger/Behavior/Output Format/Rules/Transition structure, post-phase checkpoints ('After each phase, ask if the user wants to continue'), defined phase-entry triggers, and a rules-summary checklist. This matches the top anchor's clear sequence, explicit checkpoints, and checklist; the skill involves no destructive or batch operations, so no validation cap applies.

Progressive Disclosure

No bundle files exist; the skill is a well-organized single file with clear section headers, a flow overview, and navigable structure appropriate to one coherent conversation flow. Matches anchor 4 (good structure, minor organization gaps) — not 5 because at ~250 lines all detail is inline with no well-signaled reference split (e.g., experiment-type guidance could live in a reference file), and not 3 because nothing is buried or disorganized.

Specificity

Names the domain ('test a business idea, strategy, or initiative against real-world risk') and the mechanism ('Runs a guided Extract → Map → Test system based on David J. Bland's Precoil methodology'), but the phases are labels only — it never says what each phase does (extract assumptions, critique maps, design experiments). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 4, which requires several listed specific actions.

Completeness

Explicitly answers both 'what' (runs a guided Extract → Map → Test system to pressure-test business ideas against real-world risk) and 'when' ('Use this skill when the user wants to...' followed by concrete trigger phrases). This is a direct match for the top anchor; it is not 4 because the 'when' clause is already fully explicit and specific.

Trigger Term Quality

Twelve quoted, natural trigger phrases ('test my idea', 'what are the riskiest assumptions', 'pressure test this', 'validate this plan', 'identify hidden risk in this idea', etc.) plus a catch-all clause give comprehensive coverage with synonyms and variations a user would actually say. No common variations are missing, so it fits the top anchor rather than 4.

Distinctiveness Conflict Risk

Clear niche (Precoil/EMT business-assumption testing) with domain-specific triggers like 'run EMT on this' and 'what are the riskiest assumptions' that no adjacent skill would claim. Minimal conflict risk, matching the 'clear niche with distinct triggers' anchor rather than 4's 'minor overlap risk'.