Conciseness

The body is extremely dense and assumes Claude's competence (no textbook explanation of what strategy is; every sentence carries a test, framework step or named source), but the "Receipts" section's six quotes duplicate `references/quotes.md` ("verified quotes with timestamps") and the opening line repeats the frontmatter's "909 insights from 236 guests". Not 5 because these duplicative sections are tokens that could be trimmed; not 3 because there is no padded or already-known concept explanation anywhere.

Actionability

Guidance is fully executable for an instruction-only skill: a copy-paste-ready markdown deliverable template, a decision table mapping situations to plays, exact diagnostic questions ("max 4", enumerated), concrete tests (coin-flip test, castle-or-shack, benefit/barrier/materiality) and a 1/3/5-anchored grading rubric. Not 4 because specific examples cover the common cases end to end, from intake questions to finished artifact.

Workflow Clarity

Clear sequence (Step 1 diagnose → Step 2 pick play via table → Step 3 run → deliverable → grade) with explicit validation checkpoints: "Done when three people from different functions can say what they will stop doing on Monday", per-claim moat verdicts, iterative toggling in Play 2, and re-test triggers in the deliverable. Not 4 because checkpoints and feedback loops are explicit throughout, not merely present for most steps; no destructive/batch operations, so no cap applies.

Progressive Disclosure

References are real, one level deep (verified: `references/frameworks.md` and `references/quotes.md` exist and contain no nested links) and clearly signaled in "Go deeper" with one-line descriptions. Not 5 because the body inlines full runbook detail for all six plays while `frameworks.md` promises "every framework in this skill, how to run it", so the split between overview and reference is not clean — the Receipts quotes and some play detail could live in the reference files.

Specificity

"Builds a product strategy and stress-tests your moat, then writes a one-page strategy doc (diagnosis, where to play, how to win, guiding policy, coherent actions, moat verdicts)" lists multiple concrete actions with the deliverable's components enumerated, in third-person voice. Not 4 because coverage of what the skill does is comprehensive rather than having minor gaps.

Completeness

Both 'what' (builds strategy, stress-tests moat, writes one-page doc with named sections) and 'when' (explicit 'Use for...' clause with concrete trigger phrases) are clearly present. Not 4 because the 'when' is fully explicit with quoted trigger phrases rather than only somewhat specific.

Trigger Term Quality

"Use for 'we need a product strategy', 'is our moat real', 'do we have a competitive advantage', 'where should we play', 'defensibility', 'should we expand into X', 'our roadmap has no strategy', or 'write a product vision'" gives eight natural phrases users would actually say, including synonyms (moat, competitive advantage, defensibility). Not 4 because common variations (vision, roadmap, expansion) are covered, not just a few.

Distinctiveness Conflict Risk

"stress-tests your moat", "defensibility", "where should we play" stake a clear product-strategy/moat niche with distinctive trigger vocabulary unlikely to fire for unrelated skills. Not 4 because the trigger terms (moat, defensibility, guiding policy) are niche-specific, with only negligible overlap risk against adjacent planning skills.