Conciseness

The body is dense and rule-driven with tables and templates rather than padded explanation, and it assumes Claude's competence throughout. Minor redundancy keeps it below anchor 5: 'Never silently chain' is stated twice, the 'When to invoke' symptom table overlaps the signal table, and the 'Distinct from' section restates the description's boundary list. It is well above anchor 3 since there is no explanation of concepts Claude already knows.

Actionability

The guidance is fully concrete and copy-paste ready: a literal forcing-question template ('Q1/1: [precise question naming the two candidate lanes] / Recommended: [Lane X, because <signal-table rationale>]'), executable commands ('python3 skills/<sub-skill>/scripts/onboard.py --show'), a deterministic keyword-to-sub-skill signal table, an exact digest spec ('≤ 200 words: analyzed, top 3 findings... artifact path, and one grill challenge'), and worked grill examples. This matches anchor 5's fully-executable, common-cases-covered standard for an instruction-only skill.

Workflow Clarity

The five-step workflow is clearly sequenced (explore → forcing question → decision-tree walk → invoke → digest) with explicit confirm gates ('(Confirm, or override?)', 'Confirm before chaining', 'Never run a sub-skill until the lane-defining decision is locked'). It falls short of anchor 5 because there is no error-recovery path for cases like a lane remaining ambiguous after the forcing question or a sub-skill invocation failing, but the checkpoints are explicit rather than implicit, keeping it above anchor 3.

Progressive Disclosure

Sections are well organized and, as an orchestrator, routing content appropriately lives inline while detail is delegated to sub-skills ('references/ of each sub-skill', per-sub-skill onboarding and evaluator scripts). It does not reach anchor 5 because no bundle files exist in this skill and the 'References' section lists canon names (ICH E9, CONSORT, Bessemer, Rohrer) without file links, plus one external path; it stays above anchor 3 because structure and content placement are good and references are mentioned where relevant.

Specificity

The description lists several concrete capabilities ('Forks context to route to one of four Research-Operations sub-skills... and returns a digest') with named workstreams and all four sub-skills enumerated. It falls short of anchor 5 because the capability verbs ('planning, funding, scoping, or synthesizing') are more abstract than the fully concrete action lists in the top anchor, but it clearly exceeds anchor 3's '1-2 concrete actions' with comprehensive routing detail.

Completeness

Both questions are answered explicitly: 'Use when planning, funding, scoping, or synthesizing enterprise research...' gives the when with concrete trigger phrases, and 'Forks context to route to one of four... sub-skills and returns a digest' gives the what. This matches the anchor-5 structure of clearly answering both what and when with concrete triggers.

Trigger Term Quality

The explicit 'Triggers on' clause provides twelve natural phrases users would actually say ('design this clinical study', 'what sample size', 'R&D budget', 'burn rate', 'capitalize or expense', 'TAM SAM SOM', 'survey design', 'plan user interviews', 'usability test'), covering synonyms across all four lanes. This matches the anchor-5 example's comprehensive natural-term coverage.

Distinctiveness Conflict Risk

The 'Distinct from' clause explicitly disambiguates five neighboring skills with their scopes (ra-qm-team, finance, research/grants, product-team, marketing-skill), and the enterprise-vs-academic research framing carves out a clear niche. Minimal conflict risk, matching the anchor-5 'clear niche with distinct triggers' example.