Conciseness

Dense and skill-specific throughout — the workflow, scripts table, onboarding, and forcing-question sections all carry non-obvious content (method-mapped flags, config scopes, canon citations). However, the core insight-recurrence rule is restated ~4 times ("a single quote is an anecdote", "flags any candidate below the source threshold as an ANECDOTE", "One participant is a signal to probe", "require recurrence across ≥3 sources"), and the intro largely restates the frontmatter description — minor trimming opportunities, matching level 4 rather than the every-token-earns-its-place level 5; well above level 3 since nothing explains concepts Claude already knows.

Actionability

Concrete, complete CLI invocations with all flags: "study_designer.py --goal {discovery|evaluative|validation} --stage {concept|prototype|beta|live} --profile {...}", "saturation_planner.py --method {...} --segments N", "insight_synthesizer.py --input observations.json --min-sources 3", plus runnable quick examples and onboarding commands. Not 5 because the referenced scripts (scripts/study_designer.py, saturation_planner.py, insight_synthesizer.py, onboard.py, ar_evaluator.py) and assets/research_plan_template.md are not present in the bundle, so the copy-paste-ready commands cannot actually execute as shipped; not 3 because the guidance itself is specific, syntactically complete, and covers the common cases.

Workflow Clarity

A clearly sequenced 5-step workflow (frame → pick method → size → synthesize → file in repository) with a concrete command per step and useful checkpoints ("Honor the redirect if it routes to experiment-designer", "Record the confidence label and limits", "Treat ANECDOTE-flagged clusters as signals, not findings"). Not 5 because there is no explicit validate-output/recovery step (e.g., verifying repository tags before filing); not 3 because checkpoints are mostly present and the sequence has no gaps.

Progressive Disclosure

The body is well-sectioned with a dedicated References section giving one-line descriptions of three reference files, and references are one level deep and clearly signaled. However, none of the referenced bundle files exist — there is no scripts/, references/, or assets/ directory in the bundle — so every cited path (3 references, 5 scripts, 1 asset) is dead and navigation to the deferred detail is impossible. This sits between level 3 (structure present but organization compromised) and level 4; the dead references keep it at 3 rather than 4, while the clean internal signaling keeps it above 2.

Specificity

Multiple specific concrete actions with comprehensive coverage: "selecting the right method for the goal (generative interviews vs usability test vs concept test vs validation)", "computing method-based saturation/sample size with an explicit confidence level", and "synthesizing coded observations into insights while flagging single-source anecdotes". Each capability is enumerated with its variations, matching the level-5 anchor; not 4 because coverage spans the skill's full scope with named method types rather than minor gaps.

Completeness

Explicitly answers both what and when: opens with "Use when planning and synthesizing product/user research..." giving concrete trigger situations (method selection, saturation/sample size, synthesis of coded observations), and the what is the three enumerated capabilities. Not 4 because the when-clause is explicit, specific, and loaded with trigger phrases rather than merely adequate.

Trigger Term Quality

Good keyword coverage: "product/user research", "usability test", "interviews", "sample size", "saturation", "synthesizing", "insights", "research repository". A few natural terms users would say are missing (e.g., "user testing", "usability study", "research findings", "discovery interviews"), so it fits the level-4 anchor rather than the comprehensive synonym coverage of level 5; clearly above level 3 since most relevant trigger phrases are present.

Distinctiveness Conflict Risk

Explicitly disambiguates: "Distinct from product-team/ux-researcher-designer (persona/journey artifacts), product-discovery (discovery-sprint planning), and experiment-designer (live A/B) — this is the research-ops method + insight-repository layer." Named neighbors with scope boundaries give a clear niche with minimal conflict risk, matching the level-5 anchor.