Conciseness

The body is dense and prescriptive throughout — ranked lists, tables, checklists, and specific numbers ("16-25% higher LTV", "say '$10 off,' not '40% off'") with no concept-teaching padding, matching the 'efficient; minor instances' anchor. Not 3 because there is no unnecessary library/concept explanation; not 5 because the "Task-Specific Questions" section duplicates the "Before Starting" context questions and a few bullets ("Ask at better moments", "Test different incentive types") are generic filler.

Actionability

Mostly concrete, executable guidance: copy-paste-ready email templates with placeholders, share mechanisms ranked by effectiveness, specific value-presentation rules, a problems/fixes table, and a tool table mapping named tools to use cases. Not 5 because some optimization guidance stays high-level ("Ask at better moments", "Improve landing experience") and incentive sizing is deferred entirely to a reference file.

Workflow Clarity

A clear lifecycle sequence is present — context gathering, virality diagnostic, referral-vs-affiliate choice, a 3-step design process, then a phased Before Launch / Launch / Post-Launch checklist with checkpoints like "Test complete referral flow" and "Review conversion funnel". Not 5 because there are no explicit error-recovery or re-validation loops (the post-launch review is implicit rather than a structured feedback loop); not 3 because the phased checklists provide real, ordered checkpoints.

Progressive Disclosure

The overview is well-structured with six clearly signaled references, each annotated with its contents ("For examples and incentive sizing: See [references/program-examples.md]"), all verified to exist and one level deep. Not 5 because review-program-operations.md is only reachable via a second hop through review-programs.md (orphaned from the SKILL.md overview), and the Tool Integrations section routes implementation guides to external GitHub URLs rather than the bundle.

Specificity

Lists several concrete capability areas — "refer-a-friend incentives, commissions and payouts, partner programs, 'made with' badges, review campaigns" plus "what to reward, how much to pay, or which loop to start with" — matching the 'several specific actions; minor gaps' anchor. Not 5 because capabilities are stated as topics rather than explicit actions, and coverage is not comprehensive.

Completeness

Explicitly answers both: what ("refer-a-friend incentives, commissions and payouts, partner programs, 'made with' badges, review campaigns") and when ("When the user wants referral and affiliate programs or word of mouth, or asks what to reward, how much to pay") with concrete trigger phrases — structurally identical to the anchor-5 example. Not 4 because the when-clause is fully explicit rather than merely present-but-imprecise.

Trigger Term Quality

Good natural keyword coverage with synonyms — "referral and affiliate programs", "word of mouth", "refer-a-friend", "commissions and payouts", "partner programs", "review campaigns" — phrases users would actually say. Not 5 because common variants like "ambassador program", "referral code/link", or "customer referral" are missing.

Distinctiveness Conflict Risk

Clear niche with distinct domain-specific triggers, and it actively de-conflicts the closest siblings: "For launch virality, see launch. For creator deals, see influencer-marketing." This exceeds the anchor-5 example (which achieves minimal conflict risk without any disambiguation); only trivial overlap remains around "review campaigns" and "word of mouth".