Conciseness

Every line is operational and non-obvious: tool names with parameters, platform-specific measured data (the reply-composition table), field-level metric definitions, and hard thresholds ("Bounce rate above ~2%", "over 5%"). There is no explanation of concepts Claude already knows and no padding — every token earns its place.

Actionability

Guidance is fully concrete for an instruction-only skill: named tools (`company_intel_search_people`, `enrich_contacts`, `action_card`) with parameter values (`domain: "outbound"`, `action: "approve" | "pause" | "resume"`), exact field names to use and avoid (`reply_rate_pct`, `total_replied_including_automated`), and specific behavioral rules (never top up a 0.3% campaign). Per the rubric's code_vs_instruction note, the absence of code is not penalized because the guidance is directly executable.

Workflow Clarity

The multi-step flow is clearly sequenced — discover prospects, check pipeline state, read metrics honestly, pass two mandatory pre-send gates, then manage launch/pause/replies — with explicit validation checkpoints (qualification fact, `enrich_contacts` verification, suppression-list check, merge-token rendering) and feedback loops (immediate no-ask pause on bounce >5%, literal merge tokens, or suppression violations, then report). This matches the level-5 anchor including its destructive-operation validation requirement.

Progressive Disclosure

The skill is a single-purpose, cohesive instruction set with well-organized numbered sections and no bundle files; nothing in the body (the small stats table, the tool lists) is large enough to warrant extraction to a separate reference file. Per the rubric's simple-skill guidance, well-organized sections with no need for external references earn the top score.

Specificity

The description enumerates multiple concrete actions — "search contacts, enrich identifiers, review the pipeline, inspect campaigns, check sending health, and pause or resume" — covering the skill's full capability surface with no vague filler. It clearly exceeds the level-4 anchor's "minor gaps in coverage" since every body section maps to a named capability.

Completeness

It explicitly answers both questions: the first sentence states what the skill does (prospect discovery, enrichment, cold-email campaign management through Synter Outbound) and the "Use when a user asks..." clause gives concrete when-to-use triggers. This is a direct match for the level-5 exemplar pattern.

Trigger Term Quality

Trigger phrases are the exact words a user would say: "find prospects, emails, phone numbers, LinkedIn profiles," "cold email, sequences, their lead pipeline, reply rates," and "launch, pause, or top up an email campaign." This comprehensively covers natural synonyms and verb variants rather than technical jargon, matching the level-5 anchor.

Distinctiveness Conflict Risk

The Synter Outbound branding and cold-email/pipeline domain give it a clear niche with minimal conflict risk, but the generic triggers "emails" and "phone numbers" could overlap with general contact-lookup or email-drafting skills (the body itself references a sibling outbound-research skill). It fits the level-4 anchor ("mostly distinct; minor overlap risk") better than level 5.