Conciseness

The body is lean and prescriptive throughout — signal rankings with decay windows, a disqualifier table, banned-opener lists, and GOOD/BAD copy pairs — with zero padding and no explanation of concepts Claude already knows. Justifying asides (e.g. the 750-person campaign anecdote) directly motivate a rule, so every token earns its place; this matches the 5 anchor rather than the 4 anchor ('minor instances of over-explanation').

Actionability

Guidance is fully concrete and executable for an instruction-only skill: named tools (`company_intel_search_people`, `enrich_contacts`, `company_intel_get_signals`), exact decay windows (30/45/60/90 days), an explicit banned-phrase list, a line-by-line opening shape, and GOOD/BAD example sentences covering the common cases. Per the rubric's code-vs-instruction note, the absence of code is not penalized when guidance is this actionable; it matches the 5 anchor.

Workflow Clarity

The sequence is clear with explicit ordering cues ('Disqualifiers first — check these before any positive research', numbered discovery steps) and validation checkpoints with defined actions: the 'where did you get my information?' test, 'One hit stops the send', 'Cut the cohort rather than send it', and the creepiness test with its corrective rule ('If yes, reference the topic, not the event'). The disqualifier table functions as a checklist, matching the 5 anchor; the 4 anchor's 'minor validation gaps' does not apply since no checkpoint is missing.

Progressive Disclosure

Sections are well-organized with clear headers and the single-file content is cohesive operational guidance, so structure is good — but at ~125 lines with no external references and no content split, it exceeds the under-50-line threshold under which a reference-free skill can score 5 on organization alone. This fits the 4 anchor ('good structure; most content is appropriately placed; minor organization gaps') better than the 5 anchor, which expects appropriately split content with well-signaled references.

Specificity

The description lists multiple specific concrete actions — "find people and verified contact info (emails, phone numbers, LinkedIn URLs), verify a checkable fact from first-party signals, rank competing signals, and land it in the email without sounding AI-generated" — with comprehensive coverage of the skill's capabilities. This matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage') and exceeds the 4 anchor, which expects minor gaps in coverage.

Completeness

Both 'what' and 'when' are explicit: the what is the enumerated action list, and the when is a dedicated "Use when..." clause with four concrete trigger conditions. This clearly matches the 5 anchor ('clearly and explicitly answers both what AND when with concrete trigger phrases') and exceeds the 4 anchor where 'when' could be more specific.

Trigger Term Quality

Natural trigger phrases are comprehensively covered with synonyms: "finding prospects or leads", "building or topping up an outbound list or lead list", "writing a first-touch cold email to a researched prospect", "deciding whether someone should be contacted at all". These are exactly the phrasings a user would say when needing this skill; no common variation is missing, matching the 5 anchor rather than the 4 anchor ('a few natural terms missing').

Distinctiveness Conflict Risk

The description carves out a clear niche — pre-outreach prospect research and qualification in Synter — with distinct triggers (lead list building, first-touch email to a researched prospect, contact-worthiness decisions). Overlap risk with a generic copywriting skill is minimal since the cold-email trigger is qualified as 'to a researched prospect', matching the 5 anchor's 'clear niche with distinct triggers; minimal conflict risk'.