Conciseness

The body is lean and assumes Claude's competence — the Problem section documents genuinely non-obvious failure modes (the {"data": ...} envelope, MAX_YIELD_RETRIES=3, the 'result' label pitfall) rather than known concepts. Minor trimmable instances remain: the version-gated line 'Since omp 18.10.3...' is time-sensitive info outside a deprecated/old-patterns section, and the enumerated example field lists are slightly padded, fitting the score-4 anchor rather than a flawless 5.

Actionability

The Practice section supplies a copy-paste-ready contract template ('Output contract: finish by calling yield with {"data": {...}} on success...'), specifies placement (append to the task/prompt text, not just the mechanically attached schema), frequency ('applied every time an outputSchema is supplied'), and covers the nested-array case. For an instruction-only skill this is fully executable guidance covering the common cases, matching the 5 anchor.

Workflow Clarity

This is a simple, single-purpose prompting habit whose single action is unambiguous, and the conditional case is explicitly handled ('apply this to task() only for agents whose frontmatter sets structured: true'). Per the simple-skill exception the single action scores 5; it involves no destructive or batch operations, so no validation cap applies.

Progressive Disclosure

The body is under 50 lines, well-organized into Problem / Practice / Non-fix sections, and needs no external references — no references/, scripts/, or assets/ bundle exists and none is required. The under-50-line simple-skill exception applies, so well-organized sections alone merit a 5.

Specificity

Names the precise targets ('agent()/workpool() subagent with an outputSchema', 'a task agent whose frontmatter sets structured: true') and a concrete action ('stating the exact result envelope and required fields in the prompt'). It goes beyond the score-3 anchor's generic 1-2 actions, but describes essentially one mechanism rather than listing multiple specific actions, so it falls short of a 5.

Completeness

The explicit 'Use when spawning an agent()/workpool() subagent with an outputSchema, or a task agent whose frontmatter sets structured: true' answers 'when' with concrete trigger phrases, and 'stating the exact result envelope and required fields in the prompt' clearly answers 'what'. Both are explicit and specific, matching the 5 anchor rather than the 4 anchor where the 'when' could be more explicit.

Trigger Term Quality

Terms like 'spawning', 'agent()', 'workpool()', 'outputSchema', 'structured: true', and 'yield retry failures' are exactly what a user writing workflow scripts would naturally say. Good keyword coverage matching the score-4 anchor, though natural synonyms such as 'structured output' or 'result schema' are missing, keeping it from comprehensive 5-level coverage.

Distinctiveness Conflict Risk

Triggers are tightly scoped to a clear niche (outputSchema'd subagent spawns and yield behavior), terms virtually no other skill would fire on. Minimal conflict risk, matching the 5 anchor for a distinct niche with distinct triggers.