Conciseness

The body is dense prescriptive instruction with zero concept explanations — no "what is planning" padding, no restating what Claude already knows; every sentence issues a directive ("Execute one bounded unit per owner at a time, check its result, and record the observed evidence before dependent work"). Matches the 'lean and efficient; assumes Claude's competence; every token earns its place' anchor; even level 4 would require over-explanation to trim, and none is evident.

Actionability

Concrete scaffolds are provided: the four named contract fields ("Outcome", "Scope and constraints", "Verification", "Completion condition"), a three-row depth selection table with explicit criteria, per-step "Ready when" gates, and a five-item output checklist — comparable to 'mostly executable guidance with minor gaps' for an instruction-only skill. Not 5 because no filled example or template artifact appears in the body itself (demonstrations are delegated to worked-examples.md), and some directives stay directional ("Choose evidence that observes the claimed outcome") without showing what that choice looks like.

Workflow Clarity

Five clearly sequenced stages, each closed by an explicit "Ready when:" validation checkpoint, plus a feedback loop — "When a check fails, use its evidence to diagnose and correct the unit; when attempts repeat the same failure, revisit the premise" — and pause conditions ("Pause the affected work when progress requires a new decision, capability, or authorization"). This matches the level-5 anchor (clear sequence, explicit validation steps, error-recovery loops, checklists); the skill involves no destructive or batch operation, so no cap applies.

Progressive Disclosure

Good structure against the actual bundle: all four referenced files (references/task-contracts.md, decomposition.md, verification.md, worked-examples.md) exist and are substantive, references are one level deep, appear inline at the decision point with a when-to-read condition, and are re-listed with purpose annotations under References. Not 5 because four of the eight referenced paths — ../behavioural-specs/SKILL.md, ../task-breakdown/SKILL.md, ../writing-plans/SKILL.md, ../using-beads/SKILL.md — do not resolve in this bundle, leaving navigation broken for half the reference list.

Specificity

Quotes several distinct capabilities — "Coordinate substantial work with multiple outcomes, dependencies, handoffs, or durable checkpoints", "decomposing work, resuming a tracked effort, or revising a plan", "Reuse the active environment's work record and authorization" — matching the 'lists several specific actions; minor gaps' anchor. Not 5 because terms like "substantial work" and "durable checkpoints" stay abstract without covering the planning domain comprehensively; not 3 because well over 1–2 concrete actions are named.

Completeness

Explicitly answers both questions: what — "Coordinate substantial work with multiple outcomes, dependencies, handoffs, or durable checkpoints... Reuse the active environment's work record and authorization"; when — "Use when decomposing work, resuming a tracked effort, or revising a plan after evidence changes its premises". This matches the level-5 anchor (both clearly present with concrete trigger phrases) rather than level 4, since the when-clause names three specific trigger scenarios rather than a vague condition.

Trigger Term Quality

Relevant keywords present — "decomposing work", "resuming a tracked effort", "revising a plan", "dependencies, handoffs" — but common user phrasings are missing ("break down", "plan this project", "pick up where we left off", "task tracking"), and phrases like "durable checkpoints" and "work record" are jargon users would not naturally say. Fits the 'some relevant keywords but missing common variations or synonyms' anchor better than the level-4 anchor's good natural coverage.

Distinctiveness Conflict Risk

The resumption and "evidence changes its premises" triggers are distinctive, but "Coordinate substantial work with multiple outcomes, dependencies, handoffs" overlaps heavily with generic project-planning and task-breakdown skills — the body itself lists four sibling planning skills whose domains border this one, and the description does not delineate boundaries from them. Fits 'somewhat specific but could still overlap with similar skills'; not 4 because the overlap is with multiple closely related skills rather than a minor one.