Conciseness

The body is dense and fragment-style ('Stdlib only', bare numeric thresholds, no basic-concept padding), matching 'efficient; minor instances of over-explanation that could be trimmed'. The discipline instruction 'One question at a time. Do not skip ahead. Answers must be written down' is repeated three times (Workflow step 5, the library header, and the closing note), and 'Why it's the first question' re-explains Goldratt's single-binding-constraint idea Claude already knows; per-question 'Canon' citations also duplicate references/queueing_theory_canon.md. Not 5 because of that repetition and the Goldratt/Frei re-explanation; not 3 because there is no broad explanatory padding of known concepts.

Actionability

Concrete, mostly executable guidance: a copy-paste quick example ('cd business-operations/skills/capacity-planner && python3 scripts/capacity_modeler.py --sample'), named scripts with flags ('--profile', '--input <path> (JSON)', '--output {markdown,json}', '--sample', '--help'), and specific thresholds ('Anyone >85% sustained', 'span of control crosses 7 ICs/manager', 'front-load hires (Q1 35%, Q4 15%)'). Scored 4 rather than 5 because no real-parameter invocation is shown inline — running with actual demand/AHT/SLA inputs relies on --help/--sample and the absent assets/capacity_brief_template.md.

Workflow Clarity

A five-step numbered workflow with an explicit early stop-checkpoint ('If you only have averages, stop and pull the distribution'), risk flagging ('Anyone >85% sustained is a throughput-collapse risk', 'Spread >30 percentage points ... means UNBALANCED'), and the forcing-question walk acting as a validation checklist with threshold-based verdicts ('If P(breach at P90) > 10% you are understaffed at the sizing point'). This is sizing math, not a destructive/batch operation, so the validation cap does not apply; sequence, checkpoints, and a written-answer gate before committing the plan match the anchor-5 example.

Progressive Disclosure

In-body organization is well-signaled — dedicated Scripts, References, and Assets sections, one level deep, each annotated with scope ('Erlang-C sizing with shrinkage adjustment', 'The math', '20-minute fill-out template'). However, none of the seven referenced bundle files exist in the provided bundle (scripts/capacity_modeler.py, scripts/utilization_analyzer.py, scripts/hiring_sequencer.py, references/queueing_theory_canon.md, references/ops_workforce_planning_canon.md, references/capacity_anti_patterns.md, assets/capacity_brief_template.md), so the deep content cannot actually be reached, and the ~90-line Forcing-question library is inlined in SKILL.md rather than split into a reference. Better organized than anchor 3's 'references not clearly signaled', but dangling references and inlined reference-grade content keep it below anchor 4's 'appropriately placed' and anchor 5's 'easy navigation'.

Specificity

It lists multiple specific concrete actions with comprehensive coverage: 'sizing ops capacity, building a headcount plan, modeling utilization risk, planning Q3 capacity or annual support capacity, or designing CS coverage' plus 'Erlang-C queueing math, P90 demand sizing, shrinkage-adjusted FTE, manager-trigger thresholds, and a quarterly hiring sequence with ramp + attrition'. Matches the anchor-5 example ('Extract text and tables from PDF files, fill forms, merge documents, convert pages to images') rather than anchor 4, which is reserved for coverage with minor gaps.

Completeness

Both what and when are explicit: what — 'sizing ops capacity, building a headcount plan, modeling utilization risk ... designing CS coverage ... needs Erlang-C queueing math, P90 demand sizing, shrinkage-adjusted FTE'; when — the 'Use when an ops leader ... is sizing ops capacity' clause plus concrete numeric triggers ('Apply when sustained team utilization is above 80% or when the team is growing >50% in 12 months', 'Run before committing the headcount budget'). This exceeds the anchor-5 example's explicitness.

Trigger Term Quality

Comprehensive natural terms with synonyms: 'headcount plan', 'annual support capacity', 'Q3 capacity', 'CS coverage', 'utilization', plus role variations ('Director of CX, Head of Support, VP Ops, Head of BizOps, Head of IT ops, Head of Finance ops') and colloquial framings ('Run before committing the headcount budget'). Terms like 'Erlang-C' and 'shrinkage-adjusted FTE' are exactly what the target ops persona says, matching the anchor-5 'comprehensive coverage of natural terms including synonyms' rather than anchor 4's 'a few natural terms missing'.

Distinctiveness Conflict Risk

A clear niche (ops queued-work capacity sizing) with explicit negative boundaries: 'This is NOT engineering capacity (see vpe-advisor for DORA + cycle time) and NOT strategic 3-year workforce planning (see chro-advisor)'. The named sibling skills and negation pattern give minimal conflict risk, matching anchor 5.