Conciseness

The body is largely lean — tight bullet lists, well-chosen stop conditions ("Stop when the flow answers these shaping questions"), and it assumes Claude's competence throughout. Minor over-explanation that could be trimmed or pushed to references: the renderer compatibility note ("Some Markdown/SVG renderers (for example Zed) do not fully support CSS variables..."), the naming-convention details, and a slight restatement of affordance concepts between the Purpose section and step 1. This matches anchor 4 ('minor instances of over-explanation that could be trimmed') rather than anchor 5's every-token-earns-its-place.

Actionability

Concrete, executable instruction-level guidance throughout: numbered field lists for each affordance type, a required dual-output format for the diagram (Mermaid source + static SVG + ASCII fallback), explicit template paths per step, and a quality bar with checkable rules. It falls short of anchor 5 only in small gaps — e.g., no sample invocation of scripts/render_mermaid_from_edges.py (no command line or input JSON shape shown) and no inline mini-example of a table row, both of which are deferred to bundle files. Anchor 3 is ruled out because the guidance is concrete and specific, not pseudocode or high-level hints.

Workflow Clarity

Nine clearly sequenced steps with explicit stop conditions (step 2's "Stop when the flow answers these shaping questions"), an embedded validation checkpoint (step 7's fit check surfacing unsolved requirements and the decision type needed), an error-recovery loop ("If the render appears as black blocks, post-process the SVG..."), and a closing quality-bar checklist. No destructive or batch operations exist, so no validation cap applies; this matches anchor 5 rather than anchor 4 (which requires missing checkpoints).

Progressive Disclosure

A clear overview body (~210 lines) with well-signaled, one-level-deep references: every cited path (references/templates/breadboard-pack-template.md, wiring-diagram-mermaid-template.md, parts-bom-template.md, fit-check-template.md, extract-vs-duplicate-template.md, references/shapeup-breadboarding-notes.md, references/examples/letter-search-example.md, scripts/render_mermaid_from_edges.py) exists in the bundle, is referenced at the exact step where it is needed, and is cataloged in a final "Bundled resources" section. Content is appropriately split: templates and examples live outside the body; only the decision rules stay inline. This matches anchor 5; anchor 4's 'minor organization gaps' are absent.

Specificity

The description enumerates multiple concrete deliverables — "mapping an existing system via UI + code affordances, producing a wiring diagram, a parts/BOM plan, a fit check, and (when relevant) an extract-vs-duplicate analysis" — giving comprehensive, action-level coverage of the skill's outputs. No neighboring anchor fits better: score 4 requires 'minor gaps in coverage', but every major capability of the skill body is represented.

Completeness

Both what and when are explicitly present: "This skill should be used when shaping a software change and needing to breadboard the solution...". However the when-clause is partially circular — it triggers on the skill's own coinage ("breadboard the solution") rather than concrete external trigger phrases (e.g., 'when the user asks to breadboard, map system affordances, or plan parts'), so it matches anchor 4 ('when could be more explicit or specific') rather than anchor 5.

Trigger Term Quality

Good natural keywords for the target audience — "shaping a software change", "breadboard", "wiring diagram", "parts/BOM plan", "fit check" — but common synonyms and variations (e.g., "wireframe-free sketch", "rough out", "architecture diagram", "plan the parts") are absent. It is above anchor 3 ('some relevant keywords but missing common variations') but short of anchor 5's comprehensive synonym coverage.

Distinctiveness Conflict Risk

The Shape Up vocabulary ("breadboard", "places, affordances, connections", "fit check", "extract-vs-duplicate") carves a clear niche with minimal overlap, but "producing a wiring diagram" carries minor overlap risk with general diagramming/mermaid skills. Mostly distinct with minor overlap risk, matching anchor 4; anchor 5 would require no meaningful conflict surface.