Conciseness

The body is four sentences with zero padding, no explanation of concepts Claude already knows, and no redundancy — 'Read .claude/skills/museum-art/SKILL.md and execute it exactly as written — that file is the authoritative playbook. Then follow .agents/rules/cog.md.' Every token earns its place, matching anchor 5.

Actionability

The written instructions are concrete — exact file paths to read and an explicit substitution rule ('invoke .agents/agents/<name>.md via invoke_subagent instead') — so it is above anchor 2's 'high-level hints'. But the skill's actual guidance (sourcing recipes, API usage, licensing rules) is entirely absent from the body, living only in an external file that is not part of this bundle, which fits anchor 3: 'some concrete guidance but incomplete; missing key details'.

Workflow Clarity

A clear two-step sequence — read and execute the playbook, then follow .agents/rules/cog.md — with an unambiguous conditional substitution rule for agent delegation. No validation checkpoints are present, but none are evidently needed for these non-destructive pointer steps, so this matches anchor 4's 'clear sequence with most checkpoints present; minor validation gaps' rather than 5's explicit validation/feedback loops.

Progressive Disclosure

The references are clearly signaled (explicit paths and roles: 'authoritative playbook', rules file, agent substitution), but the body contains no overview content of its own — it is pure indirection to .claude/skills/museum-art/SKILL.md, and no bundle files (references/, scripts/, assets/) exist to back any of it. That fits anchor 3 ('references present but not clearly signaled / content that should be separate is inline' territory) rather than 4, since there is no in-file content at all to be appropriately placed.

Specificity

The description gives one concrete, highly specified action — 'Source authentic, high-res PUBLIC-DOMAIN artwork from museum open-access APIs' naming eight museums — plus 'Verified keyless recipes + licensing rules inside'. It is more than 'names domain and 1-2 concrete actions' (3) because sourcing scope, quality, licensing, and keyless access are all explicit, but it stops short of anchor 5's 'multiple specific concrete actions' since there is effectively a single core verb.

Completeness

Both what and when are explicit: 'Source authentic, high-res PUBLIC-DOMAIN artwork from museum open-access APIs… instead of AI-generated or generic-stock imagery' states the what, and 'The default move whenever a visual needs an aesthetic, credible image (blog heroes, decks, social cards, essay/spec figures)' is a concrete when-clause with named trigger contexts, matching anchor 5. It uses third person ('Source', 'The default move'), so no voice penalty applies.

Trigger Term Quality

Natural user-facing terms are present: 'artwork', 'aesthetic, credible image', 'blog heroes, decks, social cards, essay/spec figures', plus the museum names. Common synonyms such as 'picture', 'photo', 'illustration', or 'painting' are missing, so it fits anchor 4 ('good keyword coverage; a few natural terms missing') rather than 5's comprehensive synonym coverage.

Distinctiveness Conflict Risk

The museum open-access / public-domain niche is highly distinct with specific named institutions, but 'The default move whenever a visual needs an aesthetic, credible image' claims broad default territory that overlaps with generic image-sourcing or visualization skills — 'mostly distinct; minor overlap risk' (4) rather than 5's 'minimal conflict risk'.