Conciseness

The ~30-line body is directive-only with no padding and no explanation of concepts Claude already knows ("Use the canonical identity without turning every surface into a marketing page"; rules like "Preserve logo proportions and colors. Do not rotate, distort, outline, or add effects.") — every token earns its place, matching anchor 5.

Actionability

Concrete, directive guidance throughout ("Use sentence case for headings", "Use sea-glass green as a restrained secondary accent"), but a few steps defer the method ("Verify contrast, responsive cropping, and text legibility" gives no technique, and "Use semantic design tokens" names no tokens), fitting anchor 4; it is not 5 because specifics like hex values and exact stacks are deferred entirely to identity.md, and not 3 because the rules are executable directives rather than high-level hints.

Workflow Clarity

A clearly sequenced 7-step workflow with verification checkpoints in steps 6 and 7, including an honest fallback ("otherwise report that check as unavailable rather than inventing a measurement"); it stops short of anchor 5 because there are no error-recovery feedback loops, and exceeds anchor 3 because validation steps are explicit rather than implicit. No destructive/batch cap applies.

Progressive Disclosure

Two references (references/identity.md, references/asset-rights.md), both verified to exist, one level deep with no nested references, each clearly signaled with its purpose ("Read [identity.md](references/identity.md) for palette, typography, logo, and voice"; "Read [asset-rights.md](references/asset-rights.md) before copying or redistributing assets") in a well-organized short body — matching anchor 5.

Specificity

"Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials" names one concrete action but comprehensively enumerates the target surfaces, matching anchor 4; it is not 5 because there is a single action verb rather than multiple distinct concrete actions, and not 3 because the enumerated coverage goes well beyond 1-2 actions.

Completeness

It explicitly answers both what ("Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials") and when ("Use when the task changes brand identity rather than ordinary product UI or public-page composition") with a concrete trigger phrase plus a negative boundary, matching the top anchor and mirroring the good brand-skill example.

Trigger Term Quality

Natural terms users would say are present ("brand identity", "logos", "typography", "presentations", "social graphics"), giving good keyword coverage; a few natural synonyms are missing (e.g., "branding", "style guide", "rebrand"), so it falls just short of the comprehensive synonym coverage of anchor 5 and clearly above the 3 anchor's missing-variations profile.

Distinctiveness Conflict Risk

The explicit boundary clause "rather than ordinary product UI or public-page composition" separates it from adjacent design skills, and the single named brand (OpenClaw) gives it a clear niche with minimal conflict risk, matching anchor 5; anchor 4 would require some residual overlap risk, which the boundary language largely eliminates.