Conciseness

The body is a terse command catalog — MCP tool names, default parameters, and expected outputs per command — with essentially no explanation of concepts Claude already knows. Minor trim candidates exist: the 24-row Quick Reference table duplicates the per-command sections that follow, and the serp-images caveat is stated three times (though the repetition reads as a deliberate anti-hallucination guard). This matches anchor 4 (efficient, minor instances that could be trimmed) rather than anchor 5.

Actionability

Fully executable guidance throughout: exact MCP tool names per command, default parameters (location_code=2840, language_code=en, depth=100), copy-paste commands (`./extensions/dataforseo/install.sh`, the cost check/log invocations with explicit status handling), and concrete expected outputs. Matches the copy-paste-ready anchor (5); no pseudocode or vague direction is present.

Workflow Clarity

The cost guardrail forms an explicit validation loop for expensive/batch operations: "Before every DataForSEO MCP call, run cost estimation" with three outcome branches (approved/needs_approval/blocked) and "After each API call completes, log the cost". Add to that a numbered 4-step ai-mentions workflow, a pre-use availability check, and an Error Handling section with recovery guidance — clear sequences with explicit validation steps and feedback loops, matching anchor 5.

Progressive Disclosure

Two clearly signaled, one-level-deep references that were verified to exist and match their claimed content (references/cost-tiers.md for the pricing table, references/tool-catalog.md for utility tools), plus a quick-reference table for navigation. Not 5: the ~400-line per-command catalog is fully inlined in SKILL.md when much of it could be split into references (as the utility tool catalog already is), leaving only the quick table and key workflows inline — good structure with minor organization gaps, matching anchor 4.

Specificity

The description lists multiple specific concrete actions — "SERP analysis, keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis, competitor and content analysis, business listings, AI visibility (LLM mention tracking), and domain analytics" — with comprehensive coverage and parenthetical sub-capabilities. No meaningful coverage gaps, so it matches the top anchor rather than the minor-gaps anchor (4).

Completeness

It explicitly answers both "what" (the full capability list) and "when" ("Use when user says 'dataforseo', 'live SERP', 'keyword volume'...") with concrete trigger phrases, matching the top anchor exactly. Not 4: the "when" clause is explicit and enumerates specific trigger phrases rather than being merely present.

Trigger Term Quality

Triggers include natural phrases a user would actually say: "dataforseo", "live SERP", "keyword volume", "backlink data", "AI visibility check", "real search data". However, common variations and synonyms such as "search volume", "SERP analysis", "competitor research", and "trends" are missing, matching the good-coverage-with-a-few-gaps anchor (4) rather than comprehensive coverage (5).

Distinctiveness Conflict Risk

"dataforseo" and "live SERP" are highly distinctive triggers, but "keyword volume" and "real search data" could plausibly overlap with sibling claude-seo skills or other SEO-data skills in the same plugin family — mostly distinct with minor overlap risk against closely related skills, matching anchor 4 rather than the minimal-conflict anchor (5).