Conciseness

The body is lean: a three-example Quick Reference, a compact parameters table, five one-line workflow steps, and short anti-pattern/when-not-to-use bullets — every section earns its place and nothing explains concepts Claude already knows. It sits at anchor 5 rather than 4 because there is no padded or over-explained content to trim.

Actionability

Quick Reference gives three copy-paste-ready invocations (plain prompt, prompt+schema, prompt+urls) covering the common cases, and the Parameters table supplies concrete defaults, ranges ('max 100', 'max 600000'), and option values ('numbered' / 'json' / 'anthropic_tags'). This matches anchor 5: fully executable examples covering the common cases with no gaps.

Workflow Clarity

The 5-step sequence (Plans → Executes → Extracts → Synthesizes → Reports) is clearly ordered, and there is an explicit error-recovery loop — "Use steps to debug weak results — if extraction is poor, check which pages were fetched" — plus a synthesis fallback ladder. It stops short of anchor 5 because result validation checkpoints are implicit rather than explicit (e.g., no instruction to verify extracted fields against the schema before returning).

Progressive Disclosure

The skill has no bundle files (no references/, scripts/, or assets/), and the ~78-line body is appropriately self-contained with well-organized sections (Quick Reference, Parameters, How It Works, Output Transparency, Anti-Patterns, When NOT to use, See Also) and clearly signaled one-level cross-links to sibling skills. Nothing inlined belongs in a separate file, so it fits anchor 5's 'content appropriately split; easy navigation'.

Specificity

The description lists multiple concrete actions covering the full pipeline — "plans search queries and URLs from a natural-language prompt", "executes in parallel within a time budget", "extracts structured fields via JSON Schema", and "synthesizes results with full step transparency" — which comprehensively covers what the skill does. It exceeds anchor 4 ('minor gaps in coverage') because each pipeline stage is named with its mechanism, not just hinted at.

Completeness

Both 'what' and 'when' are explicitly answered: the action pipeline states what it does, and "Use when the user needs data collected from the web with a specific shape, says 'gather data'..." gives concrete trigger phrases. This matches the anchor-5 example structure exactly (capabilities sentence + explicit 'Use when' with concrete triggers).

Trigger Term Quality

Natural quoted trigger phrases are strong — "gather data", "find pricing for", "collect information about", "extract from multiple sites", "provides a JSON schema for web data" — giving good keyword coverage. It falls short of anchor 5 because common synonyms like "scrape/scraping", "web research", or "look up" are missing, which keeps it at 'a few natural terms missing'.

Distinctiveness Conflict Risk

The niche is mostly distinct — autonomous multi-source gathering with schema-based extraction is specific, and triggers like "extract from multiple sites" steer correctly. It is not anchor 5 because broad triggers ("collect information about") overlap with the sibling wigolo-research skill and the description includes no negative disambiguation (e.g., 'not for reports'), leaving minor overlap risk with closely related skills.