Teams need reliable structured data from unstructured text. This skill shows how to use Cohere v2 Python and JSON Schema mode for validated extraction.

Dynamic websites make reliable data extraction difficult. This skill discovers selectors, handles common loading patterns, and produces reusable Playwright scripts with structured output.

PDF conversion often fails when text, layout, and images are extracted separately. This skill creates traceable page artifacts that combine text metadata, rendered images, and page mappings.

Database setup can be difficult when connection, schema, and migration steps are unclear. This skill provides a focused reference for Neon Postgres and Drizzle ORM workflows.

Database schema changes can create data loss, slow queries, or inconsistent Drizzle definitions. This skill guides Claude, Codex, and Claude Code through structured schema design, relations, indexes, and review steps.

Email teams can make costly decisions from underpowered or poorly controlled tests. This skill creates a structured experiment plan and interprets results using user-provided campaign data.

Paid-search exports can hide converting queries and costly irrelevant traffic. This skill turns an export into keyword opportunities, negative keywords, n-gram waste findings, and a reviewable maintenance diff.

Campaign teams often lack a consistent way to connect influencer spend with revenue, media value, and customer outcomes. This skill applies transparent formulas and records assumptions, evidence gaps, comparisons, and practical recommendations.

Ranking changes are hard to interpret without consistent baselines and source labels. This skill compares snapshots, identifies meaningful movements, and recommends focused SEO actions.

SEO teams struggle to compare performance consistently and detect meaningful declines. This skill creates source-labeled reports and threshold-based alert plans from supplied or connected data.

Influencer results are difficult to compare across creators, platforms, and attribution methods. This skill converts campaign data into scorecards, rankings, insights, and recommendations.

Paid campaign changes can look successful when attribution, learning phase, or seasonal effects distort results. This skill compares a fixed candidate window with a control and gives a documented decision.

Backlink exports and AI referral data are difficult to compare consistently. This skill produces source-labeled profiles, trends, landing-page insights, and prioritized actions.

Creator shortlists are difficult to compare consistently across audience, credibility, engagement, and campaign needs. This skill applies typed ACE scoring and separates commercial fit.

Campaign metrics can decline for different reasons, which makes budget decisions difficult. This skill compares frequency, CTR, CVR, and reach trends to recommend rotating creative, widening an audience, or holding.

Live campaigns can overspend, underspend, or produce misleading signals during learning. This skill compares spend with a planned curve and gives a clear pacing verdict with a next action.

Influencer campaign budgets are difficult to balance across creators, platforms, and content formats. This skill builds allocations, projections, scenarios, and reallocation recommendations from your inputs.

First-party customer data often lacks a clear, reusable audience plan. This skill turns approved CRM or GA4 exports into named seeds, exclusions, and funnel-stage targeting maps.

Platform reports can overstate conversions when several channels claim the same order. This skill matches conversion exports to an order-ID truth set and produces a normalized reconciliation view.

Paid-ad tests can produce misleading results when variables, thresholds, and decision ownership are unclear. This skill creates structured test plans and interprets exported results with separate statistical and practical-effect checks.