跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

seo-vs-ads

Find money leaking between search ads and SEO — queries you pay for while already ranking organically, and paid queries with no organic coverage. Use when asked "am I paying for clicks I'd get free", "brand bidding waste", "SEO vs ads overlap", or "cut wasted ad spend with SEO".

科研4.6kskills/seo-vs-ads/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/ryze-ai-adgent/open-seo-mcp-skills/seo-vs-ads/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

SEO vs Ads

Requires

The free Ryze MCP connector (https://connector.get-ryze.ai/mcp). Claude Code: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp. claude.ai / Desktop / Cursor: add it as a custom connector with the same URL. Setup: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp

The report subscription tools can't do: it needs your ads account AND your Search Console together. Both are on the Ryze MCP.

Workflow

  1. Paid search terms. google_ads__runRawGaql on the default account — search terms report, last 90 days: term, impressions, clicks, cost, conversions. (GAQL shape via native__get_provider_docs, provider google_ads, if needed.)
  2. Organic positions. google_search_console__runRawSearchAnalytics, dimension ["query"], same window.
  3. Join on query and bucket:
    • Double-paying — organic position ≤ 3 AND paid spend on the same term. Especially brand terms with no competing advertisers (check top-of-page rate / competition). Sum the spend: that's the number for the headline.
    • Defensible — organic ≤ 3 but competitors bid on the term (paid presence may be justified; say so honestly)
    • Paid-only winners — terms converting in ads with no organic ranking → the SEO content roadmap, pre-validated by money
    • Organic-only converters — strong organic queries with no ad coverage → scale candidates if ads team wants volume
  4. Estimate savings. For the double-paying bucket: spend × the organic click-capture you'd retain (be conservative, ~50–70% for position 1 brand terms; label it an estimate).

Output

Headline first: "$X/quarter going to clicks you already rank #1 for." Then the four buckets as tables (term, cost, conversions, organic position), the savings estimate with its assumptions stated, and a short action list: exact negatives to add, exact pages to build.

Fallback

If only one of the two accounts is connected, run what's possible, and name the missing connection instead of guessing at the other half.

相似的 Skill

lead-research-assistant
ComposioHQ/awesome-claude-skills77k

lead-research-assistant

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

科研

cellprofiler
K-Dense-AI/scientific-agent-skills48k

cellprofiler

Runs reproducible CellProfiler microscopy pipelines for nuclear segmentation, cell counts, and per-object fluorescence measurements. Supports image/channel manifests, headless batch execution, segmentation overlays, and measurement QC for 2D fluorescence assays.

科研

autoskill
K-Dense-AI/scientific-agent-skills48k

autoskill

Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for review. Requires a reachable Screenpipe HTTP API, normally on localhost:3030. Detection and embedding inference run locally; the selected LLM receives redacted app/title cluster summaries and matched skill descriptions. Use only when the user explicitly asks to analyze their recent work and propose skills.

科研

arbor
K-Dense-AI/scientific-agent-skills48k

arbor

Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.

科研

cantera
K-Dense-AI/scientific-agent-skills48k

cantera

Runs Cantera homogeneous chemical reactors and evaluates ignition delay with mechanism provenance, conservation checks, and numerical refinement. Use for combustion kinetics, closed adiabatic ideal-gas constant-volume or constant-pressure ignition, temperature histories, or mechanism-specific ignition-delay comparisons.

科研

bgpt-paper-search
K-Dense-AI/scientific-agent-skills48k

bgpt-paper-search

Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance. Use for literature reviews, evidence synthesis, and finding experimental details beyond abstracts.

科研