agentleFS
sitetillersitetiller/ai-visibility-skills/skills/gsc-bing/SKILL.md

gsc-bing

Skill0 starsChanged 3 days agoMITView on GitHub

Read Google Search Console and Bing Webmaster Tools data together and act on the differences: queries that only one engine shows you for, big position gaps, and pages where Bing (which grounds Microsoft Copilot answers) lags Google. Use when the user asks to compare Google and Bing, 'why do I rank on Google but not Bing', 'pull my Search Console data', 'what queries should I target', 'Bing traffic', 'Copilot visibility', or wants one report from both engines. Requires the user's own read-only credentials.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read totals, onlyBing, onlyGoogle and biggestPositionGaps.

    line 24
  2. Distinctive:

    Search Console's API returns top rows, not every row, and both engines omit rare queries.

    line 49
  3. Very specific:

    Do not claim Bing rankings decide Copilot citations.

    line 51
  4. Distinctive:

    Read-only. Never request write scopes.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google + Bing, side by side

Most SEO work reads Google only. Bing's index also feeds Copilot answers, and the two engines often disagree about which of your pages deserve to rank. This skill pulls both, joins them by query, and turns the differences into a short action list.

Setup (once)

  • Google: a service account JSON key with read access to the Search Console property (add the service account email under Settings → Users and permissions as a "Restricted" user), then GOOGLE_APPLICATION_CREDENTIALS=/path/key.json. Or GOOGLE_ACCESS_TOKEN from gcloud auth print-access-token with the webmasters.readonly scope.
  • Bing: Bing Webmaster Tools → Settings → API Access → Generate API Key, then BING_WEBMASTER_API_KEY=.... The key is per user and works for all your verified sites. Never paste keys into chat; set them in the shell or a local .env that is gitignored.
  • Details and troubleshooting: the setup skill.

Steps

  1. Pick a window. Bing updates its stats weekly, so use at least 28 days and end the window a few days ago.
    npx sitetiller engines example.com https://example.com/ --start 2026-10-01 --end 2026-11-05 --json > engines.json
    The first argument is the Search Console site (example.com becomes sc-domain:example.com; pass a URL-prefix property as a full URL). The second is the Bing site URL exactly as verified in Bing.
  2. Read totals, onlyBing, onlyGoogle and biggestPositionGaps.
  3. Classify each finding:
PatternLikely meaningAction
Query only in Google, many impressionsBing has not indexed or does not rank the pageCheck the page in Bing URL Inspection; submit the sitemap in Bing; ping IndexNow
Query only in BingGoogle filters or ranks the page lowerInspect in Search Console (indexing, canonical); compare the page with what ranks on Google
Bing position much worse (gap > 5)Page weak on Bing's signals for that queryCheck title/meta match, internal links, and Bing's Site Explorer for crawl issues
Google position much worseOften freshness or a competing page on GoogleLook for cannibalization (cannibal skill) and update the page
Clicks share on Bing far below impressions shareSnippet or title not chosen on BingRewrite the title for the query wording
  1. Pull page-level data when a query points to a page:
    npx sitetiller gsc example.com --start 2026-10-01 --end 2026-11-05 --dims query,page --out gsc-query-page.csv
    npx sitetiller bing https://example.com/ --pages --start 2026-10-01 --end 2026-11-05 --json
    npx sitetiller inspect example.com https://example.com/pricing --json

Output to the user

  1. Totals for both engines, same window, stated with dates.
  2. Top 10 "only in Bing" and "only in Google" queries with impressions.
  3. Top 10 position gaps with the page involved.
  4. Five actions, each tied to a specific query or page.

Guardrails

  • Search Console's API returns top rows, not every row, and both engines omit rare queries; say so when comparing totals.
  • Bing's data is weekly; never compare a Bing week with a Google day.
  • Do not claim Bing rankings decide Copilot citations. Microsoft says Copilot answers ground on Bing; citation data is only in Bing's AI Performance report (see ai-citations).
  • Read-only. Never request write scopes.

References

  • references/sources.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.