agentleFS
jbobbinkjbobbink/seo-gsc-wizard/skills/bing-crawl-health/SKILL.md

bing-crawl-health

Skill0 starsChanged 24 days agoMITView on GitHub

Check Bing crawl, index and link health for a Search Console property with the GSC Wizard MCP server's Bing Webmaster tools: daily pages crawled and indexed with the response-code breakdown, crawl issues grouped by type (4xx, 5xx, redirects, robots blocks, DNS and timeout errors, malware) with fixes, sitemap and feed status, the most-linked URLs and whether they are healthy, the URL submission quota, and an optional confirmed IndexNow resubmission of fixed pages. Use when the user asks "is Bing crawling my site", "Bing crawl errors", "Bing index count", "Bing sitemap status", "backlinks in Bing", "resubmit to Bing", or "IndexNow".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Submission quota: Call get_bing_url_submission_quota for dailyQuota and monthlyQuota (null when Bing did not report one).

    line 24
  2. Very specific:

    Do not fabricate rows the tools did not return.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Bing Crawl Health

Diagnose how Bing crawls, indexes and links a property, and produce an issue summary grouped by type with concrete fixes, the feed status, the most-linked URLs and recommendations. This is the Bing counterpart of the indexing-health skill; for Google's index run that one. The user's request may contain a property name or URL, a date range for the crawl trend, a focus hint (a path or section), or a list of fixed URLs to resubmit; use it to skip resolution or narrow the suspect set.

Workflow

  1. Resolve the property. If the user's request or the conversation names a property, use it. Site URLs use GSC formats: sc-domain:example.com or https://www.example.com/. Otherwise call list_sites and pick the obvious match. If several plausible properties exist, ask the user which one before continuing. Every property-scoped Bing tool takes that same GSC siteUrl and maps it to Bing's form itself (sc-domain:example.com becomes https://example.com/), echoing the result as bingSiteUrl.
  2. Confirm the Bing side. Call list_bing_sites (no arguments). A notConfigured: true answer means Bing Webmaster Tools is not connected for the property's Google account in the GSC Wizard app; tell the user to add it there, point them at the indexing-health skill for the Google side, and stop. Otherwise find the property in siteDetails and read isVerified: Bing serves data only for a verified site, an unverified one makes the property-scoped tools answer with a not-verified error that names the fix (a subfolder property has to be verified as its own site in Bing Webmaster Tools), and a property missing from sites has to be added there first.
  3. Crawl trend. Call get_bing_crawl_stats with startDate and endDate for the last 28 days unless the user set a range; omit both dates for everything Bing has, about 6 months of crawl data, when the user wants the long trend. daily[] rows (oldest first) carry crawledPages, inIndex, inLinks, code2xx, code301, code302, code4xx, code5xx, blockedByRobotsTxt, allOtherCodes, crawlErrors and containsMalware. A day Bing did not report is missing from the series, not a zero, so never read a gap as a crawl stop. Compare the first and last reported weeks: whether pages crawled and inIndex rise or fall, and the share of the crawl that hit a 4xx, a 5xx or a robots block (derived from the row sums; say so). An inIndex drop with a 5xx or robots rise on the same days is the pattern to flag first. Bing reports on its own calendar and carries no settledThrough or partialDays, so do not apply the Google reporting-lag rule here.
  4. Crawl issues. Call get_bing_crawl_issues; the limit default of 200 is fine, and raise it when rowCount equals the limit. issues[] rows carry url, httpCode, inLinks and issues, a list of decoded labels: "301 redirect", "302 redirect", "HTTP 4xx", "HTTP 5xx", "Blocked by robots.txt", "Important URL blocked by robots.txt", "Contains malware", "DNS error" and "Timeout error". Rows come most inbound links first, so the top of the list is the most damaging. Group by label (a URL with several labels counts under each), count the URLs per group, keep the two or three examples with the most inLinks, and narrow to the user's focus path when one was given. An emptyBecause answer means Bing reports no issues; say so rather than leaving the section blank. Any "Contains malware" row is urgent and goes first.
  5. Feeds. Call get_bing_feeds. feeds[] rows carry url, status (Pending, Success, Warning or Error), type (Sitemap, Sitemap index, Atom, RSS, Text or mRSS), lastCrawled, submitted, urlCount, fileSize and compressed; a date of 1601-01-01 is Bing's empty value, not a real date. Flag Error and Warning feeds, a lastCrawled well behind today, a urlCount of 0, and a property with no feeds at all (emptyBecause), which means Bing discovers pages only by crawling. For the Google sitemap view run the indexing-health skill rather than repeating it here.
  6. Most-linked URLs. Call get_bing_link_counts with page: 0 and limit: 50. Page 0 usually holds every linked URL, and totalPages is the number of linked URLs Bing reports, not a count of result pages, so do not page further; when truncated is true and the user wants the full list, raise limit instead. links[] rows carry url and count, most links first. Check each top URL against step 4 by exact URL: a most-linked URL that is also a 4xx, a redirect or a robots block wastes the links pointing at it and is the top fix, and a most-linked URL that redirects should have its links repointed at the final page.
  7. Submission quota. Call get_bing_url_submission_quota for dailyQuota and monthlyQuota (null when Bing did not report one). Report both as Bing's remaining URL submission allowance for the property, which is separate from IndexNow and is not spent by anything in this workflow.
  8. Resubmit fixed URLs (optional, write). Only when the user asks, or names URLs they have fixed. First call get_indexnow_settings and read indexnowApiKeySet, keyFileVerified and keyFileUrl: when indexnowApiKeySet is false, say the setup needs update_indexnow_settings with generateKey: true and the returned key file published at the site root, and ask before running that write. Then ALWAYS list the exact URLs (at most 100, all on the property; others are dropped and reported in skippedOffProperty) and ask the user to confirm before calling submit_indexnow_urls with siteUrl and urls. Read outcome and explain it:
    • submitted: IndexNow accepted the batch.
    • pending_key_validation: the usual 202, accepted with key validation pending; engines fetch the key file afterwards and discard the batch without notice if it is unreachable, so this is not delivered and not indexed.
    • setup_incomplete: nothing was sent, and message names the key file to publish.
    • rejected: IndexNow refused everything that was sent. Report submitted, failed and message. If the call is refused because the connection is read-only, say this step needs write access and continue with the read-only parts. list_indexnow_submissions shows the history afterwards; batches refused before sending are absent from it on purpose.

Interpretation rules

  • A day missing from get_bing_crawl_stats is unreported, not zero; a day with crawledPages: 0 is a real zero.
  • Weight every issue by inLinks and by the crawl volume behind it, not by the count of URLs alone: ten orphan 404s matter less than one 404 with fifty links.
  • A URL carries every label that applies, so the per-type counts in the issue table can add up to more than the number of issue URLs; say so under the table.
  • A feed date of 1601-01-01 means "never": a lastCrawled of 1601-01-01 is a feed Bing has not fetched.
  • Present every multi-row result as a compact markdown table (top rows only, typically 5 to 10); keep prose for interpretation, not for restating numbers.
  • Do not fabricate rows the tools did not return; if a tool returns nothing, say so and relay its emptyBecause and nextStep where present.

Output

Present the findings in this order, with compact markdown tables (top rows only, typically 5 to 10) for multi-row data and prose only for interpretation:

  1. Crawl trend: a sentence or two, plus a small table of the first and last reported weeks (pages crawled, inIndex, 4xx, 5xx, robots blocks) derived from the daily rows.
  2. Issues by type:
Issue typeURLsExamples (most linked first)Fix

Map each type to a concrete fix:

  • HTTP 4xx: restore the page or 301 it to the closest live page, then drop it from sitemaps and internal links.
  • HTTP 5xx, DNS error, Timeout error: a server or DNS problem, so check hosting, the CDN and any rate limiting of Bing's crawler.
  • 301 or 302 redirect: point internal links and sitemap entries at the final URL; turn a permanent 302 into a 301.
  • Blocked by robots.txt, Important URL blocked by robots.txt: confirm the block is intended and remove the rule if not.
  • Contains malware: urgent; clean the page and request a review in Bing Webmaster Tools.
  1. Feed status:
Feed URLTypeStatusLast crawledURLsFix
  1. Most-linked URLs: a table with URL, link count and health ("clean", or the issue label from step 4).
  2. Quota in one line, and the submission result when step 8 ran.
  3. End with a short prioritized list of 3 to 7 concrete recommendations, highest impact first: the most-linked broken URLs, the issue group with the most URLs, the feed to fix, and whether a resubmission is worth it once fixes ship.

For Bing traffic and rankings run the bing-performance skill; for Google's index run the indexing-health skill.

Error handling

If any tool call fails with an authentication or subscription error, tell the user to run /mcp to (re)authenticate, and that a GSC Wizard account with an active plan or trial plus a connected Google Search Console account is required. If the property is not found, re-run list_sites and offer the closest matches instead of guessing a URL format. If a single tool fails for another reason, report the gap in the relevant section and complete the rest of the workflow with the remaining data. A Bing rate-limit error says to wait a moment and try again: do that once, and never loop.

Grounding

Every number you report must name the tool it came from and the date range it covers, for example "clicks 12,340 (get_site_summary, 2026-09-21 to 2026-09-27)". For a table, state the tool and date range once on the line above it. If you derive a figure yourself (a delta, a sum, a share), say so and name the tool outputs it was computed from. Never report a number no tool returned.

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.