New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Index Fix

by Houseofmvps in Houseofmvps/ultraship

Diagnose and fix non-indexed pages using GSC and Bing Webmaster data.

MITAuto-check: notesMarketing & SEO

Install Index Fix

skills CLI
$ npx skills add Houseofmvps/ultraship --skill index-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Houseofmvps/ultraship index-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Houseofmvps/ultraship.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/index-fix .claude/skills/index-fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
index-fix
GitHub stars
123
Token cost
~2.2k tokens
SKILL.md length
1,085 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Diagnose and fix non-indexed pages using GSC and Bing Webmaster data.

  • Works in 9 steps: Credential Check → Index Coverage Overview → Cross-Engine Comparison → …
  • Marketing & SEO work in your project
  • SKILL.md covers Phase 1: Credential Check, Phase 2: Index Coverage Overview, Phase 3: Cross-Engine Comparison and Phase 4: Diagnose Non-Indexed…, plus 7 more sections
  • Calls node; needs ULTRASHIP_GSC_CREDENTIALS and ULTRASHIP_GSC_ACCESS_TOKEN

What it does

Index Fix is an agent skill from Houseofmvps/ultraship. Diagnose and fix non-indexed pages using GSC and Bing Webmaster data. Finds exactly why each page isn't indexed and applies the fix.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO. The repository describes itself as: "ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness… The licence is MIT.

When your agent uses it

  • Marketing & SEO work in your project

Example prompts

  • “/index-fix”

Requirements

  • A credential in ULTRASHIP_GSC_ACCESS_TOKEN
  • A credential in ULTRASHIP_BING_KEY
  • Pre-approved tools (allowed-tools): Bash, Read, Edit, Grep, Glob

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Credential Check
  2. Index Coverage Overview
  3. Cross-Engine Comparison
  4. Diagnose Non-Indexed Pages
  5. Apply Fixes
  6. Resubmit for Indexing
  7. Auto-Fix and Resubmit
  8. Verification Plan
  9. Prevention

What it can do on your machine

Read from SKILL.md and the folder at commit ed232cb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Edit
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ULTRASHIP_GSC_CREDENTIALS
    • ULTRASHIP_GSC_ACCESS_TOKEN
    • ULTRASHIP_BING_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Index Fix loads about 2.2k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,085 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Edit, Grep, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Houseofmvps/ultraship at commit ed232cb, republished under its MIT licence (© Houseofmvps). 1,085 words, ~2,207 tokens.

Download SKILL.mdSave it as .claude/skills/index-fix/SKILL.md (or your agent's skills folder).
name
index-fix
description
Diagnose and fix non-indexed pages using GSC and Bing Webmaster data. Finds exactly why each page isn't indexed and applies the fix.
allowed-tools
Bash, Read, Edit, Grep, Glob
argument-hint
<site-url>

Index Fix — Get Every Page Indexed

Diagnose why pages aren't indexed in Google and Bing, fix the root causes, and resubmit for indexing. This skill uses real data from GSC URL Inspection API and Bing Webmaster Tools — no guessing.

Goal: 100% index coverage for pages that SHOULD be indexed. Not every URL belongs in the index — staging pages, admin panels, thin pagination, and intentionally private content should stay excluded.

Phase 1: Credential Check

Verify data sources:

  1. GSC (required): ULTRASHIP_GSC_CREDENTIALS or ULTRASHIP_GSC_ACCESS_TOKEN
  2. Bing (recommended): ULTRASHIP_BING_KEY

If GSC is not configured, show setup guide and stop — GSC is required for URL inspection.

Phase 2: Index Coverage Overview

Get the current index state:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/index-doctor.mjs coverage <site-url>

This shows:

  • Total pages submitted via sitemaps
  • Total pages indexed
  • Index rate percentage
  • Health status (HEALTHY/WARNING/CRITICAL)

Phase 3: Cross-Engine Comparison

If Bing key is available:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/index-doctor.mjs compare <site-url> <sitemap-url>

Compare Google vs Bing indexing to find:

  • Pages indexed by Google but not Bing (submit to Bing)
  • Pages indexed by Bing but not Google (investigate Google issues)
  • Overall gap analysis

Phase 4: Diagnose Non-Indexed Pages

Run the full diagnosis:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/index-doctor.mjs diagnose <site-url> <sitemap-url>

This inspects up to 50 URLs via GSC URL Inspection API and reports:

  • Which pages are indexed vs not
  • The specific reason each page isn't indexed
  • Severity rating (critical/high/medium/low)
  • Exact fix for each issue
Common Non-Indexing Reasons and Fixes:

Blocked by robots.txt (critical):

  • FIRST: Determine if the block is intentional. Common legitimate reasons to block:
    • Admin/dashboard pages, staging environments, internal tools
    • User-generated content pages, search result pages, faceted navigation
    • API endpoints, health check routes
  • If the block is intentional, do NOT remove it — remove the page from the sitemap instead
  • If the block is unintentional, find the Disallow rule and modify it using the Edit tool
  • Verify the fix: the page should be crawlable

Noindex tag (critical):

  • FIRST: Determine WHY noindex was added. Common legitimate reasons:
    • Staging/preview pages, paginated archives, tag/category pages
    • Thank-you/confirmation pages with sensitive info
    • Legal/compliance requirements, duplicate content by design
    • Pages that should only be accessible via direct link
  • Ask the user before removing noindex — removing it from staging or admin pages can expose sensitive content to search engines
  • If removal is confirmed appropriate, find <meta name="robots" content="noindex"> in the page HTML
  • Remove the noindex directive using the Edit tool
  • Check for X-Robots-Tag header in server config

Soft 404 (high):

  • Google thinks the page looks empty or error-like
  • Add substantial unique content (minimum 300 words)
  • Ensure the page returns HTTP 200 with real content
  • Remove any empty state or placeholder content

Crawled but not indexed (high):

  • Google found the page but decided not to index it
  • Usually means content is too thin, duplicate, or low quality
  • Add more unique, valuable content
  • Build 3+ internal links pointing to this page
  • Differentiate from similar pages on the site

Discovered but not crawled (medium):

  • Google knows the URL exists but hasn't visited it yet
  • Build internal links from high-traffic pages
  • Submit directly for indexing
  • Usually resolves within 1-2 weeks

Redirect (medium):

  • Page redirects to another URL
  • Update sitemap and internal links to use the final destination URL
  • Remove the redirecting URL from sitemap

Canonical mismatch (medium):

  • Google chose a different canonical URL
  • Either fix the canonical tag to point to this URL, or accept Google's choice
  • Remove from sitemap if it's truly a duplicate

Server error (critical):

  • Page returns 5xx error when Google crawls it
  • Fix the server error (check logs)
  • Ensure the page loads correctly under load

404 Not Found (high):

  • Page doesn't exist anymore
  • Remove from sitemap
  • Set up 301 redirect to relevant page
Show full SKILL.md (503 more words)Show less

Phase 5: Apply Fixes

⚠️ SAFETY FIRST: Before applying ANY fix, verify the block/exclusion wasn't intentional. Ask the user if unsure. Removing noindex from staging pages or robots.txt Disallow from admin paths can expose sensitive content.

For each diagnosed issue, apply the fix:

robots.txt fixes:

  • Read the current robots.txt
  • Check if the Disallow rule protects staging, admin, or private pages — if so, remove the page from the sitemap instead of unblocking it
  • Only edit rules that are clearly unintentional blocks on public content
  • Ensure important public paths are not blocked

noindex fixes:

  • Verify with the user that the page should be public before removing noindex
  • Search HTML files for noindex tags
  • Remove them using Edit tool only after confirming they're not protecting sensitive content

Content quality fixes:

  • Identify thin pages (<300 words)
  • Flag for content expansion
  • Cannot auto-generate content, but can restructure and add schema

Sitemap cleanup:

  • Remove 404 and redirect URLs from sitemap
  • Regenerate if needed:
bash
node ${CLAUDE_PLUGIN_ROOT}/tools/sitemap-generator.mjs <dir> <base-url>

Internal linking:

  • Find high-traffic pages (from GSC query data)
  • Add contextual links from high-traffic pages to non-indexed pages
  • Use descriptive anchor text with target keywords

Phase 6: Resubmit for Indexing

Only resubmit pages where you've made SUBSTANTIAL fixes (added content, removed blocking directives, fixed server errors). Do NOT resubmit unchanged pages — this wastes API quota and can flag your account for spam.

After fixes, submit to both search engines:

Google:

bash
# Resubmit sitemap (only after sitemap changes)
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs submit-sitemap <site-url> <sitemap-url>

Bing:

bash
# Submit sitemap (only after sitemap changes)
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs submit-sitemap <site-url> <sitemap-url>

# Batch submit specific fixed URLs for fast indexing (max 500/day — only URLs you actually fixed)
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs submit-url-batch <site-url> <url1> <url2> ...

Phase 7: Auto-Fix and Resubmit

Run the auto-fix command which diagnoses AND submits non-indexed URLs:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/index-doctor.mjs fix <site-url> <sitemap-url>

This automatically:

  1. Inspects all sitemap URLs
  2. Identifies non-indexed pages
  3. Submits fixable URLs to Bing for re-indexing
  4. Returns a prioritized fix plan

Phase 8: Verification Plan

After applying fixes:

  1. Re-run coverage check to compare before/after
  2. Set a reminder to re-check in 1-2 weeks (Google re-crawl takes time)
  3. Monitor GSC for new indexing issues
bash
node ${CLAUDE_PLUGIN_ROOT}/tools/index-doctor.mjs coverage <site-url>

Phase 9: Prevention

Advise on preventing future indexing issues:

  • Always test new pages for noindex tags before deploying
  • Keep sitemap updated (auto-generate on deploy)
  • Monitor robots.txt changes
  • Ensure all pages have unique, substantial content
  • Build internal links to every new page
  • Submit sitemap to both GSC and Bing after every deploy

Key Principles

  1. Diagnose before fixing — understand WHY each page isn't indexed
  2. Verify intent before removing blocks — noindex and robots.txt Disallow rules are often intentional (staging, admin, privacy, legal). Ask before removing.
  3. Fix the root cause — don't just resubmit, fix the underlying issue
  4. Both engines matter — Bing powers ChatGPT Search, DuckDuckGo, Yahoo
  5. Only submit pages you've actually fixed — resubmitting unchanged pages wastes quota and can trigger spam flags
  6. Prevention > cure — set up processes to catch issues before they happen

Rollback Plan

If fixes cause unexpected issues (pages appearing in search that shouldn't, traffic drops):

  1. Re-add noindex to any pages that were incorrectly unblocked
  2. Restore robots.txt Disallow rules that were removed in error
  3. Remove pages from sitemap that shouldn't be indexed
  4. Re-run coverage to verify the rollback took effect
  5. Google re-crawl may take 1-2 weeks — request re-crawl via GSC for urgent fixes

© Houseofmvps, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/index-fix of Houseofmvps/ultraship.

Open the folder on GitHubat commit ed232cb

Compare with similar skills

Index Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Index Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Index Fix this skillHouseofmvps/ultraship123—~2.2kAutomated safety check: NotesMIT
Geo Fundamentalswasp-lang/wasp19k9 repos~861Automated safety check: PassMIT
Ab Testingcoreyhaines31/marketingskills54k3 repos~3.1kAutomated safety check: PassMIT
Hreflang and International SEOAgriciDaniel/claude-seo19k5 repos~3.4kAutomated safety check: PassMIT
Referralscoreyhaines31/marketingskills54k2 repos~2.6kAutomated safety check: PassMIT
SEO GeoReScienceLab/opc-skills1.8k4 repos~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • Geo Fundamentals

    wasp-lang/wasp

    Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

    19k GitHub starsUsed in 9 repos~861 tokens
    Marketing & SEOAuto-check passed

  • Ab Testing

    coreyhaines31/marketingskills

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.

    54k GitHub starsUsed in 3 repos~3.1k tokens
    Marketing & SEOAuto-check passed

  • Hreflang and International SEO

    AgriciDaniel/claude-seo

    Audits, validates and generates hreflang tags for multi-language and multi-region sites in HTML, HTTP headers or XML sitemaps, flagging common code and return-tag mistakes.

    19k GitHub starsUsed in 5 repos~3.4k tokens
    Marketing & SEOAuto-check passed

  • Referrals

    coreyhaines31/marketingskills

    When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.

    54k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed

  • SEO Geo

    ReScienceLab/opc-skills

    SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.

    1.8k GitHub starsUsed in 4 repos~2.1k tokens
    Marketing & SEOAuto-check passed

  • Ad Creative

    LeoYeAI/openclaw-marketing-skills

    When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.

    1k GitHub starsUsed in 8 repos~3.4k tokens
    Marketing & SEOAuto-check passed

More from Houseofmvps/ultraship

All 28 skills in this repo

  • Using Ultraship

    Houseofmvps/ultraship

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    123 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed

  • A11y

    Houseofmvps/ultraship

    Accessibility audit + auto-fix (WCAG 2.2 A/AA). An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check: notes

  • Architecture

    Houseofmvps/ultraship

    Living Architecture Map — auto-generate Mermaid diagrams of your codebase.

    123 GitHub stars~708 tokensUpdated 3 mo ago
    Auto-check: notes

  • Clone Patterns

    Houseofmvps/ultraship

    Learn From the Best — analyze patterns from any codebase and apply them to yours.

    123 GitHub stars~682 tokensUpdated 3 mo ago
    Auto-check: notes

  • Code Review

    Houseofmvps/ultraship

    Code review with principal-engineer-level depth. An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Compete

    Houseofmvps/ultraship

    Competitive X-Ray — analyze any competitor URL vs your site.

    123 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Index Fix

What does Index Fix do?

Diagnose and fix non-indexed pages using GSC and Bing Webmaster data. Index Fix is an agent skill from Houseofmvps/ultraship. Diagnose and fix non-indexed pages using GSC and Bing Webmaster data.

When should I use Index Fix?

Index Fix fits situations like: marketing & SEO work in your project.

How do I install Index Fix in Claude Code?

Run `npx skills add Houseofmvps/ultraship --skill index-fix -a claude-code`. Or copy the skill folder (skills/index-fix in Houseofmvps/ultraship) into .claude/skills/index-fix in your project. Claude Code loads it when a task matches its description.

How do I install Index Fix in Codex?

Run `npx skills add Houseofmvps/ultraship --skill index-fix -a codex`. Or copy the skill folder (skills/index-fix in Houseofmvps/ultraship) into .agents/skills/index-fix in your project. Codex loads it when a task matches its description.

Can I use Index Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Houseofmvps/ultraship --skill index-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/index-fix, .gemini/skills/index-fix, .github/skills/index-fix and .opencode/skills/index-fix in your project.

What does Index Fix need to run?

Going by SKILL.md and its folder, Index Fix needs the command-line tools its instructions call (node) and credentials named ULTRASHIP_GSC_CREDENTIALS, ULTRASHIP_GSC_ACCESS_TOKEN and ULTRASHIP_BING_KEY. Our summary lists: A credential in ULTRASHIP_GSC_ACCESS_TOKEN; A credential in ULTRASHIP_BING_KEY. Its frontmatter pre-approves these tools: Bash, Read, Edit, Grep, Glob.

Does Index Fix access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Index Fix safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Index Fix use?

Index Fix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Index Fix use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Index Fix?

Skills that share tags, products or a category with Index Fix: Geo Fundamentals (wasp-lang/wasp, 19k stars), Ab Testing (coreyhaines31/marketingskills, 54k stars), Hreflang and International SEO (AgriciDaniel/claude-seo, 19k stars) and Referrals (coreyhaines31/marketingskills, 54k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Index Fix?

Houseofmvps (a GitHub user) maintains it in Houseofmvps/ultraship, which has 123 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on July 8, 2026.

Source: Houseofmvps/ultraship on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.