From customgpt-ai-rag
Look up whether a specific file or URL was successfully crawled and indexed in the CustomGPT.ai agent. Returns status, page ID, and diagnostic guidance.
How this skill is triggered — by the user, by Claude, or both
Slash command
/customgpt-ai-rag:check-pageThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Find a specific file or URL in the agent's knowledge base and report its crawl and index status. Returns the page ID so you can reference it in `/delete-page` or `/reindex-file`.
Find a specific file or URL in the agent's knowledge base and report its crawl and index status. Returns the page ID so you can reference it in /delete-page or /reindex-file.
.customgpt-meta.json to get agent_idfilename (uploaded files) AND page_url (web sources)Follow the lookup procedure in skills/_shared/api-key.md. Store the result as $API_KEY.
Walk up from $PWD toward /, looking for .customgpt-meta.json. Extract agent_id.
If not found:
"No agent found in this directory tree. Run
/create-agentto set one up first."
If the user provided a filename, path segment, or URL with the command, use it.
Otherwise ask:
"Which file or URL do you want to look up? You can provide a partial name."
Fetch pages 100 at a time, checking each document's filename and page_url for a case-insensitive substring match against the search term. Stop as soon as a match is found.
curl -s --request GET \
--url "https://app.customgpt.ai/api/v1/projects/${AGENT_ID}/pages?page=${PAGE}&limit=100&order=asc" \
--header "Authorization: Bearer ${API_KEY}" \
--header "accept: application/json"
For each entry in data.pages.data[], check filename and page_url (both lowercased) against the lowercased search term.
Continue through pages up to data.pages.last_page. If more than 500 entries have been scanned with no match, warn the user: "Scanned 500+ documents with no match. Try a more specific search term."
If found:
Found:
{filename or page_url}
Field Value Page ID {id} Type {is_file ? "uploaded file" : "URL"} Crawl status {crawl_status} Index status {index_status} Created {created_at}
Status guidance:
| Crawl | Index | Meaning |
|---|---|---|
queued | any | Not yet crawled — indexing is in progress |
ok | queued | Crawled successfully, waiting to be indexed |
ok | ok | Fully indexed and available for queries |
limited | any | Plan limit reached — content was partially processed |
failed | any | Crawl failed — see below |
| any | failed | Indexing failed — see below |
If either status is failed:
"This document failed to process. Try
/reindex-file {filename}to delete and re-upload it. If it continues to fail, check that the file format is supported and the file is not corrupted."
If status is limited:
"Your plan limit was reached while processing this document. Upgrade your CustomGPT.ai plan at https://app.customgpt.ai/billing to process more content."
If not found:
"No document matching '{search_term}' found in the knowledge base." "If you uploaded this file recently, it may still be processing — run
/check-statusto see overall progress, or/list-pagesto browse all indexed documents." "To add this file, run/index-files {filename}."
npx claudepluginhub adorosario/customgpt-skill-plugin --plugin customgpt-ai-ragProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.