Skip to content

Conversation

@thedaviddias
Copy link
Owner

@thedaviddias thedaviddias commented Jan 5, 2026

This PR adds Incol Intelligence to the llms.txt hub.

Submitted by: x23436913

Website: https://www.incolintelligence.com/
llms.txt: https://www.incolintelligence.com/llms.txt
llms-full.txt: https://www.incolintelligence.com/llms-full.txt
Category: finance-fintech


This PR was created via admin token for a user without GitHub repository access.

Please review and merge if appropriate.


Note

Adds a new website entry for Incol Intelligence to the hub.

  • New packages/content/data/websites/incol-intelligence-llms-txt.mdx with name, description, website, llmsUrl, llmsFullUrl, category (finance-fintech), and publishedAt
  • Includes brief content section with title and description

Written by Cursor Bugbot for commit 8bc8ddb. This will update automatically on new commits. Configure here.

Summary by CodeRabbit

  • New Content
    • Added website content information for Incol Intelligence.

✏️ Tip: You can customize this high-level summary in your review settings.

@vercel
Copy link

vercel bot commented Jan 5, 2026

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Review Updated (UTC)
llms-txt-hub Ready Ready Preview, Comment Jan 5, 2026 9:26am

@coderabbitai
Copy link

coderabbitai bot commented Jan 5, 2026

Walkthrough

A new MDX data file for Incol Intelligence's website entry was added to the llms.txt hub content directory. The file contains standard YAML front matter metadata (name, description, website URLs, category, and publish date) along with descriptive content. No code logic or API changes introduced.

Changes

Cohort / File(s) Summary
Website Content Metadata
packages/content/data/websites/incol-intelligence-llms-txt.mdx
New MDX file added with YAML front matter containing website metadata fields (name, description, website, llmsUrl, llmsFullUrl, category, publishedAt) and content describing Incol Intelligence

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

Pre-merge checks

✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and concisely describes the main change: adding Incol Intelligence to the llms.txt hub, which matches the PR's primary objective.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

Fix all issues with AI Agents 🤖
In @packages/content/data/websites/incol-intelligence-llms-txt.mdx:
- Around line 5-6: Both llms.txt endpoints referenced by llmsUrl and llmsFullUrl
are returning 404/HTML WordPress pages; either update the values to point to
working plain-text endpoints or create/configure the two paths on the site to
serve the required plain-text files. Fix by (a) placing the llms.txt and
llms-full.txt files at the site root or correct paths and ensure the server
serves them with Content-Type: text/plain, or (b) change the llmsUrl and
llmsFullUrl values to the correct existing plain-text URLs; after updating,
verify each URL returns HTTP 200 with plain-text content before merging.
📜 Review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between a28c655 and 8bc8ddb.

📒 Files selected for processing (1)
  • packages/content/data/websites/incol-intelligence-llms-txt.mdx
🧰 Additional context used
🔍 Remote MCP

I'll search for relevant information about this PR to help with the review. Let me gather context about the llms.txt hub project, Incol Intelligence, and the submission validation process.## Summary: Relevant Context for PR #507 Review

About Incol Intelligence

Incol Intelligence is an analytical, reporting, and risk management SaaS platform for residential mortgage stakeholders that combines proprietary data with third-party and public data to facilitate optimal credit, climate, physical risk analysis, and ESG, funding, regulatory and capital management reporting. The platform features over 50 interactive dashboards and tools for detailed analytics, portfolio management, and climate risk assessment. The company is a legitimate fintech provider in the finance-fintech category matching the PR's category designation.

llms.txt Hub Submission Standards and Validation

Most submissions are reviewed within 24-48 hours, with verification that the llms.txt file is accessible, contains valid content, and meets quality standards.

File Format Requirements:

  • An optional /llms-full.txt file is also supported for comprehensive documentation.
  • llms.txt should contain essential information about your site (typically under 2,000 tokens).
  • llms.txt files should be plain text without HTML formatting, using simple text formatting like line breaks, headers with dashes or equals signs, and bullet points with dashes or asterisks for structure.

Submission Process:

  • Submissions follow a template format in the content/websites directory, and are automatically validated and processed.

Content Requirements

Submissions should include the site's purpose, main content areas, key pages or APIs, usage guidelines for AI systems, and any specific instructions for LLMs, keeping it informative but concise with clear, structured information.

Validation Checkpoints for PR Review

Key items to verify in this PR submission:

  1. URL Accessibility: Confirm both provided llms.txt URLs are currently accessible and return valid content
  2. File Format: Verify the MDX file follows the established schema (name, description, website, llmsUrl, llmsFullUrl, category, publishedAt)
  3. Category Accuracy: Confirm "finance-fintech" is appropriate for Incol Intelligence's business focus
  4. Content Validity: Check that the referenced llms.txt files contain LLM-friendly formatted content
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
  • GitHub Check: Cursor Bugbot
  • GitHub Check: Validate
🔇 Additional comments (2)
packages/content/data/websites/incol-intelligence-llms-txt.mdx (2)

1-9: ✓ YAML front matter structure is correct.

The file follows the established schema with all required fields: name, description, website, llmsUrl, llmsFullUrl, category, and publishedAt. The "finance-fintech" category accurately reflects Incol Intelligence's business focus in climate-related risk management for the mortgage and fintech sector.


11-13: Markdown content is minimal but appropriate.

The header and description are consistent with the YAML front matter and provide adequate context for the hub entry. Content is concise and follows the simple text formatting guidelines.

Comment on lines +5 to +6
llmsUrl: 'https://www.incolintelligence.com/llms.txt'
llmsFullUrl: 'https://www.incolintelligence.com/llms-full.txt'
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Description: Verify that the llms.txt and llms-full.txt URLs are accessible 
# and contain plain text content without HTML formatting.

echo "=== Checking llms.txt accessibility and format ==="
curl -s -o /dev/null -w "HTTP Status: %{http_code}\n" "https://www.incolintelligence.com/llms.txt"
echo "Content preview (first 500 chars):"
curl -s "https://www.incolintelligence.com/llms.txt" | head -c 500
echo -e "\n\n=== Checking llms-full.txt accessibility and format ==="
curl -s -o /dev/null -w "HTTP Status: %{http_code}\n" "https://www.incolintelligence.com/llms-full.txt"
echo "Content preview (first 500 chars):"
curl -s "https://www.incolintelligence.com/llms-full.txt" | head -c 500
echo -e "\n\n=== Format validation: checking for HTML tags ==="
if curl -s "https://www.incolintelligence.com/llms.txt" | grep -q "<html\|<body\|<div\|<p>"; then
  echo "⚠️  WARNING: HTML tags detected in llms.txt (should be plain text)"
else
  echo "✓ llms.txt appears to be plain text format"
fi

if curl -s "https://www.incolintelligence.com/llms-full.txt" | grep -q "<html\|<body\|<div\|<p>"; then
  echo "⚠️  WARNING: HTML tags detected in llms-full.txt (should be plain text)"
else
  echo "✓ llms-full.txt appears to be plain text format"
fi

Repository: thedaviddias/llms-txt-hub

Length of output: 1472


Both llms.txt URLs return 404 errors and must be fixed before merge.

Verification reveals both referenced endpoints are broken:

  • https://www.incolintelligence.com/llms.txt returns HTTP 404
  • https://www.incolintelligence.com/llms-full.txt returns HTTP 404

Both URLs return WordPress error pages in HTML format instead of the required plain text content per llms.txt hub submission standards. These endpoints must be created and properly configured before this change can be merged.

🤖 Prompt for AI Agents
In @packages/content/data/websites/incol-intelligence-llms-txt.mdx around lines
5-6, Both llms.txt endpoints referenced by llmsUrl and llmsFullUrl are returning
404/HTML WordPress pages; either update the values to point to working
plain-text endpoints or create/configure the two paths on the site to serve the
required plain-text files. Fix by (a) placing the llms.txt and llms-full.txt
files at the site root or correct paths and ensure the server serves them with
Content-Type: text/plain, or (b) change the llmsUrl and llmsFullUrl values to
the correct existing plain-text URLs; after updating, verify each URL returns
HTTP 200 with plain-text content before merging.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants