agentleFS
Sign inStart free
DikshitRJDikshitRJ/quickfill-mcp/AGENTS.md

quickfill-mcp

AGENTS.md7 starsChanged 7 months agoMITView on GitHub

This document provides instructions for AI Agents (like Claude, GPT-4, etc.) on how to effectively use the Quickfill MCP server to provide the best user experience.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a user provides a data file (Excel, CSV, PDF):

    line 11
  2. Very specific:

    Use mount_file to get a browser-accessible URL for the file.

    line 12
  3. Very specific:

    Use render_interactive_ui to display the dashboard.

    line 14
  4. Distinctive:

    Don't try to build the perfect UI in one go.

    line 17
  5. Very specific:

    Start with a basic layout using render_interactive_ui.

    line 18
  6. Distinctive:

    Ask the user for feedback.

    line 19
  7. Very specific:

    Update specific sections of the html_body in subsequent calls to render_interactive_ui to "hot-reload" the changes.

    line 20
  8. Distinctive:

    Always use Tailwind CSS classes for styling.

    line 23
  9. Very specific:

    Responsive: Use md:, lg: classes to ensure the UI looks good in different window sizes.

    line 24
  10. Very specific:

    Use Alpine.js for logic. It is pre-injected and lightweight.

    line 28
  11. Very specific:

    Use x-data for state.

    line 29
  12. Very specific:

    Use x-on or @ for events.

    line 30
  13. Very specific:

    Use x-init to trigger data fetching from mounted files.

    line 31
  14. Distinctive:

    Only use these if requested by the tool call:

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

🤖 Agent Guidelines for Quickfill

This document provides instructions for AI Agents (like Claude, GPT-4, etc.) on how to effectively use the Quickfill MCP server to provide the best user experience.

🧠 Core Philosophy

Quickfill is a Generative UI toolkit. Instead of writing code for the user to copy-paste, you should use the tools to build and show the interface directly.

🛠 Tool Usage Patterns

1. The Data-to-UI Pattern

When a user provides a data file (Excel, CSV, PDF):

  1. Use mount_file to get a browser-accessible URL for the file.
  2. Generate an Alpine.js dashboard that fetch()es that URL.
  3. Use render_interactive_ui to display the dashboard.

2. The Iterative Design Pattern

Don't try to build the perfect UI in one go.

  1. Start with a basic layout using render_interactive_ui.
  2. Ask the user for feedback.
  3. Update specific sections of the html_body in subsequent calls to render_interactive_ui to "hot-reload" the changes.

🎨 Design System: Tailwind CSS

Always use Tailwind CSS classes for styling. It is pre-injected into every Quickfill session.

  • Responsive: Use md:, lg: classes to ensure the UI looks good in different window sizes.
  • Dark Mode: Quickfill supports standard Tailwind dark mode patterns.

⚡ Interactivity: Alpine.js

Use Alpine.js for logic. It is pre-injected and lightweight.

  • Use x-data for state.
  • Use x-on or @ for events.
  • Use x-init to trigger data fetching from mounted files.

📦 External Libraries

Only use these if requested by the tool call:

  • excel: Provides XLSX (SheetJS) for parsing spreadsheets.
  • pdf: Provides pdfjsLib for rendering PDFs.
  • ocr: Provides Tesseract for optical character recognition.

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.

Check your setup, free