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

quickfill-mcp

CLAUDE.md7 starsChanged 7 months agoMITView on GitHub

This file provides Claude with instructions on how to use the Quickfill Generative UI toolkit.

  • In this repositoryOne other file it gives its agents.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When using Quickfill to render UIs:

    line 11
  2. Very specific:

    Lazy Fetching: If the user provides a data file, mount_file it first, then use fetch() in the Alpine.js x-init block to load and parse it.

    line 14
  3. Very specific:

    Proactive Visuals: If the user asks for data analysis, don't just output text.

    line 18
  4. Distinctive:

    Iterative Updates: Update the UI frequently based on user feedback.

    line 19
  5. Very specific:

    Portability: Use relative paths (e.g., ./filename.csv) for mounted files in your UI code.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Quickfill Project Rules

This file provides Claude with instructions on how to use the Quickfill Generative UI toolkit.

🛠 MCP Tools

Quickfill provides two core tools:

  • mcp_quickfill_render_interactive_ui: Renders HTML/Alpine.js/Tailwind code to a live browser window.
  • mcp_quickfill_mount_file: Exposes a local file to the web server for browser parsing.

🎨 Generative UI Standards

When using Quickfill to render UIs:

  1. Always use Tailwind CSS: It is pre-injected. Use it for all styling.
  2. Always use Alpine.js: It is pre-injected. Use it for reactivity and logic.
  3. Lazy Fetching: If the user provides a data file, mount_file it first, then use fetch() in the Alpine.js x-init block to load and parse it.
  4. WASM Support: Mention excel, pdf, or ocr in the required_libs array of render_interactive_ui if you need to parse those file types.

🧠 Strategic Advice

  • Proactive Visuals: If the user asks for data analysis, don't just output text. Proactively build a dashboard using render_interactive_ui.
  • Iterative Updates: Update the UI frequently based on user feedback. The server supports hot-reloading.
  • Portability: Use relative paths (e.g., ./filename.csv) for mounted files in your UI code.

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