agentleFS
andrefigueiraandrefigueira/.context/.claude/skills/generate-tool-config/SKILL.md

generate-tool-config

Skill253 starsChanged 11 months agoMITView on GitHub

Generate tool-specific configuration files (Cursor rules, Copilot instructions, Windsurf rules) from the .context/ documentation. Use when setting up a project for a specific AI coding tool.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create .cursor/rules/ directory with .mdc files:

    line 13
  2. Very specific:

    Use alwaysApply: true only for general.mdc

    line 16
  3. Distinctive:

    Keep under 50 lines (Copilot works best with concise instructions)

    line 22
  4. Distinctive:

    Must stay under 6000 characters

    line 27
  5. Very specific:

    Read .context/ai-rules.md and .context/architecture/patterns.md first

    line 35
  6. Very specific:

    Keep generated files minimal.

    line 36
  7. Distinctive:

    Follow each tool's format requirements exactly

    line 37
  8. Distinctive:

    Test that file paths are correct relative to project root

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
SKILL.md

Generate AI tool configuration files from the existing .context/ documentation.

Target: $ARGUMENTS

For "cursor"

Create .cursor/rules/ directory with .mdc files:

  • general.mdc - Always-apply rules from @.context/ai-rules.md
  • One .mdc per domain with appropriate glob patterns
  • Use alwaysApply: true only for general.mdc
  • Reference .context/ files with @ syntax

For "copilot"

Create .github/copilot-instructions.md:

  • Extract key rules from .context/ai-rules.md
  • Keep under 50 lines (Copilot works best with concise instructions)
  • Reference .context/ file paths for the agent to read

For "windsurf"

Create .windsurfrules:

  • Must stay under 6000 characters
  • Prioritize rules from .context/ai-rules.md and .context/architecture/patterns.md
  • Include file references for domain-specific context

For "all"

Generate all three above.

Rules

  • Read .context/ai-rules.md and .context/architecture/patterns.md first
  • Keep generated files minimal. Don't duplicate content, point to .context/ files
  • Follow each tool's format requirements exactly
  • Test that file paths are correct relative to project root

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.