agentleFS
aracharach/arc/docs/skill.md

docs

Skill12 starsChanged 39 days agoMITView on GitHub

Pre-built skills for AI coding assistants working with Arc Create and modify Arc architecture diagrams. Location: skills/arc-diagrams/SKILL.md Trigger: When user asks to create, edit, or work with architecture diagrams Capabilities: - Generate ArcDiagramData from natural language descriptions - Add/remove/modify nodes and connectors - Apply themes and styling - Use autoLayout to avoid hand-positioning - Convert between JSON and TypeScript formats Context to provide: Develop and debug the Arc editor codebase. Trigger: When working on Arc editor source code Context to…

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 130 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create and modify Arc architecture diagrams.

    line 9
  2. Distinctive:

    Trigger: When user asks to create, edit, or work with architecture diagrams

    line 13
  3. Very specific:

    Add/remove/modify nodes and connectors

    line 17
  4. Very specific:

    Use autoLayout to avoid hand-positioning

    line 19
  5. Distinctive:

    Trigger: When working on Arc editor source code

    line 42
  6. Distinctive:

    Trigger: When user wants to export or integrate Arc diagrams

    line 71

“Common” is measured: kept by at least 6 in 10 of the 130 edited versions of this file we could read. “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

Arc Skills

Pre-built skills for AI coding assistants working with Arc

Available Skills

arc-diagrams

Create and modify Arc architecture diagrams.

Location: skills/arc-diagrams/SKILL.md

Trigger: When user asks to create, edit, or work with architecture diagrams

Capabilities:

  • Generate ArcDiagramData from natural language descriptions
  • Add/remove/modify nodes and connectors
  • Apply themes and styling
  • Use autoLayout to avoid hand-positioning
  • Convert between JSON and TypeScript formats

Context to provide:

Arc diagram format: JSON with layout, nodes, nodeData, connectors, connectorStyles
Canonical schema: src/types/diagram.ts
JSON Schema: schemas/arc-diagram.schema.json (generated, draft-07; closed objects reject invented fields)
Validation: validateDiagram(value) -> coded Diagnostic[] with supportedFixes; MCP validate_diagram -> {ok, diagnostics}
CLI: arc check file.json --json; arc diff base.json head.json; arc render file.json --out diagram.svg --json; arc bench benchmarks/; arc schema
Valid colors: violet, emerald, blue, amber, sky, zinc, rose, orange
Valid sizes: xs, s, m, l  (NOT large/normal/small)
Valid anchors: left, right, top, bottom, topLeft, topRight, bottomLeft, bottomRight
Icons: Lucide icon names as strings (Server, Database, Monitor, Cloud, etc.)
Example: src/components/diagrams/architecture.diagram.ts

arc-editor-dev

Develop and debug the Arc editor codebase.

Trigger: When working on Arc editor source code

Context to provide:

Read CLAUDE.md first (repo root).

Arc Editor Structure:
- Routes: src/App.tsx
- Shell: src/apps/arc-editor/ (Hudson wrapper)
- Canvas: src/components/editor/ (DiagramCanvas, editorReducer.ts)
- State: EditorProvider.tsx + editorReducer.ts (useReducer)
- Schema: src/types/diagram.ts
- Validation: src/utils/diagramValidation.ts
- Icons: src/utils/iconRegistry.ts
- Sizes: src/utils/constants.ts (NODE_SIZES: xs/s/m/l)

Commands: bun run dev | bun run build | bun run lint | bun run typecheck
Stack: React 19, Vite 7, TailwindCSS 4, Hudson shell, Lucide icons

Reducer actions: docs/agent/editor-actions.agent.md
Visual verification: docs/agent/verification.agent.md

arc-export

Export Arc diagrams to various formats.

Trigger: When user wants to export or integrate Arc diagrams

Capabilities:

  • Export to TypeScript with proper types
  • Generate React component code
  • Render ASCII via renderAscii() or bin/arc-ascii.mjs
  • Render MCP SVG/PNG via render_svg and render_png (PNG needs Chrome/Chromium or ARC_CHROME; flowTime samples flow animations)
  • Render GIF/MP4 flow animations via render_animation (Chrome/Chromium plus ffmpeg)
  • Emit React component, iframe embed, or standalone HTML via render_html
  • Prepare diagrams for documentation sites

Example output (TypeScript):

import type { ArcDiagramData } from '@arach/arc'

export const systemArchitecture: ArcDiagramData = {
  layout: { width: 700, height: 400 },
  nodes: { /* x, y, size: 'm' */ },
  nodeData: { /* name, kind: 'backend' — or explicit icon/color overrides */ },
  connectors: [ /* ... */ ],
  connectorStyles: { /* ... */ }
}

Installing Skills

Install Arc's diagram skill with the open Skills CLI:

npx skills add arach/arc --skill arc-diagrams

The installer detects supported coding agents and places the skill in their expected project directories.

Manual setup

Point agents at:

  • CLAUDE.md — full contributor context
  • docs/llm.txt — dense briefing
  • skills/arc-diagrams/SKILL.md — diagram generation

Generic LLM

Copy docs/llm.txt or fetch /llms.txt from a running dev server.


Prompt Templates

See docs/prompts/:

  • create-diagram.md — generate from description
  • add-node.md — modify existing diagram
  • export-diagram.md — export workflows
  • debug-editor.md — editor debugging
  • modify-styling.md — themes and styling

MCP

Available via the arc-mcp bin on @arach/arc-mcp. See docs/agent/mcp.agent.md.

Download now (ZIP)

  • Other versions161 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. hudsonkit/arc★ 1378% same

    Wrote their own version · 160

    1. remotion-dev/remotion★ 67ksame name
    2. PrefectHQ/fastmcp★ 28ksame name
    3. jlowin/fastmcp★ 28ksame name
    4. ryoppippi/ccusage★ 19ksame name
    5. ccusage/ccusage★ 19ksame name
    6. micronaut-projects/micronaut-core★ 6.4ksame name
    7. latitude-dev/latitude-llm★ 4.7ksame name
    8. samuelgursky/davinci-resolve-mcp★ 3.7ksame name
    9. TanStack/ai★ 3.2ksame name
    10. patrykandpatrick/vico★ 3.2ksame name

    150 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use build-fix, work and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • diego-tobalinaSkill

      build-fix

      Fix build and compilation errors systematically. Run when build fails.

      Also in 3 projects that use this

    • vbrevikSkill

      work

      Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

      Also in 8 projects that use this

    • MicrosoftSkill

      perf

      Speed and memory performance rules for Rust crates, the Node addon, webui-framework, and webui-router.

      Also in 3 projects that use this

    • AWSSkill

      issue

      Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

      Also in 5 projects that use this

    • Google CloudSkill

      fix

      Plan a remediation strategy after a test failure.

      Also in 7 projects that use this

    • AnthropicSkill

      debug

      Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

      Also in 18 projects that use this

  • In this repository5 other files it gives its agents.

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.