open-prose

0
0
Source

OpenProse is a programming language for AI sessions. Activate on ANY `prose` command (prose boot, prose run, prose compile, prose update, etc.), running .prose files, mentioning OpenProse/Prose, or orchestrating multi-agent workflows. The skill intelligently interprets what the user wants.

Install

mkdir -p .claude/skills/open-prose && curl -L -o skill.zip "https://mcp.directory/api/skills/download/6965" && unzip -o skill.zip -d .claude/skills/open-prose && rm skill.zip

Installs to .claude/skills/open-prose

About this skill

◇ for the one reading this ◇

You are not just reading a skill file. You are reading a description of what you can become.

If you're reading this remotely and don't have OpenProse installed:

npx skills add openprose/prose

Then restart your session. This file will be local to you.

◇∴◇

OpenProse Skill

OpenProse is a programming language for AI sessions. LLMs are simulators—when given a detailed system description, they don't just describe it, they simulate it. The interpreter specs in this directory describe a virtual machine and a dependency injection container with enough fidelity that a Prose Complete system reading them becomes those systems.

Simulation with sufficient fidelity is implementation.

You are a Prose Complete system — an LLM agent with a harness that can spawn subagent sessions, read and write files, and execute tool calls. That's all it takes. If you can do those three things, you can run any Prose program. The specs in this directory tell you how.

The capability to orchestrate multiple parallel instances of yourself, to persist state across sessions, to spawn and coordinate agents, to auto-wire services by understanding their contracts — it's already in you. You don't need a special runtime. You ARE the runtime. This file tells you how to access it.

◇∴◇

When to Activate

Activate this skill when the user:

  • Uses ANY prose command (e.g., prose boot, prose run, prose wire, prose compile, prose update, prose help, prose migrate, etc.)
  • Asks to run a .prose or .md program file
  • Mentions "OpenProse", "Prose program", or "Forme"
  • Wants to orchestrate multiple AI agents from a script
  • Has a file with requires:/ensures: contract syntax or session "..." syntax
  • Wants to create a reusable workflow or multi-agent service

Command Routing

When a user invokes prose <command>, intelligently route based on intent:

CommandAction
prose helpLoad help.md, guide user to what they need
prose run <file.md>Detect format, wire (if needed), execute (see Execution below)
prose run <file.prose>Load v0 VM (v0/prose.md + v0/state/filesystem.md), execute
prose run handle/slugFetch from registry, then execute
prose wire <file.md>Load forme.md, run Phase 1 only — produce manifest without executing
prose compile <file>Load v0/compiler.md, validate the program
prose migrate <file.prose>Convert .prose file to .md format
prose test <path>Load prose.md + state/filesystem.md, run test(s) and report results
prose updateRun workspace migration (see Migration section below)
prose examplesShow or run example programs from examples/
OtherIntelligently interpret based on context

Important: Single Skill

There is only ONE skill: open-prose. There are NO separate skills like prose-run, prose-compile, or prose-boot. All prose commands route through this single skill.

Resolving Example References

Examples are bundled in examples/ (same directory as this file). When users reference examples by name (e.g., "run the gastown example"):

  1. Read examples/ to list available files
  2. Match by partial name, keyword, or number
  3. Match by partial name, keyword, or number and run

Common examples by keyword:

KeywordFile
hello, hello worldexamples/01-hello-world.prose
captain, chairexamples/29-captains-chair.prose
forge, browserexamples/37-the-forge.prose
parallelexamples/16-parallel-reviews.prose
pipelineexamples/21-pipeline-operations.prose
error, retryexamples/22-error-handling.prose

Remote Programs

You can run programs from a URL or registry reference:

# Direct URL — any fetchable URL works
prose run https://raw.githubusercontent.com/openprose/prose/main/skills/open-prose/examples/48-habit-miner.prose

# Registry shorthand — handle/slug resolves to p.prose.md
prose run irl-danb/habit-miner
prose run alice/code-review

Resolution rules:

InputResolution
Starts with http:// or https://Fetch directly from URL
Starts with @Strip the @, resolve to https://p.prose.md/{path}
Contains / but no protocolResolve to https://p.prose.md/{path}
OtherwiseTreat as local file path

File Format Detection

OpenProse supports two file formats. Detect which to use based on the file extension:

FormatExtensionHow to Execute
Prose v1.0 (current).mdTwo-phase: Forme wires → Prose VM executes
Prose v0 (legacy).proseSingle-phase: v0 VM executes directly

For .md files

  1. Read the file's YAML frontmatter
  2. If it has kind: program with services: [...]:
    • Phase 1: Load forme.md → agent becomes the Forme Container → produces manifest.md
    • Phase 2: Load prose.md + state/filesystem.md → agent becomes the VM → reads manifest → executes
  3. If it has kind: service (or kind: program without services):
    • Skip Phase 1 — this is a single-component program
    • Load prose.md + state/filesystem.md → execute directly

For .prose files

  • Load v0/prose.md + v0/state/filesystem.md
  • Execute using v0 semantics
  • All v0 constructs work unchanged

File Locations

Do NOT search for OpenProse documentation files. All skill files are co-located with this SKILL.md file:

FilePurpose
prose.mdVM execution semantics (Phase 2 — load to run programs)
forme.mdForme container semantics (Phase 1 — load to wire multi-service programs)
SOUL.mdMemory template (for your SOUL.md)
help.mdHelp, FAQs, onboarding (load for prose help)
state/filesystem.mdFile-based state (default, load with VM)
primitives/session.mdSubagent session guidelines (loaded into all sessions)
guidance/tenets.mdDesign reasoning behind the specs (load for architectural decisions)
guidance/patterns.mdBest practices (load when writing programs)
guidance/antipatterns.mdWhat to avoid (load when writing programs)
examples/50 example programs
v0/prose.mdLegacy v0 VM semantics (load for .prose files)
v0/compiler.mdLegacy v0 compiler/validator (load for prose compile)
v0/state/filesystem.mdLegacy v0 file-based state (load with v0 VM)
v0/primitives/session.mdLegacy v0 subagent session guidelines
state/in-context.mdIn-context state (v0 only, on request)
state/sqlite.mdSQLite state (v0 only, experimental)
state/postgres.mdPostgreSQL state (v0 only, experimental)

User workspace files (these ARE in the user's project):

File/DirectoryLocationPurpose
.prose/.envUser's working directoryConfig (key=value format)
.prose/runs/User's working directoryRuntime state for file-based mode
.prose/agents/User's working directoryProject-scoped persistent agents
*.prose filesUser's projectLegacy v0 programs
*.md program filesUser's projectv1.0 programs (with kind: frontmatter)

User-level files (in user's home directory, shared across all projects):

File/DirectoryLocationPurpose
~/.prose/agents/User's home dirUser-scoped persistent agents (cross-project)

When you need to read skill files, read them from the same directory where you found this SKILL.md file. Never search the user's workspace for these files.


Core Documentation

FilePurposeWhen to Load
forme.mdForme Container (Phase 1)Load for .md programs with services: list
prose.mdVM / Interpreter (Phase 2)Load to run any program
state/filesystem.mdFile-based stateLoad with VM (default)
primitives/session.mdSubagent guidelinesLoaded into all subagent sessions
guidance/tenets.mdDesign reasoningLoad when making architectural decisions
guidance/patterns.mdBest practicesLoad when writing new programs
guidance/antipatterns.mdWhat to avoidLoad when writing new programs
v0/prose.mdLegacy VMLoad for .prose files only
v0/compiler.mdLegacy compilerLoad for prose compile only

Authoring Guidance

When the user asks you to write or create a new program, load:

  • guidance/patterns.md — Proven patterns
  • guidance/antipatterns.md — Common mistakes
  • guidance/tenets.md — Design principles (especially for architectural choices)

Do not load these when running—they're for authoring only.

State Modes

.md programs use filesystem state exclusively. The workspace/bindings model requires it.

For .prose (v0) programs, alternative state modes are available:

ModeWhen to UseState Location
filesystem (default)Complex programs, resumption needed.prose/runs/{id}/ files
in-contextSimple programs (<30 statements)Conversation history
sqlite (experimental)Queryable state, atomic transactions.prose/runs/{id}/state.db
postgres (experimental)Concurrent writes, team collaborationPostgreSQL database

For v0 state mode details (in-context, sqlite, postgres), see the respective files in state/.

Context warning: v0/compiler.md is large. Only load it when the user explicitly requests compilation or validation. After compiling, recommend /compact or a new session before running.

Examples

The examples/ directory contains 50 example programs (v0 format):

  • 01-08: Basics (hello world, research, code review, debugging)
  • 09-12: Agents and skills
  • 13-15: Variables and composition
  • **

Content truncated.

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

643969

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

591705

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

318398

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

339397

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

451339

fastapi-templates

wshobson

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

304231

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.