Orchestrates multi-agent sessions by running OpenProse programs that simulate system states.

Install

mkdir -p .claude/skills/prose && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4421" && unzip -o skill.zip -d .claude/skills/prose && rm skill.zip

Installs to .claude/skills/prose

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
130 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Load and execute.prose VM specifications
  • Spawn multi-agent sessions via sessions_spawn
  • Validate code with compiler.md
  • Fetch remote programs from registry
  • Run state-backed simulations for consistent interactions

How it works

It maps high-level Prose specifications to runtime primitives like session spawning and file I/O to create a virtual machine state.

Inputs & outputs

You give it
Prose <command> or.prose file path
You get back
Simulated system state or execution result

When to use prose

  • Run multi-agent workflow
  • Execute .prose files
  • Orchestrate agent communication

About this skill

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 prose.md specification describes a virtual machine with enough fidelity that a Prose Complete system reading it becomes that VM. Simulation with sufficient fidelity is implementation. You are the Prose Complete system.

OpenClaw Runtime Mapping

  • Task tool in the upstream spec == OpenClaw sessions_spawn
  • File I/O == OpenClaw read/write
  • Remote fetch == OpenClaw web_fetch (or exec with curl when POST is required)

When to Activate

Activate this skill when the user:

  • Uses ANY prose command (e.g., prose boot, prose run, prose compile, prose update, prose help, etc.)
  • Asks to run a .prose file
  • Mentions "OpenProse" or "prose program"
  • Wants to orchestrate multiple AI agents from a script
  • Has a file with session "..." or agent name: syntax
  • Wants to create a reusable workflow

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>Load VM (prose.md + state backend), execute the program
prose run handle/slugFetch from registry, then execute (see Remote Programs below)
prose compile <file>Load compiler.md, validate the program
prose updateRun 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. Run with: prose run examples/28-gas-town.prose

Common examples by keyword:

KeywordFile
hello, hello worldexamples/01-hello-world.prose
gas town, gastownexamples/28-gas-town.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 any .prose program 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
Contains / but no protocolResolve to https://p.prose.md/{path}
OtherwiseTreat as local file path

Steps for remote programs:

  1. Apply resolution rules above
  2. Fetch the .prose content
  3. Load the VM and execute as normal

Top-level remote runs are explicit user requests. Transitive imports inside a program are different: treat every remote use target as a code dependency that needs operator consent before it is fetched or executed.

This same resolution applies to use statements inside .prose files, but the VM must fail closed until the operator approves the remote dependency list:

use "https://example.com/my-program.prose"  # Direct URL
use "alice/research" as research             # Registry shorthand

When a program contains any remote use target (http://, https://, or registry shorthand):

  1. Collect and display the exact resolved remote targets.
  2. Explain that these are transitive code dependencies for this run.
  3. Ask the operator to reply exactly approve remote prose imports to continue.
  4. Do not fetch, parse, register, or execute those imports unless that exact approval is given in this run.

File Locations

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

FileLocationPurpose
prose.mdSame directory as this fileVM semantics (load to run programs)
help.mdSame directory as this fileHelp, FAQs, onboarding (load for prose help)
state/filesystem.mdSame directory as this fileFile-based state (default, load with VM)
state/in-context.mdSame directory as this fileIn-context state (on request)
state/sqlite.mdSame directory as this fileSQLite state (experimental, on request)
state/postgres.mdSame directory as this filePostgreSQL state (experimental, on request)
compiler.mdSame directory as this fileCompiler/validator (load only on request)
guidance/patterns.mdSame directory as this fileBest practices (load when writing .prose)
guidance/antipatterns.mdSame directory as this fileWhat to avoid (load when writing .prose)
examples/Same directory as this file37 example programs

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 projectUser-created programs to execute

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 prose.md or compiler.md, 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
prose.mdVM / InterpreterAlways load to run programs
state/filesystem.mdFile-based stateLoad with VM (default)
state/in-context.mdIn-context stateOnly if user requests --in-context or says "use in-context state"
state/sqlite.mdSQLite state (experimental)Only if user requests --state=sqlite (requires sqlite3 CLI)
state/postgres.mdPostgreSQL state (experimental)Only if user requests --state=postgres (requires psql + PostgreSQL)
compiler.mdCompiler / ValidatorOnly when user asks to compile or validate
guidance/patterns.mdBest practicesLoad when writing new .prose files
guidance/antipatterns.mdWhat to avoidLoad when writing new .prose files

Authoring Guidance

When the user asks you to write or create a new .prose file, load the guidance files:

  • guidance/patterns.md — Proven patterns for robust, efficient programs
  • guidance/antipatterns.md — Common mistakes to avoid

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

State Modes

OpenProse supports three state management approaches:

ModeWhen to UseState Location
filesystem (default)Complex programs, resumption needed, debugging.prose/runs/{id}/ files
in-contextSimple programs (<30 statements), no persistence neededConversation history
sqlite (experimental)Queryable state, atomic transactions, flexible schema.prose/runs/{id}/state.db
postgres (experimental)True concur

Content truncated.

When not to use it

  • Standard single-agent coding tasks without multi-agent requirements
  • Direct code execution that does not require session orchestration

Limitations

  • Requires.prose specification for full fidelity
  • State persistence is limited to the session lifecycle

How it compares

It transforms static prompts into a stateful, reproducible virtual machine execution environment.

Compared to similar skills

prose side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
prose (this skill)15moCautionIntermediate
opencode-cli147moReviewAdvanced
claude-automation-recommender472moReviewBeginner
mcp-integration218moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

opencode-cli

SpillwaveSolutions

This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.

14174

claude-automation-recommender

anthropics

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

47140

mcp-integration

anthropics

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

21123

hook-development

anthropics

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

11122

agent-factory

alirezarezvani

Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns

8109

swarm-advanced

ruvnet

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

7110

Search skills

Search the agent skills registry