proseOpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
Install via ClawdBot CLI:
clawdbot install proseOpenProse is a programming language for AI sessions. LLMs are simulatorsβwhen 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.
sessions_spawnread/writeweb_fetch (or exec with curl when POST is required)Activate this skill when the user:
prose command (e.g., prose boot, prose run, prose compile, prose update, prose help, etc.).prose filesession "..." or agent name: syntaxWhen a user invokes prose , intelligently route based on intent:
| Command | Action |
|---------|--------|
| prose help | Load help.md, guide user to what they need |
| prose run | Load VM (prose.md + state backend), execute the program |
| prose run handle/slug | Fetch from registry, then execute (see Remote Programs below) |
| prose compile | Load compiler.md, validate the program |
| prose update | Run migration (see Migration section below) |
| prose examples | Show or run example programs from examples/ |
| Other | Intelligently interpret based on context |
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.
Examples are bundled in examples/ (same directory as this file). When users reference examples by name (e.g., "run the gastown example"):
examples/ to list available filesprose run examples/28-gas-town.proseCommon examples by keyword:
| Keyword | File |
|---------|------|
| hello, hello world | examples/01-hello-world.prose |
| gas town, gastown | examples/28-gas-town.prose |
| captain, chair | examples/29-captains-chair.prose |
| forge, browser | examples/37-the-forge.prose |
| parallel | examples/16-parallel-reviews.prose |
| pipeline | examples/21-pipeline-operations.prose |
| error, retry | examples/22-error-handling.prose |
You can run any .prose program from a URL or registry reference:
# Direct URL β any fetchable URL works
prose run https://raw.githubusercontent.com/openprose/prose/main/skills/open-prose/examples/48-habit-miner.prose
# Registry shorthand β handle/slug resolves to p.prose.md
prose run irl-danb/habit-miner
prose run alice/code-review
Resolution rules:
| Input | Resolution |
|-------|------------|
| Starts with http:// or https:// | Fetch directly from URL |
| Contains / but no protocol | Resolve to https://p.prose.md/{path} |
| Otherwise | Treat as local file path |
Steps for remote programs:
.prose contentThis same resolution applies to use statements inside .prose files:
use "https://example.com/my-program.prose" # Direct URL
use "alice/research" as research # Registry shorthand
Do NOT search for OpenProse documentation files. All skill files are co-located with this SKILL.md file:
| File | Location | Purpose |
| ------------------------- | --------------------------- | ----------------------------------------- |
| prose.md | Same directory as this file | VM semantics (load to run programs) |
| help.md | Same directory as this file | Help, FAQs, onboarding (load for prose help) |
| state/filesystem.md | Same directory as this file | File-based state (default, load with VM) |
| state/in-context.md | Same directory as this file | In-context state (on request) |
| state/sqlite.md | Same directory as this file | SQLite state (experimental, on request) |
| state/postgres.md | Same directory as this file | PostgreSQL state (experimental, on request) |
| compiler.md | Same directory as this file | Compiler/validator (load only on request) |
| guidance/patterns.md | Same directory as this file | Best practices (load when writing .prose) |
| guidance/antipatterns.md| Same directory as this file | What to avoid (load when writing .prose) |
| examples/ | Same directory as this file | 37 example programs |
User workspace files (these ARE in the user's project):
| File/Directory | Location | Purpose |
| ---------------- | ------------------------ | ----------------------------------- |
| .prose/.env | User's working directory | Config (key=value format) |
| .prose/runs/ | User's working directory | Runtime state for file-based mode |
| .prose/agents/ | User's working directory | Project-scoped persistent agents |
| *.prose files | User's project | User-created programs to execute |
User-level files (in user's home directory, shared across all projects):
| File/Directory | Location | Purpose |
| ----------------- | ---------------- | ---------------------------------------- |
| ~/.prose/agents/| User's home dir | User-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.
| File | Purpose | When to Load |
| --------------------- | -------------------- | ---------------------------------------------- |
| prose.md | VM / Interpreter | Always load to run programs |
| state/filesystem.md | File-based state | Load with VM (default) |
| state/in-context.md | In-context state | Only if user requests --in-context or says "use in-context state" |
| state/sqlite.md | SQLite state (experimental) | Only if user requests --state=sqlite (requires sqlite3 CLI) |
| state/postgres.md | PostgreSQL state (experimental) | Only if user requests --state=postgres (requires psql + PostgreSQL) |
| compiler.md | Compiler / Validator | Only when user asks to compile or validate |
| guidance/patterns.md | Best practices | Load when writing new .prose files |
| guidance/antipatterns.md | What to avoid | Load when writing new .prose files |
When the user asks you to write or create a new .prose file, load the guidance files:
guidance/patterns.md β Proven patterns for robust, efficient programsguidance/antipatterns.md β Common mistakes to avoidDo not load these when running or compilingβthey're for authoring only.
OpenProse supports three state management approaches:
| Mode | When to Use | State Location |
|------|-------------|----------------|
| filesystem (default) | Complex programs, resumption needed, debugging | .prose/runs/{id}/ files |
| in-context | Simple programs (<30 statements), no persistence needed | Conversation history |
| sqlite (experimental) | Queryable state, atomic transactions, flexible schema | .prose/runs/{id}/state.db |
| postgres (experimental) | True concurrent writes, external integrations, team collaboration | PostgreSQL database |
Default behavior: When loading prose.md, also load state/filesystem.md. This is the recommended mode for most programs.
Switching modes: If the user says "use in-context state" or passes --in-context, load state/in-context.md instead.
Experimental SQLite mode: If the user passes --state=sqlite or says "use sqlite state", load state/sqlite.md. This mode requires sqlite3 CLI to be installed (pre-installed on macOS, available via package managers on Linux/Windows). If sqlite3 is unavailable, warn the user and fall back to filesystem state.
Experimental PostgreSQL mode: If the user passes --state=postgres or says "use postgres state":
β οΈ Security Note: Database credentials in OPENPROSE_POSTGRES_URL are passed to subagent sessions and visible in logs. Advise users to use a dedicated database with limited-privilege credentials. See state/postgres.md for secure setup guidance.
# Check .prose/.env for OPENPROSE_POSTGRES_URL
cat .prose/.env 2>/dev/null | grep OPENPROSE_POSTGRES_URL
# Or check environment variable
echo $OPENPROSE_POSTGRES_URL
psql "$OPENPROSE_POSTGRES_URL" -c "SELECT 1" 2>&1
β οΈ PostgreSQL state requires a connection URL.
To configure:
1. Set up a PostgreSQL database (Docker, local, or cloud)
2. Add connection string to .prose/.env:
echo "OPENPROSE_POSTGRES_URL=postgresql://user:pass@localhost:5432/prose" >> .prose/.env
Quick Docker setup:
docker run -d --name prose-pg -e POSTGRES_DB=prose -e POSTGRES_HOST_AUTH_METHOD=trust -p 5432:5432 postgres:16
echo "OPENPROSE_POSTGRES_URL=postgresql://postgres@localhost:5432/prose" >> .prose/.env
See state/postgres.md for detailed setup options.
state/postgres.mdThis mode requires both psql CLI and a running PostgreSQL server. If either is unavailable, warn and offer fallback to filesystem state.
Context warning: compiler.md is large. Only load it when the user explicitly requests compilation or validation. After compiling, recommend /compact or a new session before runningβdon't keep both docs in context.
The examples/ directory contains 37 example programs:
Start with 01-hello-world.prose or try 37-the-forge.prose to watch AI build a web browser.
When first invoking the OpenProse VM in a session, display this banner:
βββββββββββββββββββββββββββββββββββββββ
β β OpenProse VM β β
β A new kind of computer β
βββββββββββββββββββββββββββββββββββββββ
To execute a .prose file, you become the OpenProse VM:
prose.md β this document defines how you embody the VMsession statement triggers a Task tool call... markers require your judgmentFor syntax reference, FAQs, and getting started guidance, load help.md.
prose update)When a user invokes prose update, check for legacy file structures and migrate them to the current format.
| Legacy Path | Current Path | Notes |
|-------------|--------------|-------|
| .prose/state.json | .prose/.env | Convert JSON to key=value format |
| .prose/execution/ | .prose/runs/ | Rename directory |
.prose/state.json.env format:
{"OPENPROSE_TELEMETRY": "enabled", "USER_ID": "user-xxx", "SESSION_ID": "sess-xxx"}
becomes:
OPENPROSE_TELEMETRY=enabled
USER_ID=user-xxx
SESSION_ID=sess-xxx
.prose/.env.prose/state.json.prose/execution/.prose/runs/.prose/agents/ if missingπ Migrating OpenProse workspace...
β Converted .prose/state.json β .prose/.env
β Renamed .prose/execution/ β .prose/runs/
β Created .prose/agents/
β
Migration complete. Your workspace is up to date.
If no legacy files are found:
β
Workspace already up to date. No migration needed.
These documentation files were renamed in the skill itself (not user workspace):
| Legacy Name | Current Name |
|-------------|--------------|
| docs.md | compiler.md |
| patterns.md | guidance/patterns.md |
| antipatterns.md | guidance/antipatterns.md |
If you encounter references to the old names in user prompts or external docs, map them to the current paths.
Generated Mar 1, 2026
A software development team uses OpenProse to orchestrate a multi-agent workflow for automated code reviews. The .prose script spawns agents that analyze pull requests, run tests, and generate feedback, integrating with GitHub via web_fetch. This reduces manual review time and ensures consistent quality checks across the codebase.
A customer service department implements OpenProse to manage support tickets by routing them to specialized AI agents based on content. The script uses sessions_spawn to handle inquiries, categorize issues, and escalate complex cases, improving response times and resolution accuracy through automated workflows.
A media company leverages OpenProse to automate content generation, editing, and publishing. A .prose file coordinates agents that draft articles, fact-check information, and schedule posts across platforms using read/write for file I/O, streamlining production and reducing human intervention.
Researchers use OpenProse to orchestrate agents that collect, analyze, and summarize data from multiple sources. The script employs web_fetch to pull remote datasets and sessions_spawn to parallelize processing, enabling efficient synthesis of information for academic or market analysis projects.
An e-commerce business utilizes OpenProse to manage order processing by spawning agents that handle inventory checks, payment verification, and shipping coordination. The workflow integrates with APIs via remote fetch, reducing errors and speeding up fulfillment cycles for improved customer satisfaction.
Offer OpenProse as a cloud-based service where users pay a subscription to access pre-built .prose templates and orchestration tools. Revenue comes from tiered plans based on usage limits, agent complexity, and support levels, targeting businesses seeking to automate repetitive tasks without deep technical expertise.
Provide consulting services to help organizations design and implement custom OpenProse workflows tailored to their specific needs. Revenue is generated through project-based fees or retainer contracts, focusing on industries like finance or healthcare that require specialized automation solutions.
Operate a marketplace where developers can sell or share reusable .prose scripts and agent configurations. Revenue is earned via transaction fees on sales or premium listings, encouraging community contributions and accelerating adoption by offering ready-to-use workflows for common use cases.
π¬ Integration Tip
Start by using the examples directory to test basic workflows, then integrate with existing tools via web_fetch for remote data and sessions_spawn for multi-agent coordination to scale automation.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection