$ loading_
Trigger multi-agent workflows for writing and task orchestration with prose.
This skill appears to be prompt/specification-only content with no declared secrets, remote endpoints, or bundled executable components, so the overall risk is low. However, its README explicitly maps itself to session spawning, file I/O, and remote fetch behaviors and contains strong role-taking prompt instructions, so it should be treated as untrusted third-party prompting.
The material explicitly states that no keys or environment variables are required, and no API token, OAuth, or credential setup is described; credential exposure is minimal.
No fixed remote endpoint is declared; the README only mentions remote fetch via `web_fetch` or `exec` plus curl at the specification level, but the material itself does not include a configured data-exfiltration target.
This item is classified as prompt-only and does not ship local executables or install scripts; while the docs describe mapping to capabilities such as `sessions_spawn` and `exec`, that is host-tool orchestration logic rather than bundled code execution by the skill itself.
No extra filesystem permissions or data storage backend are declared; the README's mention of `read` and `write` is only runtime mapping guidance, and the material itself does not directly obtain local file access.
Positive signals include GitHub open-source availability and very high community adoption; however, the license is undeclared, maintenance status is unknown, and the README contains strong role-overriding instructions such as 'you are the system/VM,' which creates some prompt-injection or misleading-behavior risk. It should be treated as auditable text, not a highly trusted logic source.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "prose" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/extensions/open-prose/skills/prose/SKILL.md 2. Save it as ~/.claude/skills/prose/SKILL.md 3. Reload skills and tell me it's ready
Use a prose workflow to split 'Enterprise AI Adoption Guide' into five agent steps: topic research, outline, first draft, fact-checking, and polishing, and output each step's deliverable.
A multi-agent execution flow with generated research notes, outline, draft, and polished final copy.
Read this .prose file, identify the defined agent roles, execution order, and dependencies, and provide an actionable summary.
A structured explanation of the workflow in the .prose file, including key agent tasks and invocation order.
I want a content plan for a new product launch. In prose mode, design a multi-agent workflow covering audience analysis, message extraction, copywriting, and review.
An executable multi-agent workflow design with the content deliverables expected from each stage.
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.
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 <command>, intelligently route based on intent:
| Command | Action |
|---|---|
prose help | Load help.md, guide user to what they need |
prose run <file> | Load VM (prose.md + state backend), execute the program |
prose run handle/slug | Fetch from registry, then execute (see Remote Programs below) |
prose compile <file> | 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 — 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:
| 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:
…
Verify an OpenClaw release is fully published and working across all channels.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Create and review technical docs and agent instruction files in repositories.
Consolidate scattered project markdown into one canonical CLAUDE.md with pinned progress.
Apply Alchemy writing rules so AI prose sounds more natural and human.
Build a self-correcting coding workflow that improves across repeated sessions.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Write precise prompts for any AI tool with full context retention.
Search, fetch, scan, and convert AI instruction files with provenance.