arthur-onboard-prompts skillB
arthur-onboard-prompts is agent-read markdown (skill) from arthur-ai/arthur-engine: Arthur onboarding sub-skill — Step 6: Extract prompts from the target repository and register them with Arthur Engine. Reads credentials from .arthur-engine.env..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Arthur Onboard — Step 6: Extract & Register Prompts
## Read State
```bash
cat .arthur-engine.env 2>/dev/null || echo "(no state file)"
```
Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`.
---
## Extract Prompts via Sub-agent
Delegate to a Task sub-agent (full claude agent) to find prompts in the repo:
```
Analyze the agentic application at: <REPO_PATH>
Use Read, Glob (find), and Grep to find all prompt definitions:
- System prompt strings assigned to variables (any language)
- User prompt templates with variables
- Multi-turn message arrays in OpenAI format ([{"role": "system", ...}])
- Prompt files (.txt, .md, .jinja2)
- Agent instruction strings passed to agent/chain initialization
Also detect the LLM model and provider used (from API call patterns, imports, env var names
like OPENAI_API_KEY, model= parameters, etc.).
Return ONLY a raw JSON object with no markdown, no explanation:
{
"prompts": [
{
"name": "kebab-case-unique-name",
"messages": [
{"role": "system", "content": "..."},
{"role": "user", "content": "..."}
],
"model_name": "gpt-4o" | null,
…Read the whole file at its exact version.
How to install
mdr add arthur-ai/arthur-engine/arthur-onboard-prompts@v1.0.0mdr add arthur-ai/arthur-engine/arthur-onboard-prompts@sha256:048881cfe2f6404dPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_rfzr37vncvwe3dux)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-06-08 | 8a00f36 | 2,494 B | B | view · diff |
| git:20260527.14c2ed0 | 2026-05-27 | 14c2ed0 | 2,479 B | B | view |
Audit of the latest version
- fail: No instruction to read or print local credentials (matched: cat .arthur-engine.env)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2494 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arthur-ai/arthur-engine · 90 stars · license MIT · pushed 2026-09-24 · branch dev
API
GET https://markdownregistry.com/api/v1/artifacts/art_rfzr37vncvwe3dux GET https://markdownregistry.com/api/v1/resolve?ref=arthur-ai/arthur-engine/arthur-onboard-prompts GET https://markdownregistry.com/api/v1/blob/048881cfe2f6404d6402cfe1488f5da32a030522409391e5f5f28085165bf42b
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.