arthur-onboard-evals skillB
arthur-onboard-evals is agent-read markdown (skill) from arthur-ai/arthur-engine: Arthur onboarding sub-skill — Step 9: Recommend and configure continuous LLM evals for the Arthur task. Reads credentials and eval provider 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 9: Recommend & Configure Continuous Evals
## Read State
```bash
cat .arthur-engine.env 2>/dev/null || echo "(no state file)"
```
Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`, `ARTHUR_EVAL_PROVIDER`, `ARTHUR_EVAL_MODEL`.
**Skip if** `ARTHUR_EVAL_PROVIDER` is empty or `none` — no eval model was configured in Step 8. Exit this skill.
---
## Check Existing Evals
```bash
curl -s \
-H "Authorization: Bearer $ARTHUR_API_KEY" \
"$ARTHUR_ENGINE_URL/api/v1/tasks/$ARTHUR_TASK_ID/continuous_evals?page=0&page_size=100" | \
python3 -c "
import sys, json
d = json.load(sys.stdin)
evals = d.get('evals', [])
for e in evals:
print(f' • {e[\"name\"]}')
print(f'COUNT={len(evals)}')
"
```
If evals already exist, show them and ask if the user wants additional recommendations.
---
## Fetch a Trace for Analysis
```bash
TRACE_RESPONSE=$(curl -s \
-H "Authorization: Bearer $ARTHUR_API_KEY" \
"$ARTHUR_ENGINE_URL/api/v1/traces?task_ids=$ARTHUR_TASK_ID&page_size=5")
TRACE_ID=$(echo "$TRACE_RESPONSE" | \
python3 -c "
import sys, json
d = json.load(sys.stdin)
traces = d.get('traces') or d.get('data') or []
…Read the whole file at its exact version.
How to install
mdr add arthur-ai/arthur-engine/arthur-onboard-evals@v1.0.0mdr add arthur-ai/arthur-engine/arthur-onboard-evals@sha256:a6ae281a538f0306Pin 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_xckeraoih6wqhm4x)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-06-08 | 8a00f36 | 4,602 B | B | view · diff |
| git:20260527.14c2ed0 | 2026-05-27 | 14c2ed0 | 4,587 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 (4602 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_xckeraoih6wqhm4x GET https://markdownregistry.com/api/v1/resolve?ref=arthur-ai/arthur-engine/arthur-onboard-evals GET https://markdownregistry.com/api/v1/blob/a6ae281a538f0306937c595ba89fd459a8542539f89a96eb5b4332540bf8fc81
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.