arthur-onboard-evals SKILL.md skillB
arthur-onboard-evals from arthur-ai/arthur-engine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arthur-ai/arthur-engine/arthur-onboard-evals@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arthur-ai/arthur-engine
- Path
integrations/claude-code-skills/arthur-onboard/arthur-onboard-evals/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Jun 8, 2026
- First version recorded
- May 27, 2026
- Size
- 4,602 bytes
- Repository stars
- 93
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file 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@sha256:a6ae281a538f0306The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xckeraoih6wqhm4x)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 27, 2026 and Jun 8, 2026, about one every 12 days.
| 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
arthur-ai/arthur-engine · 93 stars · license MIT · pushed 2026-11-09 · 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 AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.