Home / arthur-ai / arthur-engine · integrations/claude-code-skills/arthur-onboard/arthur-onboard-evals/SKILL.md · GitHub

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

Latest version
mdr add arthur-ai/arthur-engine/arthur-onboard-evals@v1.0.0
Exact content
mdr add arthur-ai/arthur-engine/arthur-onboard-evals@sha256:a6ae281a538f0306

Pin 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xckeraoih6wqhm4x.svg)](https://markdownregistry.com/a/art_xckeraoih6wqhm4x)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0.0 latest2026-06-08 8a00f36 4,602 BB view · diff
git:20260527.14c2ed02026-05-27 14c2ed0 4,587 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • 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

GitHub

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.

More from arthur-ai/arthur-engine

setup-genai-dev skill
arthur-ai/arthur-engine · .claude/skills/setup-genai-dev/SKILL.md · Set up the GenAI Engine development environment. Use when starting work on the project for the first time, or when…
git:20260407.50741a3 · audit B · 90 stars
start-genai-backend skill
arthur-ai/arthur-engine · .claude/skills/start-genai-backend/SKILL.md · Start the GenAI Engine backend server and frontend UI. Use when you need to launch the API server and the frontend…
git:20260407.50741a3 · audit B · 90 stars
start-genai-frontend skill
arthur-ai/arthur-engine · .claude/skills/start-genai-frontend/SKILL.md · Start the GenAI Engine frontend UI dev server. Use when you need to launch the React app locally.
git:20260304.0624edd · audit A · 90 stars
CLAUDE.md claude
arthur-ai/arthur-engine · CLAUDE.md
git:20260918.3b27938 · audit A · 90 stars
generate-client skill
arthur-ai/arthur-engine · arthur-observability-sdk/.claude/skills/generate-client/SKILL.md · Regenerate the arthur_genai_client package from the GenAI Engine OpenAPI spec. Use when the GenAI Engine API has…
git:20260407.50741a3 · audit A · 90 stars
test-integration skill
arthur-ai/arthur-engine · arthur-observability-sdk/.claude/skills/test-integration/SKILL.md · Run the arthur-observability-sdk integration tests. These build the SDK wheel into a fresh venv and verify OTLP…
git:20260407.50741a3 · audit A · 90 stars
test-unit skill
arthur-ai/arthur-engine · arthur-observability-sdk/.claude/skills/test-unit/SKILL.md · Run the arthur-observability-sdk unit tests. Use when you want to verify SDK logic without building a wheel or spinning…
git:20260407.50741a3 · audit A · 90 stars
update-docs skill
arthur-ai/arthur-engine · arthur-observability-sdk/.claude/skills/update-docs/SKILL.md
git:20260317.53f05ea · audit C · 90 stars
CLAUDE.md@arthur-observability-sdk claude
arthur-ai/arthur-engine · arthur-observability-sdk/CLAUDE.md
git:20260826.7bf361b · audit A · 90 stars
CLAUDE.md@genai-engine claude
arthur-ai/arthur-engine · genai-engine/CLAUDE.md
git:20260731.d2c2e65 · audit A · 90 stars
CLAUDE.md@genai-engine/ui claude
arthur-ai/arthur-engine · genai-engine/ui/CLAUDE.md
git:20260826.244ad05 · audit A · 90 stars
arthur-onboard-analyze skill
arthur-ai/arthur-engine · integrations/claude-code-skills/arthur-onboard/arthur-onboard-analyze/SKILL.md · Arthur onboarding sub-skill — Step 4: Analyze the target repository (language, framework, existing instrumentation)…
v1.0.0 · audit B · 90 stars

Every file in arthur-ai/arthur-engine

Browse by kind, by grade B, or by owner.