arthur-ai/integrations/claude-code-skills/arthur-onboard/arthur-onboard-eval-provider
integrations/claude-code-skills/arthur-onboard/arthur-onboard-eval-provider/SKILL.md
--- name: arthur-onboard-eval-provider description: Arthur onboarding sub-skill — Step 8: Configure an LLM provider for continuous evals (OpenAI, Anthropic, Gemini, Bedrock, or Vertex AI). Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write --- # Arthur Onboard — Step 8: Configure Eval Model Provider ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL` and `ARTHUR_API_KEY`. --- ## Check Existing Providers ```bash cu
$ install --global
skillsauthnpx skillsauth add arthur-ai/arthur-engine integrations/claude-code-skills/arthur-onboard/arthur-onboard-eval-providerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 28, 2026, 3:39 AM40.1s1 file scanned
SKILL.md
- name:
- arthur-onboard-eval-provider
- description:
- Arthur onboarding sub-skill — Step 8: Configure an LLM provider for continuous evals (OpenAI, Anthropic, Gemini, Bedrock, or Vertex AI). Reads/writes .arthur-engine.env.
- allowed-tools:
- Bash, Read, Write
Arthur Onboard — Step 8: Configure Eval Model Provider
Read State
cat .arthur-engine.env 2>/dev/null || echo "(no state file)"
Parse ARTHUR_ENGINE_URL and ARTHUR_API_KEY.
Check Existing Providers
curl -s \
-H "Authorization: Bearer $ARTHUR_API_KEY" \
"$ARTHUR_ENGINE_URL/api/v1/model_providers" | \
python3 -c "
import sys, json
d = json.load(sys.stdin)
for p in d.get('providers', []):
print(f'{p[\"provider\"]}: enabled={p[\"enabled\"]}')
"
If an enabled provider exists: Use it (prefer OpenAI > Anthropic > Gemini > Bedrock > Vertex AI). Write ARTHUR_EVAL_PROVIDER and ARTHUR_EVAL_MODEL to the state file, then exit this skill.
If No Provider Enabled
Ask user to choose:
openai→ modelgpt-4oanthropic→ modelclaude-3-5-haiku-20241022gemini→ modelgemini-1.5-flashbedrock→ modelanthropic.claude-3-haiku-20240307-v1:0vertex_ai→ modelgemini-1.5-flash- Skip → configure in the Arthur Engine UI later (write
ARTHUR_EVAL_PROVIDER=noneto state, then exit)
If a provider is chosen, show the user this message and wait for their confirmation (do not ask them to type the key in chat; do not run getpass via the Bash tool — it has no TTY):
Please run this to securely enter your
<Provider>API key (replace<Provider>with the actual provider name in the prompt):
! python3 -c "import getpass, os, stat; p=os.path.expanduser('~/.ae_tmp_key'); key=getpass.getpass('<Provider> API key (hidden): '); open(p,'w').write(key); os.chmod(p, 0o600); print('Key saved.')"Let me know when done.
Then read the key from the temp file and configure:
PROVIDER_API_KEY=$(cat ~/.ae_tmp_key && rm -f ~/.ae_tmp_key)
curl -s -X PUT \
-H "Authorization: Bearer $ARTHUR_API_KEY" \
-H "Content-Type: application/json" \
-d "{\"api_key\": \"$PROVIDER_API_KEY\"}" \
"$ARTHUR_ENGINE_URL/api/v1/model_providers/$PROVIDER"
Write ARTHUR_EVAL_PROVIDER and ARTHUR_EVAL_MODEL to .arthur-engine.env:
STATE_FILE=".arthur-engine.env"
grep -v '^ARTHUR_EVAL_PROVIDER=\|^ARTHUR_EVAL_MODEL=' \
"$STATE_FILE" 2>/dev/null > /tmp/ae_env_tmp && mv /tmp/ae_env_tmp "$STATE_FILE" || true
echo "ARTHUR_EVAL_PROVIDER=$PROVIDER" >> "$STATE_FILE"
echo "ARTHUR_EVAL_MODEL=$MODEL" >> "$STATE_FILE"
Related Skills
arthur-ai/integrations/claude-code-skills/arthur-onboard/arthur-onboard-verify
tools
VerifiedTrustedCommunity
--- name: arthur-onboard-verify description: Arthur onboarding sub-skill — Step 7: Verify that traces are flowing from the instrumented application to Arthur Engine. Reads credentials from .arthur-engine.env. allowed-tools: Bash, Read --- # Arthur Onboard — Step 7: Verify Instrumentation ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`. --- ## Tell the User to Run Their Application Show the
81SKILL.mdUpdated May 28, 2026
arthur-ai/integrations/claude-code-skills/arthur-onboard/arthur-onboard-task
tools
VerifiedTrustedCommunity
--- name: arthur-onboard-task description: Arthur onboarding sub-skill — Step 3: Set up an Arthur Task (create or select). Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write, Edit --- # Arthur Onboard — Step 3: Set Up Arthur Task **Goal:** Establish `ARTHUR_TASK_ID` in `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, and `ARTHUR_TASK_ID` from the output. **State write hel
81SKILL.mdUpdated May 28, 2026
arthur-ai/integrations/claude-code-skills/arthur-onboard/arthur-onboard-prompts
tools
VerifiedTrustedCommunity
--- name: arthur-onboard-prompts description: Arthur onboarding sub-skill — Step 6: Extract prompts from the target repository and register them with Arthur Engine. Reads credentials from .arthur-engine.env. allowed-tools: Bash, Read, Task --- # 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
81SKILL.mdUpdated May 28, 2026
arthur-ai/arthur-onboard-platform
development
VerifiedTrustedCommunity
Onboard an agentic application to the Arthur SaaS Platform (platform.arthur.ai). Guides through authentication, workspace selection, engine deployment, model creation, code instrumentation, trace verification, and eval configuration.
81SKILL.mdUpdated May 28, 2026