<< All versions
Skill v1.0.0
currentLLM-judged scan90/100arthur-ai/arthur-engine/arthur-onboard-analyze
──Details
PublishedOctober 21, 2026 at 11:40 PM
Content Hashsha256:657f8d87395ec7bc...
Git SHA8a00f36f091b
──Files
Files (1 file, 1.9 KB)
SKILL.md1.9 KBactive
SKILL.md · 55 lines · 1.9 KB
name: arthur-onboard-analyze description: Arthur onboarding sub-skill — Step 4: Analyze the target repository (language, framework, existing instrumentation). Writes detection results to .arthur-engine.env. allowed-tools: Bash, Read version: 1.0.0
Arthur Onboard — Step 4: Analyze Repository
Goal: Detect language, framework, and existing instrumentation. Write results to .arthur-engine.env.
Read State
bash
cat .arthur-engine.env 2>/dev/null || echo "(no state file)"
Detection
bash
# Language detection[ -f requirements.txt ] || [ -f pyproject.toml ] && echo "PYTHON=yes"[ -f tsconfig.json ] || [ -f package.json ] && echo "NODE=yes"# Framework detectiongrep -r --include="*.py" --include="*.ts" --include="*.js" -l \"mastra\|langchain\|openai\|anthropic\|crewai\|autogen" . 2>/dev/null | head -5# Existing instrumentationgrep -r --include="*.py" --include="*.ts" --include="*.js" -l \"arthur\.instrument\|arthur_observability\|ArthurExporter\|openinference" . 2>/dev/null | head -3
Also read requirements.txt, pyproject.toml, package.json, and the likely entry point (main.py, app.py, src/mastra/index.ts, src/index.ts, etc.).
Determine:
- language:
python|typescript|javascript|unknown - framework:
mastra|langchain|openai|anthropic|crewai|other|unknown - isInstrumented: true if Arthur SDK,
@mastra/arthur, oropeninferencealready present
Write Results to State
bash
STATE_FILE=".arthur-engine.env"grep -v '^ARTHUR_DETECTED_LANGUAGE=\|^ARTHUR_DETECTED_FRAMEWORK=\|^ARTHUR_IS_INSTRUMENTED=' \"$STATE_FILE" 2>/dev/null > /tmp/ae_env_tmp && mv /tmp/ae_env_tmp "$STATE_FILE" || trueecho "ARTHUR_DETECTED_LANGUAGE=<language>" >> "$STATE_FILE"echo "ARTHUR_DETECTED_FRAMEWORK=<framework>" >> "$STATE_FILE"echo "ARTHUR_IS_INSTRUMENTED=<true|false>" >> "$STATE_FILE"
Report the detected values to the user before exiting.