azure-ai-evaluation-pyAzure AI Evaluation SDK for Python. Use for evaluating generative AI applications with quality, safety, and custom evaluators. Triggers: "azure-ai-evaluation", "evaluators", "GroundednessEvaluator", "evaluate", "AI quality metrics".
Install via ClawdBot CLI:
clawdbot install thegovind/azure-ai-evaluation-pyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"ignore previous instructions"Potentially destructive shell commands in tool definitions
eval (Uses known external API (expected, informational)
azure.comAI Analysis
The skill definition is for a legitimate Azure AI evaluation SDK and shows no evidence of hidden instructions, credential harvesting, or obfuscation. The primary risk is the standard dependency on external Azure OpenAI services for AI-assisted evaluators, which is consistent with the skill's stated purpose and requires user-provided credentials.
Generated Mar 21, 2026
Assess AI-powered customer support chatbots for accuracy and safety. Use GroundednessEvaluator to verify responses align with product documentation, and SafetyEvaluators to filter harmful content before deployment.
Evaluate medical AI assistants for factual correctness and safety. Apply RelevanceEvaluator to ensure responses address patient queries accurately, and ContentSafetyEvaluator to prevent harmful medical advice.
Validate AI financial advisors for regulatory compliance and accuracy. Use CoherenceEvaluator to check logical consistency in investment advice, and custom evaluators to flag non-compliant statements.
Monitor AI tutoring systems for educational quality and appropriateness. Implement FluencyEvaluator to assess language clarity, and SafetyEvaluators to filter inappropriate content for student audiences.
Verify AI legal document reviewers for precision and completeness. Employ SimilarityEvaluator to compare AI summaries with source documents, and custom evaluators to check citation accuracy.
Offer automated evaluation services for companies deploying generative AI applications. Charge per evaluation run or monthly subscription based on data volume and number of evaluators used.
Provide regulatory compliance certification for AI systems using standardized evaluation protocols. Generate revenue through certification fees, audit services, and compliance monitoring subscriptions.
Integrate evaluation SDK into existing AI development platforms and MLOps tools. Monetize through licensing fees, enterprise support contracts, and premium evaluation features.
💬 Integration Tip
Start with single row evaluation using GroundednessEvaluator for quick validation, then scale to batch evaluation with evaluate() function for production testing.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
Safely rotate the OpenRouter API key across all config files in an OpenClaw installation. Finds every location where the key is stored, updates them, restart...
Memory graph engine with caller-provided embed and LLM callbacks; core is pure, with real-time correction flow and optional OpenAI integration.
使用豆包（火山引擎）语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色（S_ 开头的音色ID）和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时，务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...