Skill Claude CodeCodex
Design agent memory beyond a single context window: short-term (working / scratchpad), long-term (episodic, semantic, procedural), and shared / cross-session memory. Covers mem0, Zep, Letta / MemGPT, LangMem, OpenAI Memory, retrieval and consolidation policies, PII handling, and eviction.
Skill Claude CodeCodex
Instrument LLM agents with tracing, metrics, and evaluation telemetry. Use when adding OpenTelemetry GenAI semantic conventions, integrating Langfuse / LangSmith / Arize Phoenix / Helicone / OpenLLMetry, capturing prompt/response spans, tool-call latency, token cost, eval scores, and feedback signals. Distinct from…
Skill Claude CodeCodex
Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM models, implementing agent orchestration, adding tracing/observability, or evaluating agent quality. Covers agent architecture, model selection, multi-agent workflows, and production deployment.
Skill Claude CodeCodex
Evaluate AI/ML model quality, safety, and reliability. Use when designing evaluation frameworks, implementing automated evals, running benchmarks, measuring RAG quality (RAGAS), or establishing quality gates for model deployment.
Skill Claude CodeCodex
Defend LLM systems against prompt injection, jailbreaks, data exfiltration, and unsafe output. Covers input/output guardrails (NeMo Guardrails, LlamaGuard 3, ShieldGemma, Azure AI Content Safety, Bedrock Guardrails), red-team frameworks (Microsoft PyRIT, Garak, promptfoo redteam), and Responsible AI controls…
Skill Claude CodeCodex
Implement production applications with Anthropic Claude models -- Messages API, tool use, prompt caching, extended thinking, vision, computer use, and the Claude Agent SDK. Use when coding directly against Anthropic APIs, Claude via AWS Bedrock, or Claude via GCP Vertex AI rather than a higher-level framework.
Skill Claude CodeCodex
Design and architect AI agents on Azure AI Foundry -- lifecycle planning, model selection strategy, evaluation frameworks, guardrail design, and deployment patterns. Use when designing agent architecture on Foundry, choosing models, planning evaluation strategy, or defining guardrails. For step-by-step operational…
Skill Claude CodeCodex
Design and implement the cognitive architecture of AI agents including memory systems, RAG pipelines, and state management. Use when defining agent memory strategy (short/long-term), building RAG pipelines (knowledge retrieval), designing state management systems, or selecting vector databases for semantic search.
Skill Claude CodeCodex
Build agents that operate browsers and desktop GUIs via screenshots and actions. Covers Anthropic Computer Use, OpenAI Operator / Computer-Using Agent (CUA), browser-use, Playwright-based agents, sandboxing (containers, VM, ephemeral profiles), permissions and approvals, failure recovery, and testing patterns.
Skill Claude CodeCodex
Manage LLM context windows efficiently. Use when implementing context compaction, conversation summarization, token budget management, sliding window strategies, or optimizing prompt length for cost and quality.
Skill Claude CodeCodex
Design strategies to detect, monitor, and remediate data drift in GenAI applications and ML pipelines. Use when monitoring LLM input patterns, detecting query distribution shifts, tracking embedding drift, building RAG retrieval quality monitoring, or establishing data governance for model inputs.
Skill Claude CodeCodex
Design and implement feedback loops for continuous AI/ML improvement. Use when building RLHF/RLAIF pipelines, user feedback collection systems, reward modeling, iterative model refinement workflows, or online learning strategies.