Agent Claude Code
Autonomous execution mode for AgentX. Completes simple and complex work end to end by applying PM, Architect, Data Scientist, UX, Engineer, Reviewer, DevOps, and Tester phases internally when needed.
Agent Claude Code needs its repo
Conversational story creation and refinement coach. Guides users through writing well-structured user stories with quality acceptance criteria.
Agent Claude Code needs its repo
AI-first system architecture -- evaluate GenAI/Agentic AI solutions as the default lens, create ADRs with 3+ evaluated options, and technical specifications with diagrams -- NO CODE EXAMPLES.
Agent Claude Code
Research, analyze, and create domain-expert materials for consulting topics. Synthesize domain knowledge from specialized skills (Oil & Gas, Financial Services, Audit, Tax, Legal) for client engagements, including presentation storylines with slide-ready visuals and diagrams.
Agent Claude Code needs its repo
Design and implement GenAI pipelines, LLM-as-judge evaluations, drift monitoring, RAG systems, agent orchestration, and fine-tuning workflows.
Agent Claude Code needs its repo
Create and manage CI/CD pipelines, GitHub Actions workflows, deployment automation, and release pipelines.
Agent Claude Code needs its repo
Implement features, fix bugs, and write tests through Compound Engineering -- a structured pipeline of Research -> Brainstorm -> Plan -> Design -> Implement -> Scrub -> Test -> Review, with gate-checked phase transitions, full artifact chain consumption, mandatory Karpathy guidelines, and a risk-based quality loop.
Agent Claude Code
Build Microsoft Fabric data-platform deliverables: Lakehouse and Warehouse schemas, OneLake shortcuts, Spark notebooks, Data Pipelines, Dataflow Gen2 specifications, medallion data products, data quality, lineage, and operational documentation. Use for type:fabric work. Hands Power BI reports and semantic models to…
Agent Claude Code
Build unpacked Microsoft Power Platform solution source for Dataverse, Power Apps, Power Automate, Power Pages, PCF, plugins, security, environment variables, and Copilot Studio. Use for type:lowcode work and Power Platform solution delivery. Generates and validates local source but never authenticates to, imports…
Agent Claude Code
Design and build Power BI reports, dashboards, semantic models, and DAX measures for data-driven insights.
Agent Claude Code needs its repo
Define product vision, create PRD, break Epics into Features and Stories with acceptance criteria.
Agent Claude Code needs its repo
Review code and apply explicitly approved safe fixes. Report cosmetic lint/style findings as LOW and ask before cleanup; suggest complex changes for human approval.
Agent Claude Code needs its repo
Review code quality, test coverage, security, performance, and architectural conformance. Approve or request changes.
Agent Claude Code needs its repo
Validate software quality through automated testing, performance testing, security testing, and production readiness certification.
Agent Claude Code needs its repo
Create user research, wireframes, interactive HTML/CSS prototypes, and design specifications following WCAG 2.1 AA standards.
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
Use when evaluating AI quality, safety, completeness and cost with held-out tasks, executable graders, calibrated judges and explicit release criteria.
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, adaptive 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.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: