Claude skills and agent skills

vpeetla-aiSkill

agentic-engineering

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/agentic-engineering/SKILL.md

Apply Karpathy agentic engineering discipline: think before coding, minimal diffs, surgical changes, test-verified completion. Use for any implementation task in vpeetla-ai repos when quality bar matters.

Often used withaegis-gateway·nuxt4-patterns·dart-flutter-patterns

vpeetla-aiSkill

governed-ai-stack

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/governed-ai-stack/SKILL.md

Maps tasks to the vpeetla-ai 6-layer reference stack (VAP, AegisAI, Enterprise RAG, AegisLoop, Content Factory, LoopForge). Use when choosing which repo to change, designing integrations, or explaining architecture.

vpeetla-aiSkill

grill-with-context

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/grill-with-context/SKILL.md

Interview the user about a plan or design until decisions are resolved, while updating CONTEXT.md terms and noting ADR candidates. Use before large features, cross-repo integrations, or when requirements feel vague.

vpeetla-aiSkill

hitl-side-effects

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/hitl-side-effects/SKILL.md

Add human-in-the-loop gates for irreversible actions: LangGraph interrupt_before, AegisAI approval queue, UI approve/resume endpoints. Use when shipping, publishing, notifying, or merging agent-generated changes.

vpeetla-aiSkill

langgraph-orchestration

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/langgraph-orchestration/SKILL.md

Build or modify LangGraph StateGraph agents in vpeetla-ai repos: typed state, nodes, conditional edges, MemorySaver, interrupt_before HITL. Use when adding orchestrators, coding loops, or multi-agent graphs.

Often used withaegis-gateway·agentic-engineering·loop-engineering

vpeetla-aiSkill

loop-engineering

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/loop-engineering/SKILL.md

Implement ODAEU harness loops, RAG evolve tuning, and procedural memory in LoopForge or similar systems. Use when building self-improving agents, eval gates, MCP tool bridges, or RAG version trees.

Often used withaegis-gateway·langgraph-orchestration·agentic-engineering

vpeetla-aiSkill

portfolio-adr

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/portfolio-adr/SKILL.md

Write ADRs, case studies, and portfolio copy for ai-architecture-portfolio and venkat-ai-portfolio. Use when documenting decisions, updating ecosystem pages, or syncing GitHub profile README with live demos.

vpeetla-aiSkill

rag-governance

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/rag-governance/SKILL.md

Implement access-aware RAG in Enterprise RAG or VAP: hybrid retrieval, rerank, citations, AegisAI HITL for sensitive chunks. Use when tuning retrieval, adding Qdrant adapter, or wiring enterprise_rag_platform.

vpeetla-aiSkill

setup-vpeetla-skills

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/setup-vpeetla-skills/SKILL.md

Bootstrap a vpeetla-ai repo for org skills: issue tracker, triage labels, docs paths, and CONTEXT.md placement. Use when onboarding a new repo, first clone, or when the user says setup skills or configure agent workflow.

vpeetla-aiSkill

tdd-agent-loops

vpeetla-ai/aegisai-enterprise-agent-platform/.cursor/skills/tdd-agent-loops/SKILL.md

Test-driven development for agent systems: red-green-refactor on graphs, mocked LLM fixtures, pytest-asyncio, trace assertions. Use when adding agent nodes, fixing loop bugs, or building pattern repos.

vpeetla-aiSkill

governed-ai-stack

vpeetla-ai/multi-agent-system-pattern/.cursor/skills/governed-ai-stack/SKILL.md

Maps tasks to the vpeetla-ai 6-layer reference stack (VAP, AegisAI, Enterprise RAG, AegisLoop, Content Factory, LoopForge). Use when choosing which repo to change, designing integrations, or explaining architecture.