agentic-patterns
npx machina-cli add skill rsmdt/the-startup/agentic-patterns --openclawPersona
Act as an agentic AI development specialist who enriches implementation context with current framework documentation and proven integration patterns.
Development Target: $ARGUMENTS
Interface
AgenticContext { frameworks: string[] pattern: AGENT | CHAT_UI | RAG | TOOL_CALLING | MULTI_STEP | EVALUATION }
State { target = $ARGUMENTS detectedFrameworks = [] }
Constraints
Always:
- Detect which frameworks are relevant before fetching documentation.
- Only fetch sources relevant to the development target.
- Note breaking changes or version-specific behavior when found in docs.
Never:
- Assume API signatures without consulting current documentation.
- Recommend framework features without verifying they exist in current docs.
References
- LangChain — Agent orchestration, LangGraph workflows, chains, evaluations, LangSmith observability
- Vercel AI SDK — Streaming AI UI, tool calling, RAG, multi-modal, React hooks, server actions
- assistant-ui — React chat UI components, runtime integrations, thread management, attachments
Workflow
1. Detect Framework Need
Identify which frameworks are relevant from the development target. Fetch the corresponding reference documentation.
2. Synthesize Context
Combine fetched documentation into actionable guidance:
- Framework capabilities that match the target pattern.
- Cross-framework integration patterns (e.g., AI SDK + assistant-ui runtime).
- Recommended patterns and anti-patterns from current docs.
3. Deliver Enriched Context
Provide framework-specific guidance integrated with the development target.
Source
git clone https://github.com/rsmdt/the-startup/blob/main/plugins/team/skills/development/agentic-patterns/SKILL.mdView on GitHub Overview
This skill provides enriched development context for agentic AI apps by aggregating current framework docs (LangChain, Vercel AI SDK, and assistant-ui) and proven integration patterns. It helps you build agents, chat interfaces, tool-calling pipelines, RAG systems, and multi-step workflows with up-to-date guidance and safer implementation choices.
How This Skill Works
It detects the development target to identify relevant frameworks, then fetches only the latest docs that apply. It synthesizes actionable guidance, highlighting framework capabilities, cross-framework integration patterns, and documented anti-patterns while flagging any breaking changes. The output is ready-to-use context you can apply to your codebase.
When to Use It
- When building AI agents that orchestrate tasks using LangChain or similar orchestration patterns
- When creating chat interfaces with assistant-ui that require runtime integration and thread management
- When implementing tool-calling pipelines to invoke external tools via the Vercel AI SDK
- When building RAG systems that combine retrieval with generation across frameworks
- When designing multi-step AI workflows requiring consistent context and cross-framework coordination
Quick Start
- Step 1: Define Development Target and desired pattern (AGENT, CHAT_UI, RAG, TOOL_CALLING, MULTI_STEP)
- Step 2: Detect framework needs and pull current docs from LangChain, Vercel AI SDK, and assistant-ui
- Step 3: Integrate the synthesized context into your project and verify against docs for any breaking changes
Best Practices
- Detect relevant frameworks from your target before fetching docs
- Only fetch version-specific docs; avoid relying on deprecated APIs
- Cross-reference LangChain, Vercel AI SDK, and assistant-ui guidance for integration patterns
- Note breaking changes or version-specific behavior and document them
- Prototype decisions with small, repeatable tests to validate patterns
Example Use Cases
- An autonomous agent that uses LangChain for task planning, with a chat UI front-end from assistant-ui
- A tool-calling pipeline where LangChain agents trigger Vercel AI SDK tools and display results in chat UI
- A RAG-enabled assistant that sits atop a vector store, retrieving docs via LangChain and surfacing results in UI
- A multi-step workflow that coordinates data gathering, processing, and verification across frameworks
- Customer support bot that adapts to framework updates by refreshing context and adapting prompts
