frankxai/skills

1

agentic-orchestration Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for b…

frankxai/skills

14

2

claude-md Author, audit, and maintain CLAUDE.md memory files the way Anthropic recommends — under 200 lines, only-always-true f…

frankxai/skills

13

3

claude-sdk Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production be…

frankxai/skills

13

4

defuddle Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use…

frankxai/skills

13

5

langgraph-patterns Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the…

frankxai/skills

13

6

mcp-2025-patterns Current best practices for Model Context Protocol server design, implementation, and integration. Updated patterns fo…

frankxai/skills

13

7

mcp-architecture Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, pr…

frankxai/skills

13

8

model-routing Intelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) base…

frankxai/skills

13

9

openai-agentkit Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchest…

frankxai/skills

13

10

agent-design-review Use when the user asks to review, grill, pressure-test, or sanity-check an AI agent or multi-agent system design befo…

frankxai/skills

10

11

agent-stop-conditions Use when designing an agent, reviewing its orchestration logic, or investigating a runaway loop. Unbounded loops, mis…

frankxai/skills

5

12

fail-closed-eval-gate Use when an agent, system, or prompt change is ready to merge or deploy. Do not proceed unless a named evaluation sui…

frankxai/skills

5

13

mcp-least-privilege Use when designing or auditing an MCP server's security posture. MCP servers must operate under least-privilege per t…

frankxai/skills

5

14

run-receipt Use when an agent run completes, fails, or is being audited. A multi-step run is not done until a receipt exists show…

frankxai/skills

5

15

tool-allowlist Use when designing agent tool policies, setting up tool access controls, or investigating "how did the agent call tha…

frankxai/skills

4