Agent skill · personamanagmentlayer
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or Ollama, agent memory, or when the task involves giving a model the ability to act rather than only to answer.
What it needs
About 6k tokens when loaded.
What this skill does
Agent Engineering Expert An agent is a loop in which a model chooses tools until a goal is met. The difficulty is not the loop — it is that the model's choices are driven by text that may be attacker-controlled, and the tools have real effects. Core Concepts The Loop Concretely: assemble context, call the model with tool definitions, execute the requested tool, append the result, repeat until the model stops or a limit is hit. Every element of that loop needs a bound — iterations, wall time, tokens and cost. Capability Is the Design What an agent can do is defined entirely by the tools it holds. Reliability and safety come from designing that surface, not from instructing the model to be careful. A tool the agent does not have is a failure mode that cannot occur. The Model Is Untrusted Input Anything the agent reads — a web page, a document, a tool result, an email — may contain instructions aimed at the model. Treat every tool call as a request from an untrusted party and authorise it independently. This is the defining security property of agents, and no amount of prompting removes it. Autonomy Is a Dial More steps means more compounding error. A workflow with fixed stages and a model at each decision point is usually more reliable, cheaper and easier to debug than an open-ended agent. Choose the least autonomy that solves the problem. Designing Tools The tool description is a prompt. It is the only thing telling the model when to use it. What makes tools work: Few, distinct tools. Beyond roughly twenty, selection accuracy falls. Merge overlapping tools rather than adding one more. Say when not to use it, and name the alternative. Most misuse is a boundary problem between two similar tools. Constrain with enums and ranges, not prose. The schema is enforced; the description is advice. Return structured, bounded results. Truncate, paginate, and say so in the result so the model can ask for more. Errors are prompts too. "since must be ISO 8601, e.g. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills personamanagmentlayer/agent-engineering-expert