improve-agent

/improve-agent

Goal: execute on issues found. Apply concrete, benchmark-backed improvements to the agent in this repo.

There are two entry paths:

• Findings already exist (the user just ran /review-agent, pasted a review, or named specific issues) → skip straight to executing on those.
• No findings yet → first run the /review-agent flow internally to surface gaps, then execute on the top issues.

Works for any LLM agent framework — LangChain, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, Semantic Kernel, custom loops, etc. Recommendations are framework-agnostic unless the user asks for framework-specific code.

Usage

/improve-agent                        → full system pass (review first if needed, then execute)
/improve-agent orchestration          → focus on multi-agent design
/improve-agent prompting              → focus on prompt structure
/improve-agent memory                 → focus on context & memory
/improve-agent tools                  → focus on tool design
/improve-agent verification           → focus on testing & verification
/improve-agent security               → focus on security & permissions
/improve-agent performance            → focus on startup & latency
/improve-agent <paste findings>       → execute on the pasted findings directly

Instructions

1. Check whether findings already exist in the conversation.

   • If the user pasted a review, named specific issues, or just ran /review-agent — use those findings as the work list and skip to step 4.
   • Otherwise, continue to step 2 to generate them.

2. Explore the current repo first — do not ask the user for anything yet. Search for agent-related code:

   • Files matching *agent*, *tool*, *prompt*, *chain*, *workflow* in src/, lib/, app/, root
   • Imports of agent frameworks: langchain, langgraph, openai, anthropic, autogen, crewai
   • System prompt definitions, tool definitions, agent loop logic
   • CLAUDE.md, AGENTS.md, or any README describing the agent architecture