exponen-agi/recursive-agentic-improvements
Skill Claude CodeCodex
Keep a documentation corpus coherent by enforcing single-source-of-truth — each fact/term has ONE canonical owning file; others point to it instead of restating it. Use when docs/specs/markdown files drift or contradict each other, when the user worries about "which doc is right", or when setting up a registry + CI…
exponen-agi/recursive-agentic-improvements
Skill Claude CodeCodex
Engineer production-grade prompts for frontier LLMs (Claude, GPT-4o, Gemini). Use when the user wants to optimize, rewrite, evaluate, or troubleshoot a prompt — including system prompts, user-turn prompts, agent instructions, or API pipeline prompts. Applies framework selection (COSTAR / RISEN / RODES / PICO / RTF /…
exponen-agi/recursive-agentic-improvements
Command Claude Code
Build any AI agent for any domain in any supported framework. The skill researches what tools and patterns actually exist before writing a single line of code.
exponen-agi/recursive-agentic-improvements
Command Claude Code
Add any new capability to an existing agent without breaking what already works. The skill researches what tools and patterns actually exist for the capability before writing code.
exponen-agi/recursive-agentic-improvements
Command Claude Code
Derive probes from the agent's own specification, run them against the live agent, judge each PASS/FAIL, apply targeted fixes, and iterate until all probes pass.
exponen-agi/recursive-agentic-improvements
Instructions file CodexOpenCode
Instructions for exponen-agi/recursive-agentic-improvements, a project described as: Three Claude Code slash commands — /create-agent, /improve-agent, /extend-agent — that research, scaffold, and recursively optimize AI agents across Agno, CrewAI, LangGraph, and Google ADK.
exponen-agi/recursive-agentic-improvements
Instructions file
Instructions for exponen-agi/recursive-agentic-improvements, covering claude.md — recursive agentic improvements, strict token optimization protocols, 1. response verbosity, 3. tool execution constraints and project snapshot.