Agent building

CLI-first web scraping & content extraction with optional MCP server.

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API.

Generate images on grok.com/imagine with the signed-in Grok session.

Build Solana applications with Helius infrastructure.

Use for Sage prompt, topology, tool, planner, runtime authority, and other consequential architecture changes; keep ordinary development measurement plumbing…

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority.

Agent-agnostic long-term project memory through `.memory-bank/` + RULES (TDD/SOLID/Clean Architecture/FSD/Mobile) + dev-toolkit commands.

Guide for creating effective skills.

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services.

Repo-local Sage GOAD/Trust Walker full lab reset and readiness workflow.

Download an existing Mythic payload, stage it onto a Ludus Windows host over WinRM, and launch it as the current user or a supplied run-as user.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.

The mandatory operational guide and metabolic flow for agents interacting with arifOS.

Analyze Sage's Phoenix/OpenInference trace database (phoenix.db) for the Sage LangGraph multi-agent system.

Repo-local Sage Forge/Codex helper workflow.

One cheap headless Claude Code worker on a cheaper brain (GLM via z.ai, or Sonnet/Haiku) - full tool harness, isolated git worktree + CLAUDE_CONFIG_DIR -…

Create, extend, repair, validate, test, and package Pi coding-agent packages (pi packages, pi-packages, Pi 패키지) for local, npm, or git distribution.

Create, improve, and evaluate reusable agent skills.

Plan a huge, foggy chunk of work — more than one agent session can hold — as a local map of decision tickets, resolved one at a time until the way to the…

Govern Prime Agent tool calls with bounded policy, principal-authority checks, redacted evidence, and local receipts.

Address actionable GitHub pull request review feedback.

Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference…

Builds and debugs Claude Code lifecycle hooks, covering event types, input payloads, JSON responses, exit codes and registration in settings or plugins.