Workflows

A set of AI development techniques: plugins, subagents and wave orchestration. The README is in Portuguese

A workspace for Claude Code: ten commands lead from a product idea to React screens and a handoff package with ready prompts for implementation

Describe the edit and get an MP4: subtitles, motion graphics, ffmpeg. From VEED; on Mac it installs what it needs through Homebrew after you confirm

Codex profiles where GPT-6 Astra orchestrates and reviews while GPT-5.6 Luna runs the explorer, worker, tester and researcher subagents

A CLI for spec-driven development: a chain of spec, plan, tasks, next, review, accept, merge. Version 4 is still a release candidate

A ready-to-fork Claude Code template for academic work: slides, papers and data analysis with multi-agent review and quality gates

A set for n8n: a VS Code and Cursor extension, GitOps, n8n workflows as TypeScript and AI skills. An independent project not affiliated with n8n

Autonomous plan execution task by task: each task in a fresh Claude Code or Codex session, then a multi-pass review. Written in Go

Knowledge bases that AI compiles: topics, import, llm-wiki lint checks, the /wiki:ingest and /wiki:archive commands. A plugin for Claude Code and Codex

Visual editing of HTML and Markdown with Google Docs-style comments: the whole edit goes to the agent at once. All local, no account or keys

Orchestration of several agents (Claude Code, Codex, OpenCode and others): workflows are described in YAML. The name expands to Agent Koordination Topology

Ten AI agents in tmux panes: a manager hands tasks to seven workers, progress shows on a dashboard, with Claude Code, Codex, Cursor and OpenCode supported

Claude Code in a continuous loop: iteration, pull request, waiting for checks and merge. Stops on several completion signals. jq and gh are needed

One hundred ready agent teams for Claude Code, each with specialists, an orchestrator skill and domain skills, in English and Korean

A skill for business promo videos: a builder-not-judge loop, 16 motion techniques, Three.js patterns. Examples are other people's, frames are not distributed

A spec-driven dev process for agents: gated phases, context memory, and a set of agents and skills

Decks as working web apps from StackBlitz: each slide is a live page with 3D, live data and prototypes. A project template

A team of AI agents from one request: it plans the task, writes code in parallel branches, tests, reviews and opens a pull request

Repeatable agent-plus-code workflows in one skill: deterministic Python runs the phases while agents work as nodes inside the process

Jupyter labs on Azure API Management as a gateway for models, MCP tools and agents: token limits, tracing and OAuth. An Azure subscription is needed

A reference implementation of a context system for an agent: structure, data flows, a blueprint the author has used for a year. README in Chinese. For study

Skills for embedded development: AI drives compilers, debuggers (J-Link and others) and buses (CAN) from code to hardware checks. README in Chinese and English

33 battle-tested skills and a minimal .claude harness for any agent. Installation by script, npx skills or cloning

A build script and templates that turn an Obsidian vault into an AI's working memory: markdown notes, no vector database