Knowledge production: project bootstrap, project init, generation of context artifacts (skills, agents, rules, commands, hooks), mermaid diagrams, learn, discovery
Detect the current project's state and open a hub of project actions - understand the project, set up or refresh the memory bank, or continue the AIDD development journey. Silently inspects the project, the AIDD setup, and which AIDD plugins are installed, then adapts the menu to that context. Use when the user says "where do I start", "onboard me", "onboard me to this project", "what should I run next", "what should I work on next", "what's the state of this project", "guide me through aidd", "guide me through aidd-context", or invokes `aidd-context:00-onboard`. Do NOT use to enumerate every installed surface from raw user intent (the discovery skill in this plugin handles that).
Imagine and validate the technical architecture of a new SaaS through interactive Q&A, candidate-stack comparison, multi-agent audit, and an INSTALL.md output. Use when starting a new SaaS project, choosing a stack, designing the architecture pattern (monolith vs microservices vs serverless), or producing a project's INSTALL.md. Do NOT use for editing an existing project's stack, database schema design, or scaffolding actual files (this skill produces docs only, no code).
Initialize or refresh the project memory bank and ensure AI context files contain the project memory block. Use when running `aidd init` for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files after they exist - use `aidd-context:10-learn` instead; do NOT use for editing a single rule - edit the file directly.
Route a request to generate a context artifact (skill, rule, agent, command, or hook) to its dedicated generator when the user has not named which kind. For a named kind, that generator triggers directly. Not for listing existing artifacts (use discovery).
Generate a router-based skill across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a skill, or turn a workflow into one. Not for other artifacts like rules, agents, commands, hooks.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
6 plugins · 37 skills · 3 agents · MIT
Quick start → · Browse plugins → · How it works → · Join Discord →
The AIDD Framework is a marketplace of skills, agents, rules, and conventions that make the AI-Driven Development flow concrete inside your AI coding assistant - the full SDLC (plan → implement → review → ship) under rigorous human supervision. It is the open toolset of the AI-Driven Dev community.
The framework is authored for Claude Code, and this repository is its native marketplace. Every release also attaches archives adapted to each tool we support - Cursor, GitHub Copilot, Codex, OpenCode (marketplace or flat format per tool) - so you grab the build that matches your assistant. See Another AI tool? for the per-tool download + install table.
Founded by Alex Soyes - Blog · GitHub · LinkedIn · X.
Join the conversation: Discord · YouTube · LinkedIn · Website
Just an AI coding assistant. Everything else is per-plugin and optional.
| To… | You need |
|---|---|
| Register & run the marketplace | An AI assistant - Claude Code runs this marketplace natively; for another tool, grab the release archive the aidd-cli builds for it |
| Use a plugin's extras | Only what that plugin's README lists - e.g. gh / glab for VCS, a ticketing tool for PM |
Nothing beyond the AI tool is required just to register the marketplace.
Register the marketplace and install the core plugins (Claude Code slash commands, not shell):
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-context@aidd-framework
/plugin install aidd-refine@aidd-framework
/plugin install aidd-dev@aidd-framework
/plugin install aidd-vcs@aidd-framework
Then set up project context (guided onboard, or direct project-init) and run the dev flow:
---
title: AIDD quick start
---
flowchart TD
Install["Marketplace + plugins installed"]
Setup{"Set up context"}
Onboard["aidd-context:00-onboard - guided hub"]
Init["aidd-context:02-project-init - context engineering"]
Brainstorm["aidd-refine:01-brainstorm"]
Plan["aidd-dev:01-plan"]
Implement["aidd-dev:02-implement"]
Assert["aidd-dev:03-assert"]
Review["aidd-dev:05-review"]
Commit["aidd-vcs:01-commit"]
PR["aidd-vcs:02-pull-request"]
Learn["aidd-context:10-learn"]
Install --> Setup
Setup -->|guided| Onboard
Setup -->|direct| Init
Onboard --> Init
Init --> Brainstorm
Brainstorm --> Plan
Plan --> Implement
Implement --> Assert
Assert --> Review
Review --> Commit
Commit --> PR
PR --> Learn
/aidd-context:00-onboard - it inspects the project and guides you./aidd-dev:00-sdlc runs plan → implement → review → ship./plugin Discover tab.Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
Orchestration plugin. v1 use case: async development - turn ready issues into pull requests, then iterate on review feedback until a human takes over. Designed to host more orchestration use cases (refactoring, docs, audits) in future versions.
Product management: ticket-info, user-stories-create, prd, spec
External artifacts: commit, pull-request, release-tag, issue-create
Meta-cognition: refine input through brainstorming, refine output through challenge and condensed communication mode.
npx claudepluginhub ai-driven-dev/frameworkUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Unified status line for Claude Code with multi-CLI (Claude, Codex, Gemini, z.ai) usage monitoring, context, rate limits, and cost tracking