Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC
This repository also configures its own agents. See what framework tells them →
Plugin Claude Code
Bundles 13 skills, 1 hook · 672 tokens together
Knowledge production: project bootstrap, project init, generation of context artifacts (skills, agents, rules, commands, hooks), mermaid diagrams, learn, explore, recipe how-to sheets.
Plugin Claude Code
Bundles 10 skills, 2 agents · 578 tokens together
Code transformation: plan, implement, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
Plugin Claude Code
Bundles 10 skills · 491 tokens together
Product backlog artifacts, refinement, Product Briefs, Epics, User Stories, Tasks, Spikes, Defects, requirements, and specs.
Plugin Claude Code
Bundles 5 skills · 262 tokens together
Meta-cognition: refine input through brainstorming, refine output through challenge, inspect blind spots and facts, and improve conversation efficiency.
Plugin Claude Code
Bundles 5 skills · 266 tokens together
External artifacts: repo-init, commit, pull-request, release-tag, issue-create.
Plugin Claude Code
Bundles 3 skills · 163 tokens together
Orchestrates the synchronous SDLC pipeline, async issue-to-PR automation, and the product backlog.
Plugin Claude Code
Bundles 1 skill · 42 tokens together
ALPHA, not ready for use. UI and UX concern for the AI-Driven Development framework. Use when the user wants to design, review, or improve a frontend interface. Do NOT use for backend-only or non-UI tasks.
Plugin Claude Code
Bundles 3 skills · 293 tokens together
Measurement. The hooks journal which skill served which task, on plain node with nothing installed; three skills reach the aidd CLI to turn it on, answer what a period or a task consumed, and check it is recording. Off unless you turn it on, and it computes no amount.
Plugin Claude Code
Bundles 1 skill · 59 tokens together
Acceptance QA: validates observable behavior against acceptance criteria and records reviewer evidence. Use when a reviewed candidate needs evidence that it meets its acceptance criteria. Do NOT use for diff review, unit or integration tests, or fixing the application.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: