Aidd — Testing skill for Claude Code
AI-Driven Development: you decide what to build and what ships, and an AI delivery team does the rest and proves it.
How to install Aidd
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open thaithienvanid/aidd and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Aidd does
AI-Driven Development: you decide what to build and what ships, and an AI delivery team does the rest and proves it. Four decisions stay yours: the plan, Spec approval, the release, and the launch. A skill and guard for your coding agent, optional agent roles, a CLI, and a CI gate. Spec-driven, trunk-based, local-first.
Alternatives in Testing
- OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
- Deliver — Delivery phase - Review, validate, and test with multi-AI quality assurance 2.8k ★
- Axiom — Development Changelog — Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions 671 ★
README
Get started · Quickstart · How do I… · The method · The delivery team · FAQ
**You decide what to build, what lands, and what leaves your machine. An AI team does everything in between, and proves it.**
AIDD, short for AI-Driven Development, is a way of working with AI agents as a delivery team. As the stakeholder, you agree to the plan, approve each contract, and release the result. The agents plan, specify, build, test, and review their own work, on their own branches, inside rules they can't bend.
**aidd** is the open-source toolkit that runs it. It gives your coding agent a skill, an optional team of agent roles, and a command-line tool. In Claude Code, Codex, Google Antigravity, Grok Build, and OpenCode V2, a guard also checks each step the agent takes. A CI check, `aidd/gate`, lets work reach your main branch only on proof. It runs on GitHub, on GitLab, or on your own machine with nothing but git.
[!IMPORTANT] **Pre-release.** aidd 1.0.0 is unreleased and Beta until it is tagged, published, and one pull request has passed this repository's own live gate. U
Related Skills
QA Phase
Run QAPhase — the autonomous acceptance-and-ship QA gauntlet. Proves a finished story end-to-end (spec-gap/gri
Divi5 Builder
Build & edit Divi 5 WordPress pages via the WP REST API from a compact JSON spec — native, builder-editable mo
Crewbook Build
You bring the idea. Your AI team ships the software. Crewbook: Build sets up a Claude Code agent team (PO, Lea
Spec Constitution
Creates or updates the project constitution — principles, conventions, and governance that guide all technical
Squad Assemble
Analyze a spec/requirement and produce a recommended team composition (review mode, models, specialists, limit
Aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a pro
Related Agents
De Cadencing Scholar
Native-English-scholar de-cadencing pass. Before an English draft ships, it finds and rewrites the rhythm patt
Codex Run
Runs a Codex job through the codex-run skill scripts and returns only the final report, so the launch, polling
Dynamic Pricing
Propose and (after approval) push rate and minimum-length-of-stay changes for hotel rooms in the next 30 days.
