kanfu-panda/pdlc-skills
10 stars · Last commit 2026-08-02
38 slash commands that turn Claude Code into a real PDLC workflow — PRD → TDD → implement → review → ship. Hard contracts force AI to persist artifacts, write failing tests first, and run self-checks. No more "looks done" in chat.
README preview
# pdlc-skills **English** · **[中文](./README.zh-CN.md)** [](https://github.com/kanfu-panda/pdlc-skills/actions/workflows/ci.yml) [](./LICENSE) [](./CHANGELOG.md) [](https://docs.anthropic.com/) > Author: **kanfu-panda** > Repo: [github.com/kanfu-panda/pdlc-skills](https://github.com/kanfu-panda/pdlc-skills) > License: [MIT](./LICENSE) **pdlc-skills** turns AI software engineering into an **auditable, on-disk state machine**. It's a [Claude Code plugin](https://docs.anthropic.com/) shipping a staged PDLC (Product Development Life Cycle) workflow — PRD → design → TDD → implement → review → ship → retro — where every stage enforces hard contracts (artifacts persisted to `docs/`, per-feature state machine, tests-before-code, mandatory self-check, single-shot auto-repair), so AI work produces real, reviewable files instead of chat-only output. Three things fall out of that state machine: - **Auditable** — every artifact lands on disk; you `git diff` exactly what the AI did. - **Autonomous** — checks come from **real command exit codes** (never model self-report), so an autonomous loop can drive `tdd → implement → review` to convergence unattended, with fail-stop, stuck-stop, and budget guards. - **Portable** — the state machine lives in your repo, so it's tool-agnostic. **Claude Code** has the richest integration (38 slash commands + statusline + in-plugin loop engine); **Codex** and others drive the same methodology via adapters. See [Multi-platform](#multi-platform-other-ai-coding-tools).