---
title: Agent Pipeline
kind: open-source
role: Solo build
years: 2025 – present
status: running
summary: >-
  Agent-orchestrated development pipeline that takes a PRD to QA-ready code
  through seven discrete stages, with human checkpoints at the two decision
  points that matter.
links:
  - label: github.com/dpaola2/pipeline-skills
    url: 'https://github.com/dpaola2/pipeline-skills'
tags:
  - ai
  - claude-code
  - developer-tools
  - open-source
  - mcp
order: 1
---

Coding agents are at their best when they have structure to work inside.
Pipeline Skills is the structure I wanted: a sequence of seven distinct stages
(Discovery, Architecture, Gameplan, Test Generation, Implementation, Review,
QA Plan), each producing a structured artifact, with two human checkpoints —
approve the architecture before tests are written, approve the gameplan before
code is written. After that the agent runs.

It ships as a set of [Claude Code](https://docs.anthropic.com/en/docs/claude-code)
skills (slash commands) that any project can install. Repos with conventions
files and test infrastructure can adopt it in minutes. The setup skill
auto-detects framework, stack, and directory structure and writes a
configuration block into the project's conventions file.

The principle behind it: AI-augmented development works best when the *handoff
points* are deliberate — where humans approve, where the agent commits, where
work flows between stages. Most "AI for coding" tools collapse those seams. The
pipeline insists on them.

Inspired in part by Doug Engelbart's framing of system design as the place
where the highest-leverage AI work actually lives — see
[/writing](/writing) for related thinking, and the
[Work Context Protocol](/portfolio/work-context-protocol) for the persistent-memory
layer the pipeline sits on top of.