Verified project record

automazeio/ccpm

A reusable Agent Skills module that converts natural-language project ideas into traceable PRDs, technical epics, and GitHub issues, and orchestrates parallel coding agents using file-based coordination. It requires a GitHub repository and the authenticated `gh` CLI to function.

Project overview

It structures AI-assisted development by maintaining plain Markdown project files as the source of truth and running project tracking operations as deterministic bash scripts rather than relying on LLM tokens.

Project type: AI Agent · AI Coding · Workflow
Use cases: Coding & Development · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developer and operations teams managing AI-assisted coding workflows who require file-based traceability and controlled GitHub synchronization.

Key capabilities

Guides brainstorming and generates structured Product Requirements Documents from natural-language project ideas.
Converts PRDs into technical epics and task files containing acceptance criteria, dependencies, parallelization, and conflict metadata.
Creates epic and sub-issues, maps local task files to corresponding issue numbers, and prepares a dedicated Git worktree.
Analyzes GitHub issues into independent streams and launches scoped parallel agents with Git-based coordination.
Provides deterministic bash-script status, standup, search, next task, and blocked reporting from project files.

Limitations and risks

Requires an authenticated GitHub CLI (`gh`) and a GitHub repository; functionality is blocked without these external services.
GPU, data boundary, cost dependency, coding requirements, minimum hardware, database, operating system, and model requirements are not documented.

Getting started

Setup difficulty is medium. Users must clone the repository and point an Agent Skills-compatible harness at `skill/ccpm/` or link the skill into the harness's skills directory.
An authenticated `gh` CLI and a designated GitHub repository are required prerequisites before executing the workflow.

Evidence and sources

README: 📢 **CCPM is now an AGENT SKILL!**
README: Every team struggles with the same problems: - **Context evaporates** between sessions, forcing constant re-discovery - **Parallel work creates conflicts** when multiple agents to…
README: CCPM gives your AI agent a structured PM brain: turn ideas into PRDs, PRDs into epics, epics into GitHub issues, and issues into production code — with full traceability at every…
README: CCPM conducts guided brainstorming before writing anything. It asks about the problem, users, success criteria, constraints, and what's out of scope — then creates a structured PR…
README: Each task gets a file with acceptance criteria, effort estimate, `depends_on`, `parallel`, and `conflicts_with` metadata. Tasks are intelligently batched for parallel creation. ≤1…

Reviewed at: 2026-07-18T05:09:04Z