$ show automazeio/ccpm
CCPM is a structured project management skill for AI agents (Claude Code, Codex, etc.) that enforces a spec-driven development workflow: PRD → Epic → GitHub Issues → Parallel Agents → Shipped Code. The codebase consists of markdown reference documents (plan.md, structure.md, sync.md, execute.md, track.md, conventions.md) and a set of deterministic bash scripts that read project state from .claude/ directory (PRDs, epics, tasks with frontmatter). The system does not contain any runtime code—it is purely a collection of instructions and helper scripts that an AI agent reads and executes. Its architecture is a flat skill structure following the agentskills.io standard, with no external dependencies beyond git, gh CLI, and a GitHub repository. The primary data flows are local file operations (creating/reading/updating markdown files) and GitHub API calls via gh CLI for issue creation, syncing, and closing. The skill is harness-agnostic and works with any compatible agent framework.
The LLM identified 2 files worth highlighting for reuse:
Provides a daily standup report by scanning the .claude/epics/ directory for active work items, recently modified files, and available tasks. It demonstrates a reusable pattern: reading markdown files with YAML frontmatter, filtering by status, and aggregating statistics. The script is self-contained and could be adapted to any project that uses flat markdown files with frontmatter for tracking work items.
Identifies tasks that are blocked by unmet dependencies by parsing the 'depends_on' frontmatter field in task files. It then checks the status of each dependency and reports which dependencies are still open. This script implements a clean dependency resolution pattern that could be reused in any project management tool that stores task metadata as frontmatter in markdown files.