Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
Scanned 5/29/2026
Install to Claude Code
Skills Directorynpx -y skills add a5c-ai/babysitter --skill github-sync --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Github Sync?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-github-sync)More formats (shields.io, HTML) on the badges page.
# GitHub Sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
## Agent
Project Tracker - `project-tracker`
## Workflow
1. Create epic issue with `epic` and `ccpm` labels
2. Create task issues linked to epic with stream-type labels
3. Add acceptance criteria as checkboxes in issue body
4. Set issue relationships (parent/child)
5. Sync progress updates as issue comments
6. Close issues when tasks complete
7. Maintain bidirectional sync state
## Inputs
- `githubRepo` - GitHub repository (owner/repo)
- `featureName` - Feature identifier
- `epic` - Epic document
- `tasks` - Task list from decomposition
## Outputs
- Epic issue number
- Task issue numbers with ID mapping
- Labels applied
- Sync status report
## Issue States
`open` -> `in-progress` -> `blocked` -> `review` -> `closed`
## Process Files
- `ccpm-orchestrator.js` - Phase 4 of full lifecycle
- `ccpm-parallel-execution.js` - Progress sync during execution
- `ccpm-tracking.js` - Tracking data sync
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
