agentleFS
OpenxIntelligenceOpenxIntelligence/Coding-Agent-Skills/github-project-management/SKILL.md

github-project-management

Skill4 starsChanged 26 days agoMITView on GitHub

Manage GitHub issues, project boards, sprints, and milestones with swarm-coordinated automation — issue triage, decomposition into subtasks, board sync, sprint planning, KPI tracking. Use when asked to "github project management", "manage github projects", "github issue automation", "swarm project board", "automate sprint", "triage issues", or "set up project board".

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use V3 DDD Architecture, V3 Memory Unification and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ruvnetSkill

    V3 DDD Architecture

    Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

    Also in 27 projects that use this

  • ruvnetSkill

    V3 Memory Unification

    Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

    Also in 27 projects that use this

  • nbossnSkill

    worker-benchmarks

    Run comprehensive worker system benchmarks and performance analysis

    Also in 9 projects that use this

  • ZekiogSkill

    agent-agent

    Agent skill for agent - invoke with $agent-agent

    Also in 5 projects that use this

  • ZekiogSkill

    agent-analyze-code-quality

    Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality

    Also in 5 projects that use this

  • +3 more from ruvnet
  • +4 more from Zekiog

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After running a workflow, confirm:

    line 97

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub Project Management

Coordinates GitHub issue management, project board automation, and sprint planning using AI swarm agents. Supports issue triage / decomposition, bidirectional board sync, automated progress tracking, and KPI reporting.

Contents

  • When to Use
  • Prerequisites
  • Quick Start
  • Workflow
  • Verification
  • References

When to Use

  • "Triage these unlabelled issues"
  • "Break down this epic into subtasks"
  • "Sync GitHub issues with the project board"
  • "Set up a sprint with velocity tracking"
  • "Generate a sprint-summary report"
  • "Coordinate work across multiple repos / boards"

Prerequisites

See references/troubleshooting.md for full tool versions, required token scopes, and GitHub API limits.

Minimum to run the plain gh examples: gh + jq. Swarm features additionally need ruv-swarm or claude-flow MCP server running — see those projects' docs for install. The skill degrades gracefully: anything prefixed with npx ruv-swarm requires the MCP server; everything else is plain gh + jq.

Quick Start

# Create a coordinated issue
gh issue create \
  --title "Feature: Advanced Authentication" \
  --body "Implement OAuth2 with social login..." \
  --label "enhancement,swarm-ready"

# Initialise swarm tracking
npx claude-flow@alpha hooks pre-task --description "Feature implementation"

# Set up the board
PROJECT_ID=$(gh project list --owner @me --format json | jq -r '.projects[0].id')

npx ruv-swarm github board-init \
  --project-id "$PROJECT_ID" \
  --sync-mode "bidirectional"

Workflow

  1. Triage incoming issues — auto-label, link duplicates (issue-management.md)
  2. Decompose large issues into subtasks with priority (issue-management.md)
  3. Sync issues to the project board (board-automation.md)
  4. Pick the right swarm topology (mesh / hierarchical / ring / star — see swarm-topologies.md)
  5. Track sprint velocity & KPIs (sprint-and-analytics.md)
  6. Automate via GitHub Actions + comment commands (automation-patterns.md)
  7. Verify (see below)

Verification

After running a workflow, confirm:

  • Every issue acted on shows the expected label change in gh issue view <num> --json labels
  • Every board-synced issue appears as a project card in the expected column
  • Subtask checklists in issue bodies are valid Markdown (parseable; no broken - [ ] syntax)
  • Progress comments posted by automation are idempotent — re-running doesn't duplicate
  • gh api rate_limit shows headroom (running this against thousands of issues can exhaust the 5,000 req/hr limit; see troubleshooting.md)
  • Closed-as-stale issues match the explicit STALE_DATE cutoff — spot-check three

References

  • references/issue-management.md — creation, batch, issue→swarm, triage, decomposition, progress, stale management
  • references/board-automation.md — board init, mapping config, sync, smart card management, views, dashboards
  • references/sprint-and-analytics.md — what gets tracked, sprint setup, kanban/scrum, analytics, KPIs, release planning
  • references/swarm-topologies.md — multi-board sync, dependencies/epics, cross-repo, team collab, topology guide
  • references/templates.md — issue templates (integration / bug / feature / swarm task)
  • references/automation-patterns.md — GitHub Actions workflow, specialised swarms, operational guidance, complete worked example, command quick-reference
  • references/troubleshooting.md — sync, performance, recovery, GitHub constraints, required permissions, security checklist (Command Authorization, Rate Limiting, Audit Logging, Data Privacy, Access Control, Webhook Security)

Related Skills

  • github-pr-workflow — link issues to pull requests automatically
  • github-release-management — coordinate release issues and milestones
  • sparc-orchestrator — complex project coordination workflows
  • sparc-tester — automated testing workflows for issues

External Documentation


Maintained by Claude Code. Version 2.1.0.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.