github-project-management

78
C

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install I-Onlabs/claude-code-skills/github-project-management
skilz install I-Onlabs/claude-code-skills/github-project-management --agent opencode
skilz install I-Onlabs/claude-code-skills/github-project-management --agent codex
skilz install I-Onlabs/claude-code-skills/github-project-management --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/I-Onlabs/claude-code-skills
2. Copy the agent skill directory:
cp -r claude-code-skills/github-project-management ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Type
Non-Technical
Meta-Domain
general
Primary Domain
general
Sub-Domain
github issue swarm
Market Score
78

Agent Skill Grade

C
Score: 78/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
14/30
Ease of Use
24/25
Writing Style
9/10
Utility
20/20

Areas to Improve

  • Description needs trigger phrases
  • SKILL.md File Too Long
  • Missing References Directory

Recommendations

  • Focus on improving Pda (currently 14/30)
  • Address 2 high-severity issues first
  • Add trigger phrases to description for discoverability

Graded: 2026-01-19

Developer Feedback

I took a look at your github-project-management skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 78/100, solid C-grade work based on Anthropic's skill best practices. Your strongest area is Utility (20/20 — really chef's kiss here with genuine problem-solving power), but Progressive Disclosure Architecture is holding you back hard (14/30). The main issue? Your SKILL.md file is 1278 lines crammed into a single file, which violates the whole layered-architecture principle that keeps skills maintainable and token-efficient.

What's Working Well

  • Utility is maxed out — You're genuinely addressing real GitHub project management gaps with the swarm coordination concept. That's the kind of practical value that matters.
  • Ease of Use scores high (24/25) — Your trigger terms ("github project management", "swarm-coordination") are solid, metadata is clean, and the workflow steps are numbered clearly.
  • Examples and templates are comprehensive — You've got input/output pairs and concrete checklists, which makes this actually usable rather than theoretical.
  • Workflow clarity — The numbered step-by-step approach in your examples makes it clear how to actually invoke this thing.

The Big One: Massive SKILL.md File

This is THE blocker. At 1278 lines in a single file, you're violating Progressive Disclosure Architecture (PDA). Here's the deal: Claude skills need to follow a layered structure where SKILL.md is a concise overview (think 150-250 lines max) and detailed implementation lives in a references/ directory.

Concrete fix:

  1. Create a github-project-management/references/ directory
  2. Move detailed sections into separate files:
    • references/swarm-topologies.md — Your topo...

Report Security Issue

Found a security vulnerability in this agent skill?