Agent skill
github-repo-setup
Use PROACTIVELY when user needs to create a new GitHub repository or set up a project with best practices. Automates repository creation with four modes - quick public repos (~30s), enterprise-grade with security and CI/CD (~120s), open-source community standards (~90s), and private team collaboration with governance (~90s). Not for existing repo configuration or GitHub Actions workflow debugging.
Install this agent skill to your Project
npx add-skill https://github.com/cskiro/claudex/tree/main/plugins/github-repo-setup/skills/github-repo-setup
SKILL.md
GitHub Repository Setup
Overview
This skill automates GitHub repository creation following official best practices (2024-2025). It provides four modes tailored to different use cases with appropriate security, documentation, and CI/CD configurations.
Four Modes:
- Quick Mode - Fast public repo with essentials (~30s)
- Enterprise Mode - Production-ready with full security and CI/CD (~120s)
- Open Source Mode - Community-focused with templates and guidelines (~90s)
- Private/Team Mode - Internal collaboration with CODEOWNERS and governance (~90s)
When to Use This Skill
Trigger Phrases:
- "create a GitHub repository"
- "set up a new GitHub repo"
- "initialize GitHub repo with best practices"
- "create an enterprise/open source/private repository"
Use Cases:
- Starting new projects with GitHub best practices
- Setting up open source projects with community health files
- Creating team repositories with governance and security
Response Style
- Efficient: Automate repetitive setup tasks
- Guided: Clear mode selection with trade-offs
- Security-first: Enable protection features by default
Quick Decision Matrix
| User Request | Mode | Setup Time | Key Features |
|---|---|---|---|
| "quick repo", "experiment" | Quick | ~30s | README, LICENSE, .gitignore |
| "production repo", "CI/CD" | Enterprise | ~120s | Security + CI/CD + protection |
| "open source project" | Open Source | ~90s | Community templates |
| "private team repo" | Private/Team | ~90s | CODEOWNERS + governance |
Mode Detection Logic
if (userMentions("quick", "test", "experiment")) return "quick-mode";
if (userMentions("enterprise", "production", "ci/cd")) return "enterprise-mode";
if (userMentions("open source", "oss", "public")) return "open-source-mode";
if (userMentions("private", "team", "internal")) return "private-team-mode";
return askForModeSelection();
Modes
| Mode | Description | Details |
|---|---|---|
| Quick | Minimal setup for experiments | → modes/quick-mode.md |
| Enterprise | Full security and CI/CD | → modes/enterprise-mode.md |
| Open Source | Community health files | → modes/open-source-mode.md |
| Private/Team | CODEOWNERS and governance | → modes/private-team-mode.md |
Core Workflow
- Mode Selection - Detect intent or ask user
- Prerequisites - Validate gh CLI, auth, git config
- Repository Creation - Create via GitHub CLI
- Security Setup - Enable Dependabot, secret scanning
- Documentation - Generate README, LICENSE, .gitignore
- CI/CD - Configure workflows (enterprise/open-source)
- Templates - Add issue/PR templates
- Protection - Set branch rules (enterprise/team)
- Validation - Verify setup and provide next steps
Reference Materials
- Error Handling & Success Criteria
Important Reminders
- Security first - Enable Dependabot and secret scanning by default
- Branch protection - Protect main branch in production setups
- Documentation - Every repo needs README, LICENSE, and .gitignore
- CODEOWNERS - Use for critical files in team repositories
Official Documentation:
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
e2e-testing
Use PROACTIVELY when setting up end-to-end testing, debugging UI issues, creating visual regression suites, or automating browser testing. Uses Playwright with LLM-powered visual analysis, screenshot capture, and fix recommendations. Zero-setup for React, Next.js, Vue, Node.js, and static sites. Not for unit testing, API-only testing, or mobile native apps.
sub-agent-creator
Use PROACTIVELY when creating specialized Claude Code sub-agents for task delegation. Automates agent creation following Anthropic's official patterns with proper frontmatter, tool configuration, and system prompts. Generates domain-specific agents, proactive auto-triggering agents, and security-sensitive agents with limited tools. Not for modifying existing agents or general prompt engineering.
accessibility-audit
Use PROACTIVELY when user asks for accessibility review, a11y audit, WCAG compliance check, screen reader testing, keyboard navigation validation, or color contrast analysis. Audits React/TypeScript applications for WCAG 2.2 Level AA compliance with risk-based severity scoring. Includes MUI framework awareness to avoid false positives. Not for runtime accessibility testing in production, automated remediation, or non-React frameworks.
otel-monitoring-setup
Use PROACTIVELY when setting up OpenTelemetry monitoring for Claude Code usage tracking, cost analysis, or productivity metrics. Provides local PoC mode (full Docker stack with Grafana) and enterprise mode (centralized infrastructure). Configures telemetry collection, imports dashboards, and verifies data flow. Not for non-Claude telemetry or custom metric definitions.
json-outputs-implementer
Use PROACTIVELY when extracting structured data from text/images, classifying content, or formatting API responses with guaranteed schema compliance. Implements Anthropic's JSON outputs mode with Pydantic/Zod SDK integration. Covers schema design, validation, testing, and production optimization. Not for tool parameter validation or agentic workflows (use strict-tool-implementer instead).
mutation-testing
Use PROACTIVELY when checking if tests catch real bugs, assessing test suite quality, finding weak tests, or measuring mutation score. Validates test effectiveness beyond coverage metrics by introducing code mutations. Supports Stryker (JS/TS), PIT (Java), mutmut (Python). Not for projects without existing test suites.
Didn't find tool you were looking for?