{"id":48525565,"url":"https://github.com/waldronlab/ai-agent-skills","last_synced_at":"2026-04-07T22:30:23.717Z","repository":{"id":348983164,"uuid":"1200595206","full_name":"waldronlab/ai-agent-skills","owner":"waldronlab","description":"A collection of AI agent skills relevant to our work, including analysis and development of R/Bioconductor packages + statistical and bioinformatic analysis.","archived":false,"fork":false,"pushed_at":"2026-04-03T18:01:39.000Z","size":116,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-03T19:35:25.959Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/waldronlab.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-03T15:46:20.000Z","updated_at":"2026-04-03T18:01:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/waldronlab/ai-agent-skills","commit_stats":null,"previous_names":["waldronlab/ai-agent-skills"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/waldronlab/ai-agent-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/waldronlab%2Fai-agent-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/waldronlab%2Fai-agent-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/waldronlab%2Fai-agent-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/waldronlab%2Fai-agent-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/waldronlab","download_url":"https://codeload.github.com/waldronlab/ai-agent-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/waldronlab%2Fai-agent-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31532074,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"ssl_error","status_checked_at":"2026-04-07T16:28:06.951Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-04-07T22:30:21.286Z","updated_at":"2026-04-07T22:30:23.711Z","avatar_url":"https://github.com/waldronlab.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# waldronlab AI Agent Skills\n\nA collection of agent-agnostic skills and instructions for AI assistants (Claude Code, GitHub Copilot, and future platforms) working on projects relevant to the Waldron Lab at CUNY SPH. This repository provides domain-specific knowledge to help AI agents understand our codebases, workflows, and standards.\n\n## What are AI Agent Skills?\n\nSkills are structured instructions that teach AI agents about:\n- Package structures and conventions\n- Analysis workflows and best practices\n- Data types and their handling\n- Testing and documentation standards\n- Organization-wide patterns\n\nWith these skills, AI agents can:\n- Generate appropriate documentation\n- Follow Bioconductor coding standards\n- Suggest context-aware improvements\n- Understand domain-specific patterns\n- Provide better assistance on complex tasks\n\n## Agent-Agnostic Design\n\nSkills in this repository are **agent-agnostic** by design. They work across multiple AI agents through natural language invocation:\n\n- **Canonical invocation**: Natural language matching skill descriptions\n- **Optional shortcuts**: Platform adapters document conveniences (slash commands, @workspace patterns)\n- **Single source**: One skill works everywhere without duplication\n- **Portable**: Skills adapt to any compliant agent platform\n\nSee [AGENTS.md](AGENTS.md) for how agent behavior and skill discovery work. See [SKILL_STANDARD.md](SKILL_STANDARD.md) for technical format details.\n\n## Quick Start\n\n### 1. Find Skills\n\nBrowse [SKILLS.md](SKILLS.md) to see all available skills organized by category and use case.\n\n### 2. Invoke Naturally\n\nDescribe what you need in natural language:\n- \"Help me create a new skill\"\n- \"Analyze this R package\"\n- \"Create .github/instructions for this package\"\n\nYour AI agent will match your request to the appropriate skill and execute it.\n\n### 3. Optional Platform Shortcuts\n\nIf you prefer shortcuts:\n- **Claude Code**: `/skill-name` slash commands (see [instructions/claude.md](instructions/claude.md))\n- **GitHub Copilot**: `@workspace` patterns (see [instructions/copilot.md](instructions/copilot.md))\n\nBut natural language works everywhere.\n\n## Available Skills\n\nSee [SKILLS.md](SKILLS.md) for the complete skill catalog organized by category and use case.\n\n**Skill domains:**\n- **Meta** - Repository infrastructure (skill creation, validation, documentation)\n- **R/Bioconductor** - Package analysis and documentation generation\n- **Metagenomics** (Planned)\n- **Statistical Methods** (Planned)\n\n## Installation\n\nSee the appropriate guide for your platform:\n- **Claude Code**: [instructions/claude.md](instructions/claude.md)\n- **GitHub Copilot**: [instructions/copilot.md](instructions/copilot.md)\n- **Google Gemini**: [instructions/gemini.md](instructions/gemini.md)\n- **Other agents**: [AGENTS.md](AGENTS.md) for compliance requirements\n\nEach guide includes complete setup instructions specific to that platform.\n\n### Verify Installation\n\nAsk your agent:\n- \"Do I have the waldronlab skills?\"\n- \"What waldronlab skills are available?\"\n\nThe agent should list the installed skills.\n\n## Usage Examples\n\n### Creating R Package Instructions\n\nNatural language invocation (works everywhere):\n```\n\"Create .github/instructions for this R package\"\n```\n\nOr use optional shortcuts:\n- Claude Code: `/create-package-instructions`\n- GitHub Copilot: `@workspace Create .github/instructions`\n\n### Analyzing an R Package\n\nNatural language invocation:\n```\n\"Analyze this R package\"\n\"What type of R package is this?\"\n```\n\nOr use optional shortcuts:\n- Claude Code: `/analyze-r-package`\n- GitHub Copilot: `@workspace analyze this package`\n\n### Creating a New Skill\n\nNatural language invocation:\n```\n\"Help me create a new skill for [purpose]\"\n```\n\nOr use optional shortcuts:\n- Claude Code: `/create-skill`\n- GitHub Copilot: `@workspace create a new skill`\n\nSee [SKILLS.md](SKILLS.md) for all available skills and invocation examples.\n\n## Repository Structure\n\n```\nai-agent-skills/\n├── README.md                      # This file\n├── LICENSE                        # MIT License\n├── AGENTS.md                      # Agent behavior standard (how discovery works)\n├── SKILLS.md                      # Human-readable skill index (what skills exist)\n├── SKILL_STANDARD.md              # Technical format spec (how to format skills)\n├── CONTRIBUTING.md                # Contribution guidelines\n├── CHANGELOG.md                   # Version history and release notes\n│\n├── skills/                        # All skills (flat structure)\n│   ├── {skill-name}/              # Each skill in its own directory\n│   │   ├── SKILL.md               # Skill documentation (required)\n│   │   ├── templates/             # Optional supporting files\n│   │   └── examples/              # Optional examples\n│   └── ... (see SKILLS.md for complete list)\n│\n└── instructions/                  # Platform adapters (thin wrappers)\n    ├── README.md                  # Adapter purpose and requirements\n    ├── claude.md                  # Claude Code setup and shortcuts\n    ├── copilot.md                 # GitHub Copilot setup and shortcuts\n    └── gemini.md                  # Google Gemini (placeholder)\n```\n\n## Key Documentation\n\n- **[AGENTS.md](AGENTS.md)** - How agents discover and invoke skills (mandatory behavior)\n- **[SKILLS.md](SKILLS.md)** - Complete skill catalog organized by domain\n- **[SKILL_STANDARD.md](SKILL_STANDARD.md)** - Technical format for creating skills\n- **[CONTRIBUTING.md](CONTRIBUTING.md)** - How to contribute new skills or improvements\n- **[CHANGELOG.md](CHANGELOG.md)** - Version history and release notes\n- **[instructions/](instructions/)** - Platform-specific setup and shortcuts\n\n## Examples\n\nSee [skills/create-package-instructions/examples/](skills/create-package-instructions/examples/) for complete examples of generated instructions from real waldronlab packages:\n\n- **data-package-parquet** - parkinsonsMetagenomicData with remote parquet access via DuckDB\n- More examples coming soon...\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n### Adding New Skills\n\n**Quick start**: Use the `create-skill` skill to get guided help!\n\nNatural language: \"Help me create a new skill for [purpose]\"\n\nOr manually:\n1. Create directory: `skills/{skill-name}/`\n2. Create file: `skills/{skill-name}/SKILL.md`\n3. Follow the [Agent Skills Standard Format](SKILL_STANDARD.md)\n4. Include YAML frontmatter with required fields (no `platforms:` or `triggers:`)\n5. Write platform-agnostic core logic\n6. Run `validate-skill` to check standards compliance\n7. Run `document-skill` to update SKILLS.md automatically\n8. Test on multiple platforms\n9. Submit PR for review\n\n### Adding New Domains\n\nIf you have a new category of skills:\n\n1. Create skills with the new `category:` value\n2. Add domain description to [SKILLS.md](SKILLS.md)\n3. Include at least one working skill with examples\n4. Submit PR for review\n\n## Maintenance\n\n### Ownership\n\nDomain maintainers are responsible for:\n- Reviewing PRs for their skills\n- Keeping skills up-to-date\n- Testing on supported platforms\n- Responding to issues\n\n### Version Compatibility\n\nWe aim to keep skills compatible with:\n- **Claude Code**: Latest stable version\n- **GitHub Copilot**: Latest VS Code extension\n- **R/Bioconductor**: Current release and devel\n\nBreaking changes are documented in [CHANGELOG.md](CHANGELOG.md).\n\n## Support and Feedback\n\n- **Issues**: Report bugs or request features via [GitHub Issues](https://github.com/waldronlab/ai-agent-skills/issues)\n- **Discussions**: Ask questions in [GitHub Discussions](https://github.com/waldronlab/ai-agent-skills/discussions)\n- **Skills Check**: Use `check-waldronlab-skills` to verify your setup\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n## Acknowledgments\n\nThese skills are developed and maintained by the waldronlab at CUNY SPH and collaborators to make AI agents more effective collaborators.\n\n---\n\n**Version**: 2.0.0 (agent-agnostic)\n**Last Updated**: 2026-04-03\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwaldronlab%2Fai-agent-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwaldronlab%2Fai-agent-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwaldronlab%2Fai-agent-skills/lists"}