Skills-for-OSS-contributors

作者 DavidOsipov已验证

AI agents skills for OSS contributors

0
Stars
0
Forks
HTML
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/DavidOsipov/Skills-for-OSS-contributors

快速入门

使用 Skills-for-OSS-contributors 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Skills for OSS Contributors

A growing collection of reusable agent skills for contributing to open-source projects and open knowledge ecosystems safely, consistently, and with verifiable workflows.

The repository currently contains one skill for standards-compatible image metadata. Future additions may cover Wikidata and other project-specific OSS contribution workflows.

Available skills

SkillPurpose
XMP Image MetadataInspect images, prepare verified metadata, reverse-geocode coordinates with privacy controls, and embed standards-compatible XMP, IPTC, EXIF, Dublin Core, and PLUS metadata.

Portable XMP Image Metadata

The xmp-image-metadata skill is designed for careful metadata work across JPEG, PNG, WebP, AVIF, HEIC, TIFF, and other ExifTool-writable formats.

It provides:

  • technical image inspection and cross-tool validation;
  • metadata generation through a structured author profile and per-image specification;
  • XMP embedding with original-file preservation;
  • offline-first reverse geocoding and explicit consent before network geocoding;
  • IPTC Media Topic and Digital Source Type lookup;
  • accessibility descriptions, rights and credit fields, and AI-generated-image disclosure;
  • Python scripts with smoke tests, Ruff checks, and mypy type checking.

The skill deliberately does not bundle a creator identity or reusable personal profile. Author, rights, contact, location, and provenance data must come from an authorized private profile and image-specific evidence.

See xmp-image-metadata/SKILL.md for the complete workflow, safety rules, dependencies, and commands.

Using a skill

Each top-level skill directory is intended to be self-contained. Preserve its internal structure when copying or installing it into an agent environment that supports folder-based skills.

<skill-name>/
├── SKILL.md
├── agents/
├── scripts/
├── reference/
└── tests/

Not every future skill will necessarily require every optional directory.

The current skill is identified as:

$xmp-image-metadata

A compatible agent can be prompted to use it for tasks such as:

Use $xmp-image-metadata to inspect this image and prepare
standards-compatible metadata without modifying the original.

Exact discovery and installation steps depend on the agent host. This repository is the source distribution; the authoritative instructions for each skill live in its own SKILL.md.

Local development

Clone the repository:

git clone https://github.com/DavidOsipov/Skills-for-OSS-contributors.git
cd Skills-for-OSS-contributors

Run the current skill's checks:

cd xmp-image-metadata
python3 -m pytest tests -q
python3 -m ruff check scripts tests
python3 -m mypy --ignore-missing-imports --disallow-untyped-defs scripts

The image-metadata workflow also depends on ExifTool 12.46+, ImageMagick, MediaInfo, Pillow, and PyYAML. Run its preflight before using the scripts:

python3 scripts/inspect_image.py --check

Design principles

Skills in this repository should:

  1. encode a concrete, repeatable contribution workflow rather than a vague prompt;
  2. distinguish verified facts from guesses, inherited metadata, and model inference;
  3. minimize destructive actions and preserve original inputs by default;
  4. keep credentials, personal profiles, and project secrets outside distributable skill folders;
  5. prefer authoritative project documentation, specifications, and machine-readable references;
  6. make network access and privacy-sensitive actions explicit;
  7. include validation, failure conditions, and tests where executable tooling is provided.

Planned directions

Potential future skills include:

  • Wikidata item creation and editing;
  • statement sourcing, reference quality, and identifier reconciliation;
  • Wikimedia Commons media preparation and metadata review;
  • project-specific contribution, issue-triage, and pull-request workflows;
  • reusable validation and provenance workflows for other open-source ecosystems.

These are directions for the collection, not a release commitment.

Contributing

Issues and pull requests are welcome.

For a new skill, keep the scope narrow, document its trigger conditions and stop conditions, cite authoritative references, and avoid embedding contributor-specific identity or credentials. Executable helpers should use safe defaults and include proportionate tests.

Changes to bundled standards or vocabularies should record their source and version so that reviewers can verify what changed.

License

This repository is licensed under the MIT License.

Copyright © 2026 David Osipov.

常见问题

What is Skills-for-OSS-contributors?

Skills-for-OSS-contributors is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by DavidOsipov. AI agents skills for OSS contributors. It has 0 GitHub stars.

Is Skills-for-OSS-contributors safe to use?

Yes. Skills-for-OSS-contributors passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install Skills-for-OSS-contributors?

Clone the repository with "git clone https://github.com/DavidOsipov/Skills-for-OSS-contributors" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is Skills-for-OSS-contributors written in?

Skills-for-OSS-contributors is primarily written in HTML. It is open-source under DavidOsipov on GitHub, so you can review or fork the full source.

Are there alternatives to Skills-for-OSS-contributors?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Skills-for-OSS-contributors against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情