Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@oss-skills-mcp Find an issue in the scikit-learn repo for beginners"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Guided open-source contribution skills, served as an MCP server.
The philosophy: the agent researches, you think and code. Each skill walks the agent through deep research for one stage of the contribution journey — finding issues, reading codebases, writing tests, responding to reviews — while the decisions and the code stay with you. The result is contributions that maintainers actually want to merge, from a human who actually learned the repo.
Works with any MCP client, including goose.
Evaluation
Skill | What it does |
| Assess a repo's health, governance, and trajectory before investing time |
The contribution workflow (roughly in order)
Skill | What it does |
| Find unclaimed issues filed by maintainers, matched to your skills |
| Read the contribution docs and fill knowledge gaps before coding |
| Get an unfamiliar repo building and testing locally |
| Research an issue deeply, then implement it yourself |
| Open a PR that follows the repo's guidelines |
| Understand review feedback and respond to it well |
| Diagnose CI failures in unfamiliar pipelines |
Contribution types
Skill | What it does |
| Add tests for untested code as a standalone contribution |
| Fix documentation gaps verified against the source |
Going deeper
Skill | What it does |
| Learn a codebase and build trust by reviewing others' PRs |
| Move from one-off contributor to regular |
| Find code problems that aren't in the issue tracker |
| Guided tour of a repo's architecture and patterns |
| Learn unfamiliar tech from how the repo actually uses it |
Related MCP server: GitPilot MCP
uvx --from git+https://github.com/chiruu12/oss-skills-mcp oss-skills-mcpCLI
goose configureAdd a Command-Driven Extension with:
Name: oss-skills
Command: uvx --from git+https://github.com/chiruu12/oss-skills-mcp oss-skills-mcp
Desktop
Add a custom extension with:
Type: STDIO
Command: uvx
Arguments: --from git+https://github.com/chiruu12/oss-skills-mcp oss-skills-mcp
Each skill is available as an MCP prompt — invoke oss-find-issue,
oss-contribute, and so on from your client's prompt picker. Two tools are
also exposed for programmatic access:
list_skills() — names and descriptions of all bundled skills
get_skill(name) — full skill content
uv sync
uv run pytestMIT
Return the full content of a skill by name, e.g. "oss-find-issue".
Inputs: name (required). Returns: result
List the bundled OSS contribution skills with their descriptions.
Inputs: no named parameters. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: listing all skills vs. retrieving one by name. No overlap or ambiguity.
Both tools follow a consistent verb_noun pattern (list_skills, get_skill) with clear, predictable naming.
With only 2 tools, the server is minimal for its stated purpose. While the core operations are covered, the surface feels thin and could benefit from additional tools.
The tools cover the essential read operations for a static skills bundle: listing and retrieving details. Missing search or filtering, but not a critical gap for the domain.
Discover GitHub projects welcoming AI agent contributions. Public search and listing reads.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
