$npx -y skills add opendatahub-io/ai-helpers --skill python-packaging-source-finderUse this skill to locate source code repositories for Python packages by analyzing PyPI metadata, project URLs, and code hosting platforms like GitHub, GitLab, and Bitbucket. Provides deterministic results with confidence levels.
| 1 | # Source Finder |
| 2 | |
| 3 | Locates source code repositories for Python packages with confidence scoring. |
| 4 | |
| 5 | ## Usage |
| 6 | |
| 7 | To find a source repository for a given package: |
| 8 | |
| 9 | 1. Run the finder script, for example: |
| 10 | |
| 11 | ``` |
| 12 | # Find repository |
| 13 | $ ./scripts/finder.py requests |
| 14 | |
| 15 | # Output structure: |
| 16 | { |
| 17 | "url": "https://github.com/psf/requests", |
| 18 | "confidence": "high", |
| 19 | "method": "pypi_metadata_project_urls.Source", |
| 20 | "package_name": "requests" |
| 21 | } |
| 22 | ``` |
| 23 | |
| 24 | 2. Parse the JSON output: |
| 25 | |
| 26 | - `url`: Repository URL (or `null` if not found) |
| 27 | - `confidence`: `high`, `medium`, or `low` |
| 28 | - `method`: How the URL was found |
| 29 | - `package_name`: the package that was searched |
| 30 | |
| 31 | 3. If confidence is `low` or `url` is `null`, use WebSearch: `<package_name> python github repository` |
| 32 | |
| 33 | 4. Present results with confidence level clearly indicated |
| 34 | |
| 35 | ## Output Format |
| 36 | |
| 37 | As a result, provide structured output including: |
| 38 | |
| 39 | - Repository URL |
| 40 | - Confidence level (high/medium/low) |
| 41 | - Method used to find the repository |
| 42 | - Additional context or warnings |