Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides a structured approach to searching and answering questions from local directories containing mixed media. It employs hierarchical index navigation to locate information without loading entire files into memory, making the retrieval process more efficient for large datasets.
By integrating specialized tools like pdfplumber and pandas, the system handles PDFs and Excel spreadsheets through a reference-first learning method. This ensures that data extraction is precise and tailored to the specific structure of each document type.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Make sure kb-retriever is installed in your agent before trying this task.
Use the kb-retriever skill to answer this question from my local knowledge base: “[QUESTION]”. The knowledge-base root is “[PATH]”. Start with its data_structure.md indexes and retrieve only the relevant passages. Replace [QUESTION] with the question to investigate and [PATH] with the actual knowledge-base directory, such as ./docs.
Concrete usage examples and desired trigger phrases
Make sure skill-creator is installed in your agent before trying this task.
Use the skill-creator skill to plan a skill for “[DOMAIN OR TASK]”. First ask me for the most important concrete usage examples and trigger phrases. Then propose the reusable scripts, references, and assets that would support those examples. Do not create files yet. Replace [DOMAIN OR TASK] with the capability the new skill should provide.
Claude