Build and query an evidence-lined GEO knowledge graph from approved source bundles. Use for entity normalization, relation lineage, conflicting fact preservation, incremental source-hash updates, local/global knowledge queries, 知识图谱, 知识库, and 知识治理. Exclude unsourced facts, hidden conflict resolution, autonomous crawling, and external database mutation.
npx skills add https://github.com/yaojingang/GEOHub --skill geo-knowledge
references/knowledge-method.md and prepare approved source bundles with stable IDs and SHA-256 hashes.python3 scripts/run_knowledge.py --input <request.json> --output <runs-root>.Produce the input snapshot, knowledge-graph.json, query result, evidence ledger, quality report, lineage, and manifest. Read references/output-contract.md before reuse.
Execution stays offline and file-backed. Conflicting approved facts remain visible for human review. The Skill never crawls, logs in, mutates an external knowledge base, or silently selects one conflicting value.
Take yaojingang/geo-knowledge from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.