GEO Knowledge
SkillDev toolsBuild 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.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the GEO Knowledge skill
What this skill tells your AI
The instructions your AI receives, as published by yaojingang/geohub in skills/geo-knowledge/SKILL.md and read by ahel’s review.
Workflow
- Read
references/knowledge-method.mdand prepare approved source bundles with stable IDs and SHA-256 hashes. - Run
python3 scripts/run_knowledge.py --input <request.json> --output <runs-root>. - Inspect canonical identities, aliases, relation source IDs, validity dates, source coverage, conflicts, and gaps.
- Use the local query for an entity neighborhood or the global query for communities, coverage, conflicts, and gaps.
- For incremental updates, replace only source bundles whose hashes changed and rebuild the governed graph.
Output contract
Produce the input snapshot, knowledge-graph.json, query result, evidence ledger, quality report, lineage, and manifest. Read references/output-contract.md before reuse.
Boundaries
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.
Signals
- GitHub stars
- 159
- Forks
- 27
- Last commit
- Aug 2026
ahel review
K6low
bundled executables the agent is told to run
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Catalog kind
- skill
- Gateway key
geo-knowledge- Source
- github.com/yaojingang/geohub