Real Skill packageSource verifiedClawHub registry

knowledge-graph

知识图谱全栈——通用 Agent 记忆图谱（CRUD/规划/跨skill通信）+ OWL 语义推理（RDFS/OWL Lite/OWL RL/SPARQL/NL混合查询）

Identity and source

Publisher attributionpaudyyinregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction with code35 recorded files
Canonical sourceClawHub registryclawhub:paudyyin:knowledge-graph
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/24/2026.claude/skills/knowledge-graph

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/24/2026.agents/skills/knowledge-graph

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/24/2026skills/knowledge-graph

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @paudyyin/knowledge-graph
clawhub inspect @paudyyin/knowledge-graph --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
35 / 35 inspected as text
Checked
8/24/2026, 2:01:32 AM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
7 dependency and API indicators
  • pypi: rdflib >=7.0.0
  • pypi: owlrl >=6.2.0
  • pypi: pytest >=7.0.0
  • api: clawhub.ai
  • api: domain-kit.midea.com
  • api: example.org
  • api: www.w3.org
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/3/2026, 1:25:00 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:b4aa13bf1cb40ea649486b9230feaa4a1f71b602905383d798b2eca7f3fb2892
Show up to 30 recorded paths
  • phase0/__init__.py
  • phase0/models.py
  • phase0/namespace.py
  • phase0/registry.py
  • phase1/__init__.py
  • phase1/jsonl_to_rdf.py
  • phase1/rdf_to_jsonl.py
  • phase1/schema_mapping.py
  • phase2/__init__.py
  • phase2/reasoner.py
  • phase3/__init__.py
  • phase3/rule_config.json
  • phase3/rules.py
  • phase4/__init__.py
  • phase4/query_engine.py
  • phase5/__init__.py
  • phase5/hybrid_query.py
  • phase6/__init__.py
  • phase6/export.py
  • references/ARCHITECTURE.md
  • references/queries.md
  • references/schema.md
  • requirements.txt
  • scripts/ontology.py
  • skill-card.md
  • SKILL.md
  • tests/__init__.py
  • tests/test_integration.py
  • tests/test_phase0.py
  • tests/test_phase1.py

Source changelog

Initial release of a full-stack, universal knowledge graph system with semantic reasoning. - Implements an extensible entity-relationship data model with type constraints and append-only JSONL storage. - Provides command-line CRUD, relationship, and validation tools via scripts/ontology.py. - Introduces a 7-phase architecture enabling bi-directional JSONL ↔ RDF conversion, multi-level OWL reasoning, rule engines, SPARQL and natural language querying, and export. - Supports domain-specific, file-based, and memory-based use cases; includes full type/schema config and integration tests. - Documentation covers unified data models, reasoning layers, file structure, CLI usage, namespaces, and cross-skill workflows.