agentleFS
jaccenjaccen/Awesome-Gaussian-Skills/skills/ontology/SKILL.md

ontology

Skill186 starsChanged 57 days agoApache-2.0View on GitHub

Build and reason over ontologies & structured knowledge representations for 3D/spatial domains: ontology-grounded

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use find-skills.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer open-vocabulary + updatable scene graphs (DynamicGSG) for long-term robot operation in changing environments

    line 41
  2. Distinctive:

    Do NOT claim an ontology/scene-graph capability without a verifiable mechanism in the cited paper — every claim must map to a library …

    line 53
  3. Very specific:

    Do NOT recommend representations from memory — re-query data/methods.json (Ontology & Knowledge Representation) first

    line 54
  4. Distinctive:

    Do NOT promise exact symbolic guarantees from LLM components — LLM outputs enter as soft, verifiable predicates, never as axioms (KLDrive's …

    line 55
  5. Very specific:

    No fabricated method names, arXiv IDs, or benchmark numbers.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ontology & Knowledge Representation for 3D Domains

Scope: ontology engineering and structured knowledge representations applied to 3D scenes, robots, and spatial reasoning. Knowledge base: 12 indexed methods in the Ontology & Knowledge Representation category (data/methods.json, single source of truth — always re-query, never answer from memory).

1. Representation Selection

NeedRepresentationLibrary exemplar
Structured scene memory that updates with changeDynamic 3D Gaussian scene graphDynamicGSG [arXiv:2502.15309]
Cross-scene unification of 3DGS maps3D scene graph registrationGraph-GSReg [arXiv:2606.29782]
Grounded, scalable long-horizon planningOntology-grounded scene representationOntoPlan [arXiv:2610.07649]
End-to-end scene graph without pipelinesDirect 3D scene graph writingGraphWrit3R [arXiv:2609.31595]
Open-plan environments (no wall heuristics)Task/prior-driven probabilistic scene graphsPrior-SG [arXiv:2608.06170]

2. Reasoning over Structured Spatial Knowledge

PatternMethodMechanism
Neuro-symbolic spatial reasoningSATURN [arXiv:2606.22694]Approximate 3D scene reconstruction + soft perspective-aware predicates + training-free Pythonic symbolic executor
KG-augmented driving QAKLDrive [arXiv:2603.21029]Knowledge graph of fine-grained 3D scene facts reduces LLM hallucination
Scene-graph-guided CoTEmbodiedVSR [arXiv:2503.11089]Dynamic scene graphs steer chain-of-thought for zero-shot spatial tasks
Zero-shot 3D path planningHiWE [arXiv:2609.39323]Point-based interface: PointVLM grounding + depth-lifted semantic 3D representation + language planner
Symbolic safety assessmentNEUROSYMLAND [arXiv:2607.02277]Probabilistic semantic scene graph + symbolic constraints (flatness, clearance), edge-deployable
Temporal-logic trajectory generationVision-TL-Action [arXiv:2607.26770]Coordinate-free TL syntax graphs fused with visual tokens via cross-attention
Open-vocabulary manipulation via symbolsGRASP [arXiv:2606.12910]VLM translates natural language → PDDL goals → real-time task-and-motion planning

3. Ontology Construction & Population

  • Robot-ontology population from URDF: LLM-guided extraction of embodied semantics (URDF → populated robot ontology, arXiv:2606.17073 lineage)
  • Design principle from OntoPlan: align objects, spaces, relations, and states in one shared symbolic vocabulary before planning — spatial facts delivered as raw text to an LLM blow up token cost and lose spatial context
  • Prefer open-vocabulary + updatable scene graphs (DynamicGSG) for long-term robot operation in changing environments

4. Design Rules

  1. One vocabulary, many modules: a spatial ontology pays off only when perception, planning, and action all commit to the same symbolic vocabulary
  2. Soft predicates over hard thresholds: noisy perception breaks binary spatial decisions — use soft, perspective-aware predicates (SATURN) with a symbolic executor separated from perception
  3. Scene graphs as the bridge: between raw Gaussians/meshes and symbolic reasoning, the 3D scene graph is the current best-served interface (GraphWrit3R, DynamicGSG, Graph-GSReg, Prior-SG)
  4. Grounding before planning: knowledge must lift to metric space (depth-lifted semantic 3D representation, HiWE) before motion-level use
  5. Update paths are first-class: real environments change; a representation without an update protocol (DynamicGSG's environment adaptation) is a dead map

5. Red Lines

  • Do NOT claim an ontology/scene-graph capability without a verifiable mechanism in the cited paper — every claim must map to a library method with arXiv ID
  • Do NOT recommend representations from memory — re-query data/methods.json (Ontology & Knowledge Representation) first
  • Do NOT promise exact symbolic guarantees from LLM components — LLM outputs enter as soft, verifiable predicates, never as axioms (KLDrive's structured-fact pattern)
  • No fabricated method names, arXiv IDs, or benchmark numbers; if unverified, mark unverified

6. Related Skills

  • super-agent — agentic frameworks that consume these representations (OntoPlan is itself an agentic framework)
  • 3dgs-spatial-agent — spatial intelligence agent (scene understanding substrate)
  • cad-mesh-3dgs — geometry↔Gaussian bridging under the scene graph
  • 3dgs-experiment-planner — designing evaluation for structured-representation papers
  • cg-paper-writing — when writing any of the above up

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.