agentleFS
jaccenjaccen/Awesome-Gaussian-Skills/skills/super-agent/SKILL.md

super-agent

Skill186 starsChanged 57 days agoApache-2.0View on GitHub

Design, orchestrate, and debug super agents & multi-agent LLM systems: architecture patterns (router,

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Grammar/constraint-constrained synthesis: when agents generate code or assets, constrain the output space with a formal grammar or template …

    line 49
  2. Distinctive:

    Do NOT claim an agent capability without a verifiable mechanism in the cited paper — every capability claim must map to a library method …

    line 55
  3. Very specific:

    Do NOT copy coordination topologies from memory — re-query data/methods.json (Super Agents & Agentic AI) before recommending

    line 56
  4. Distinctive:

    Do NOT evaluate multi-agent systems with single-agent metrics — pick the matching benchmark from §3

    line 57
  5. Very specific:

    No fabricated benchmark names or numbers.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Super Agent & Multi-Agent System Design

Scope: LLM-agent architecture, multi-agent orchestration, and the 3D/spatial agent cross-section. Knowledge base: 20 indexed methods in the Super Agents & Agentic AI category (data/methods.json, single source of truth — always re-query, never answer from memory).

1. Architecture Pattern Selection

PatternWhen to useLibrary exemplar
On-device super agentEdge deployment, privacy, low latency function callingOctopus v2 [arXiv:2404.01744] — 2B params beating GPT-4 on function-calling accuracy/latency
Agentic pipeline with physical feedbackAsset generation needing physics validityArtisan [arXiv:2610.13947] — multi-agent + simulation feedback for articulated 3D assets
Decentralized swarmEmergent coordination without assigned rolesSwarmWorld [arXiv:2608.26081] — stigmergic self-organization of LLM agents
Safe execution harnessEnterprise policy compliance, partial observabilityE-Ledger [arXiv:2610.11552] — code approval layer + world ledger of verified rules
Paper-to-code research agentReimplementation pipelinesSPLATIFY [arXiv:2610.09116] — 3DGS papers → trainable gsplat code via grammar-constrained multi-agent synthesis

2. 3D / Spatial Agent Integration

TaskMethodKey mechanism
Multi-agent 3D reconstructionCOLMAR [arXiv:2607.13524]Cooperative view-policy learning, overlap-aware coverage
Multi-agent GS SLAMGRAND-SLAM [arXiv:2506.18885]Local-optimization tracking, global consistency outdoors
Agentic 3D object reconstructionGATOR [arXiv:2610.11215]Generative + agentic recovery from casual images, occlusion inference
Autonomous CAD reconstructionCADFather [arXiv:2610.09127]VLM assistant coordinates complementary tools, decides finish
Interactive 3D scene editingDesignAgent3D [arXiv:2608.21438]Designer-like multimodal reasoning, intent disambiguation
Embodied-simulation environment buildingGASE [arXiv:2606.17520]Automated GS reconstruction for sim scenes, minimal sim-to-real gap
VLN generation-evaluation-policyGN0 [arXiv:2606.03682]Unified paradigm on a 3DGS simulation engine (GN-Matrix / GN-Bench)
Robotic photographyPhotoAgent [arXiv:2603.22796]LMM CoT → geometric constraints, reflection in internal world model
Urban planning agentCityPlanner [arXiv:2609.09578]Sandbox-agent: inspect files, generate plans, run evaluators, revise

3. Evaluation & Diagnosis

  • Benchmarks: GISAgentBench (realistic GIS workflows) · WorldBench (Three.js voxel worlds, vision-vs-code judge disagreement) · E3VS-Bench (5-DoF viewpoint-dependent active perception in 3DGS scenes) · MeMoREval (which memory modality to retain) · SkillScriptBench (skill-package self-evolution: doc repair vs script repair vs behavior preservation)
  • Failure diagnosis: coordination failures often hide behind similar symptoms; distinguish information-passing vs information-use vs verification faults before re-orchestrating (see E-Ledger's ledger pattern for verified-rules bookkeeping)
  • Memory design: textual records are not the only option — visual and spatial memory modalities change both information availability and inference cost (MeMoREval protocol: experience first, request later)

4. Design Rules

  1. Topology first: choose centralized / decentralized / hybrid before role design; multi-agent consistency and communication budget dominate architecture
  2. Sandbox over free-form: executable environments with inspect → plan → evaluate → revise loops (CityPlanner, WorldBench) outperform one-shot generation for spatial tasks
  3. Grammar/constraint-constrained synthesis: when agents generate code or assets, constrain the output space with a formal grammar or template (SPLATIFY's context-free grammar over gsplat; Artisan's physical simulation gates)
  4. Policy before autonomy: any agent that acts on external state needs an approval layer and a persistent ledger (E-Ledger)
  5. Competence-aware orchestration: more collaboration is not always better — model the backbone's task-conditioned competence, then decide how much coordination a query deserves

5. Red Lines

  • Do NOT claim an agent capability without a verifiable mechanism in the cited paper — every capability claim must map to a library method with arXiv ID
  • Do NOT copy coordination topologies from memory — re-query data/methods.json (Super Agents & Agentic AI) before recommending
  • Do NOT evaluate multi-agent systems with single-agent metrics — pick the matching benchmark from §3
  • No fabricated benchmark names or numbers; if unverified, mark unverified

6. Related Skills

  • 3dgs-spatial-agent — 3DGS/CAD/Mesh spatial intelligence agent (single-agent spatial reasoning)
  • 3dgs-mcp-renderer — MCP-driven 3DGS rendering/sculpting (tool layer for agents)
  • cad-mesh-3dgs — CAD/Mesh↔3DGS bridging (CADFather's domain substrate)
  • ontology — knowledge representation & neuro-symbolic grounding for agent state
  • 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.