Skip to content

MiaoDX/roboclaws / skills/scene-gaussian-map-alignment

scene-gaussian-map-alignment

Verified

Align scene Gaussian/splat, USD/mesh, and robot map assets into an honest digital-twin evidence workflow. Use when a new Gaussian scene arrives, when B1/Map12-style assets need to be connected, when map anchors are being projected into a 3D scene, or when an agent must decide whether an alignment is candidate, verified, runtime-proven, or planner-backed.

FileKindSize
SKILL.mdskill md6.2 KB
scripts/summarize_alignment_evidence.pyscript20.1 KB
skill.jsonconfig2.2 KB

skill.json

View on GitHub
{
  "schema": "roboclaws_skill_manifest_v1",
  "name": "scene-gaussian-map-alignment",
  "summary": "Guide scene-specific alignment of Gaussian/splat, USD/mesh, and robot map assets while keeping evidence labels honest.",
  "abstraction_level": "agent_skill",
  "role": "scene_map_alignment",
  "status": "active",
  "mcp": {
    "profiles": ["household_world"],
    "required_tools": [],
    "optional_tools": [],
    "privileged_tools": [],
    "boundary_notes": "This skill operates at the offline scene/map artifact boundary. It may prepare evidence for household-world runs, but alignment judgment and report labeling stay outside public robot capabilities until a stable MCP contract exists."
  },
  "capability_requirements": {
    "profiles": ["household_world"],
    "backend_variants": ["isaaclab_subprocess", "agibot_gdk", "artifact_only"],
    "notes": "The workflow can consume B1/Map12-style assets, future Gaussian scene drops, Isaac render smoke artifacts, and exported robot map bundles."
  },
  "scripts": [
    {
      "path": "scripts/summarize_alignment_evidence.py",
      "kind": "summarizer",
      "summary": "Reads readiness and navigation-smoke artifacts and emits a compact evidence-tier summary without making new alignment claims."
    }
  ],
  "evidence_outputs": [
    "readiness.json",
    "navigation_smoke.json",
    "readiness_with_navigation.json",
    "alignment_evidence_summary.json",
    "alignment_manifest.json",
    "report.html",
    "assets/maps/<map-bundle>/"
  ],
  "lifecycle": {
    "refactor_signals": [
      "multiple scene drops need the same deterministic transform or anchor matching code",
      "manual evidence-tier decisions become repeatable enough to validate in tests",
      "Gaussian rendering moves from inventory evidence into a stable renderer path",
      "semantic anchor to USD object binding has a durable manifest format"
    ],
    "promote_to_mcp_when": [
      "alignment inputs and outputs stabilize across scene providers",
      "public/private artifact boundaries can be enforced in traces",
      "multiple skills need the same online map-to-scene alignment capability",
      "planner-backed evidence can be reported through one contract profile"
    ]
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall