AGENT SKILL

simulation-data

Routes simulated ALOHA episode generation, replay, visualization, mirroring, compression, and truncation workflows for ACT++ HDF5 data.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
simulation-data
license
MIT
metadata
{ "disco-role": "operating" }
description
Routes simulated ALOHA episode generation, replay, visualization, mirroring, compression, and truncation workflows for ACT++ HDF5 data.
disable-model-invocation
true

02 资源文件 3

03 SKILL.md 正文

simulation-data

Use this sub-skill when the task is about creating, replaying, visualizing, mirroring, compressing, truncating, or validating simulated ACT++ episode data.

Typical triggers

  • "Generate 50 scripted transfer-cube episodes"
  • "Replay episode_0.hdf5"
  • "Mirror and compress the insertion dataset"
  • "Why does sim reset assert on BOX_POSE?"
  • "What fields are in the episode HDF5 file?"

What this sub-skill covers

  • Joint-space and end-effector MuJoCo/DM Control environments.
  • Scripted transfer-cube and insertion demo generation.
  • Replaying HDF5 action traces back into simulation.
  • Rendering videos and qpos plots from HDF5 episodes.
  • Mirroring, JPEG compression, and truncation of episode files.
  • Dataset layout and camera-name conventions for sim files.

What it excludes

  • Model training and checkpoint management, which belong in policy-training.
  • VINN feature caching and k-selection, which belong in vinn-offline.
  • Real-robot alignment, servo diagnostics, and Mobile ALOHA deployment.

Read these first

Run this helper first

Before a long rollout, use check_sim_backend.py to confirm the sim backend can create and reset both environment variants from a chosen checkout.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351