SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

Zetta-Embodimentair-embodied-brain/Zetta-Embodiment

Turns failed robot manipulation trajectories into an actionable diagnosis-and-repair loop instead of a single failure-ra…

No ratings yet Rate this skill
Stars1.3k
Forks83
Watchers1.3k
Open Issues9

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/air-embodied-brain/Zetta-Embodiment.git

OverviewOverview

Key Features

Turns failed robot manipulation trajectories into an actionable diagnosis-and-repair loop instead of a single failure-rate number. Key capabilities include: 1. Failed-trajectory clustering: groups complete failed trajectories by symptom so scattered failures collapse into analyzable failure modes; 2. Single-point causal diagnosis: gives one observable causal explanation per failure, stating at which step and why the policy went wrong; 3. Candidate repair generation and critique: a candidate writer produces repair proposals and a critic role challenges them one by one to filter out unsound ones; 4. Recovery action design: designs recovery actions for failed states so the policy can get back on track after an error; 5. Multi-environment regression evaluation: runs the repaired policy in LIBERO-Pro, RoboCasa and ManiSkill environments to confirm the change introduces no new problems.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID921
Data sourceGitHub
Repositoryair-embodied-brain/Zetta-Embodiment
CategoryAI & Agent Skills / Embodied AI & Robotics Evaluation
Primary languagePython
LicenseNot specified
Default branchmain
GitHub repository ID1337915408
Node IDR_kgDOT774EA
Rank#613 (position within the source ranking)
Site-wide popularity rank#704 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05001k1.5k2026-09-302026-10-112026-09-30 · 1,2652026-10-11 · 1,286
  • Now1,286
  • Previous point · 09-30 1,265
  • vs previous point +21
  • 2 data points 11 days
02550751002026-09-302026-10-112026-09-30 · 832026-10-11 · 83
  • Now83
  • Previous point · 09-30 83
  • vs previous point ±0
  • 2 data points 11 days

TimelineTimeline

Repository created2026-08-18 03:05:093 months ago
Data last updated2026-10-26 12:01:0421 days ago
Last commit2026-10-04 11:26:351 months ago

CommitLatest commit

Committed by ZexuWang. Update Category: New Features & Capability Expansion. Commit details: Merge pull request #36 from air-embodied-brain/feat/behavior-support. This update introduces new capabilities and expands supported use cases.

21d7a3a ZexuWang 2026-10-04