Skip to main content
AgibotTech
Perfil de creador de GitHub

AgibotTech

Vista por repositorio de 27 skills recopiladas en 1 repositorios de GitHub.

skills recopiladas
27
repositorios
1
actualizado
28 ago 2026
mapa de repositorios

Dónde viven las skills

Repositorios principales por número de skills recopiladas, con su participación en este catálogo del creador y su variedad ocupacional.

explorador de repositorios

Repositorios y skills representativas

challenge-download-datasets
sin clasificar

Download the Simulation Challenge LeRobot v2.1 training datasets from ModelScope using ./scripts/download_dataset.sh. Pulls task-suite data (instruction / manipulation / sim2real) from the agibot_world/GenieSim3.0-Dataset repo into a local dir. Trigger: When…

28 ago 2026
challenge-help
sin clasificar

Entry point for the Simulation Challenge skill set. Use when the user mentions the challenge, leaderboard, submitting a model, or any of the /api/challenge/* endpoints — this skill picks the right downstream skill for them.

28 ago 2026
challenge-inference-protocol
sin clasificar

Reference for the Simulation Challenge inference wire protocol — the exact obs (input) and action (output) message format exchanged between the gateway/genie-sim simulator and the contestant's inference agent over the reverse WebSocket tunnel. Covers the…

28 ago 2026
challenge-login
sin clasificar

Use when the contestant needs to obtain or refresh their Simulation Challenge JWT (CHALLENGE_TOKEN), or wants to inspect the current logged-in user. Trigger words include "log in", "token", "401", "current user", "name", "refresh".

28 ago 2026
challenge-poll-result
sin clasificar

Use to track a Simulation Challenge job's progress — list jobs, watch a job's status until terminal, fetch its per-task scores, or pull execution logs when it failed. Read-only; safe to run without confirmation.

28 ago 2026
challenge-ranking
sin clasificar

Use to fetch the contestant's best score and the per-board leaderboard for the Simulation Challenge. Read-only; safe to run without confirmation.

28 ago 2026
challenge-run-agent
sin clasificar

Use when the contestant wants to launch the inference Agent that connects to the Simulation gateway via WebSocket. Wraps the inference repo's ./scripts/tunnel.sh and scales to PARALLELISM processes. This is side-effecting (consumes GPUs and a parallelism…

28 ago 2026
challenge-submit-job
sin clasificar

Use when the contestant wants to submit a model evaluation job to the Simulation Challenge — POST /api/challenge/job. This is a quota-consuming, side-effecting action; always confirm with the user first. Captures JOB_UUID, PARALLELISM, TUNNEL_ENDPOINT for the…

28 ago 2026
Mostrando 8 de 27 skills recopiladas.
Mostrando 1 de 1 repositorios
Todos los repositorios cargados