How do I install the Pi05 Libero skill?

Run npx skillmds@latest add graph-robots/pi05-libero in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pi05 Libero safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pi05 Libero?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pi05 Libero free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pi05 Libero?

graph-robots (@graph-robots) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pi05 Libero by graph-robots — Agent Skill

Name: Pi05 Libero
Author: graph-robots

Pi05 Libero

Run the openpi π0.5 LIBERO checkpoint (pi05_libero) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras; the policy server is the bundle's own preset (no policy_id). Reads the graph-scoped observation_stream each window and terminates on a gripper open→close→open cycle, a VLM yes/no check, or max_windows. Use when a pick/place (or pick-and-drop-in-container) segment on tabletop rigid LIBERO objects is delegated to a learned policy — best steered (perceive + hover above the target) first. NOT for deformables/cloth folding, articulated objects, non-Franka embodiments, or tasks outside the LIBERO pick-place distribution.

graph-robots 6355311 6 files · 950.0 KB Updated Sep 17, 2026

File contents

pi05-libero

Closed-loop VLA-policy skill backed by one model checkpoint: openpi's π0.5 LIBERO checkpoint (pi05_libero). The skill is the model — it owns its serving preset (pi05-libero), so a policy node names this skill, not a free-floating policy_id. The closed-loop replan/execute/terminate body and the load-bearing LIBERO observation encoding live in gap.runtime.policy.run_policy_loop; the websocket client is resolved (and cached per preset) through the executor's PolicyExecutor.

Capability

Embodiment: Franka Panda (LIBERO/robosuite), OSC_POSE delta action space [Δx, Δy, Δz, Δrx, Δry, Δrz, gripper]. No embodiment translation happens in the loop — the checkpoint's native action space is forwarded to sim.apply_policy_action.
Tasks: the LIBERO pick-and-place distribution — pick a tabletop rigid object, optionally place/drop it in a container. Works best steered: perceive the target and hover the end-effector above it (preserving the current rotation) before handing over, so the policy starts in-distribution.
Not for: deformables / cloth folding, articulated objects, non-LIBERO embodiments, or tasks the checkpoint never saw. If the task is outside this envelope, pick a different skill or report a missing capability — do not delegate it here and hope.

Serving

The bundle ships its own server.py (vendored from openpi scripts/serve_policy.py) and declares openpi as a git dep in its own pyproject.toml — so this bundle is self-contained: no $GAP_OPENPI_DIR clone, no shared venv. First-run setup is gap skills install pi05-libero, which uv syncs the bundle's .venv/ with all model deps. The launcher then spawns the server via uv run --project policies/pi05-libero -- python server.py ... (so the bundle's own venv activates automatically) and downloads the checkpoint from s3://openpi-assets/checkpoints/pi05_libero on first run.

Run it yourself with gap policy serve pi05-libero. A policies: config entry named pi05-libero overrides the recipe (e.g. an external url:).

Termination & exits

The loop exits on whichever fires first — a commanded gripper open→close→open cycle (gripper_cycle, the per-item terminator for clean-all loops; set gripper_cycle_termination: true), a non-empty termination_prompt answered yes by the VLM (completed_by_vlm), or the max_windows backstop. These are the subgraph's success exits; the failure exit is failed (the loop raised). Whether the task actually succeeded is a checkpoint, not an exit — attach a postcondition that checks the world (e.g. the object is in the container), never an exit value like "folded".

---name: pi05-liberodescription: Run the openpi π0.5 LIBERO checkpoint (pi05_libero) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras; the policy server is the bundle's own preset (no policy_id). Reads the graph-scoped observation_stream each window and terminates on a gripper open→close→open cycle, a VLM yes/no check, or max_windows. Use when a pick/place (or pick-and-drop-in-container) segment on tabletop rigid LIBERO objects is delegated to a learned policy — best steered (perceive + hover above the target) first. NOT for deformables/cloth folding, articulated objects, non-Franka embodiments, or tasks outside the LIBERO pick-place distribution.---# pi05-liberoClosed-loop VLA-policy skill backed by **one model checkpoint**: openpi'sπ0.5 LIBERO checkpoint (`pi05_libero`). The skill *is* the model — it ownsits serving preset (`pi05-libero`), so a policy node names this skill, not afree-floating `policy_id`. The closed-loop replan/execute/terminate body andthe load-bearing LIBERO observation encoding live in`gap.runtime.policy.run_policy_loop`; the websocket client is resolved (andcached per preset) through the executor's `PolicyExecutor`.## Capability- **Embodiment:** Franka Panda (LIBERO/robosuite), OSC_POSE delta action space `[Δx, Δy, Δz, Δrx, Δry, Δrz, gripper]`. No embodiment translation happens in the loop — the checkpoint's native action space is forwarded to `sim.apply_policy_action`.- **Tasks:** the LIBERO pick-and-place distribution — pick a tabletop rigid object, optionally place/drop it in a container. Works best *steered*: perceive the target and hover the end-effector above it (preserving the current rotation) before handing over, so the policy starts in-distribution.- **Not for:** deformables / cloth folding, articulated objects, non-LIBERO embodiments, or tasks the checkpoint never saw. If the task is outside this envelope, pick a different skill or report a missing capability — do not delegate it here and hope.## ServingThe bundle ships its own `server.py` (vendored from openpi `scripts/serve_policy.py`)and declares `openpi` as a git dep in its own `pyproject.toml` — so thisbundle is **self-contained**: no `$GAP_OPENPI_DIR` clone, no shared venv.First-run setup is `gap skills install pi05-libero`, which `uv sync`s thebundle's `.venv/` with all model deps. The launcher then spawns the servervia `uv run --project policies/pi05-libero -- python server.py ...` (so thebundle's own venv activates automatically) and downloads the checkpoint from`s3://openpi-assets/checkpoints/pi05_libero` on first run.Run it yourself with `gap policy serve pi05-libero`. A `policies:` configentry named `pi05-libero` overrides the recipe (e.g. an external `url:`).## Termination & exitsThe loop exits on whichever fires first — a commanded gripperopen→close→open cycle (`gripper_cycle`, the per-item terminator forclean-all loops; set `gripper_cycle_termination: true`), a non-empty`termination_prompt` answered yes by the VLM (`completed_by_vlm`), or the`max_windows` backstop. These are the subgraph's success exits; the failureexit is `failed` (the loop raised). **Whether the task actually succeeded isa checkpoint, not an exit** — attach a postcondition that checks the world(e.g. the object is in the container), never an exit value like "folded".

Frequently asked questions