New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Physicalai Train Adding A Policy

by open-edge-platform in open-edge-platform/physical-ai-studio

Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies.

Apache-2.0Auto-check passedDevelopment

Install Physicalai Train Adding A Policy

skills CLI
$ npx skills add open-edge-platform/physical-ai-studio --skill physicalai-train-adding-a-policy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install open-edge-platform/physical-ai-studio physicalai-train-adding-a-policy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/open-edge-platform/physical-ai-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/library/physicalai-train-adding-a-policy .claude/skills/physicalai-train-adding-a-policy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
physicalai-train-adding-a-policy
GitHub stars
130
Token cost
~1.4k tokens
SKILL.md length
504 words
Files
2 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies.

  • Works in 9 steps: Read a nearby family first. Study… → Create the three-file split in policies// → Implement the policy interface used by… → …
  • Creating a new policy family with the config/model/policy split
  • SKILL.md covers Workflow, Required checks, Verify and References
  • Calls uv

What it does

Physicalai Train Adding A Policy is an agent skill from open-edge-platform/physical-ai-studio. Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies. Use when creating a new policy family with the config/model/policy split, registering it in the getpolicy factory and package exports, or keeping a policy compatible with Lightning training and export. Covers Pi0.5, Pi0, ACT, GR00T, SmolVLA, and LeRobot-wrapped policies.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/base-classes.md`).

It sits in Development. The repository describes itself as: Physical AI Studio is an end-to-end framework for training robots to perform tasks through imitation learning from human demonstrations. The licence is Apache-2.0.

When your agent uses it

  • Creating a new policy family with the config/model/policy split
  • Registering it in the getpolicy factory and package exports
  • Keeping a policy compatible with Lightning training and export

Example prompts

  • “/physicalai-train-adding-a-policy”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Read a nearby family first. Study policies/pi05/ (current reference implementation): config.py (Pi05Config(Config)), model.py…
  2. Create the three-file split in policies//
  3. Implement the policy interface used by both training and inference through the base Policy
  4. Register the family so both API and CLI users can find it
  5. Prove direct API construction before adding CLI config
  6. Add a training config under library/configs/physicalai/// when the policy is user-facing from the CLI. Wire model.class_path, a…
  7. Wire export only when ready. Add ExportablePolicyMixin and a valid sample input, then follow the physicalai-train-exporting-and-validating…
  8. Add tests under library/tests/unit/policies/ next to existing policy tests: at least one construction/config path and one shape-validation…
  9. Update docs if the policy is user-visible: library/docs/explanation/policy/ and any config/API examples.

What it can do on your machine

Read from SKILL.md and the folder at commit a80e54e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Physicalai Train Adding A Policy loads about 1.4k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from open-edge-platform/physical-ai-studio at commit a80e54e, republished under its Apache-2.0 licence (© open-edge-platform). 504 words, ~1,350 tokens.

Download SKILL.mdSave it as .claude/skills/physicalai-train-adding-a-policy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
physicalai-train-adding-a-policy
description
Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies. Use when creating a new policy family with the config/model/policy split, registering it in the get_policy factory and package exports, or keeping a policy compatible with Lightning training and export. Covers Pi0.5, Pi0, ACT, GR00T, SmolVLA, and LeRobot-wrapped policies.
license
Apache-2.0

Adding a Studio Policy

Policies live in library/src/physicalai/policies/<name>/. Each family is a Lightning-facing Policy wrapping a torch.nn.Module Model, split across three files. Base classes are in policies/base/ (Policy in policy.py, Model in model.py); shared Config types come from Runtime (physicalai.config), while class construction and CLI configuration use jsonargparse (FromConfigMixin, class_path, and init_args) — see the Runtime configuration documentation.

Workflow

  1. Read a nearby family first. Study policies/pi05/ (current reference implementation): config.py (Pi05Config(Config)), model.py (Pi05Model(Model)), policy.py (Pi05(ExportablePolicyMixin, Policy)), preprocessor.py, and any extra modules the architecture needs (e.g. pi_gemma.py). For a deliberately minimal family, policies/act/ is a smaller three-file layout without the VLM stack.

    • Done when: you can name which existing file each new file mirrors.

  2. Create the three-file split in policies/<name>/:

    • config.py — <Name>Config(Config), all hyperparameters as typed fields.
    • model.py — <Name>Model(Model), pure torch.nn.Module logic.
    • policy.py — <Name>(Policy) (add ExportablePolicyMixin only when export is implemented).
    • Done when: from physicalai.policies.<name> import <Name>, <Name>Config, <Name>Model imports cleanly.

  3. Implement the policy interface used by both training and inference through the base Policy:

    • forward(...) — training path; return values compatible with training_step.
    • predict_action_chunk(...) — inference path; return a tensor with the configured action horizon.
    • select_action(...) — use base-class action-queue behavior unless a specialized flow is justified.
    • Done when: shapes match the checks below for a synthetic batch.

  4. Register the family so both API and CLI users can find it:

    • Add exports to policies/__init__.py (__all__ and imports, e.g. <Name>, <Name>Config, <Name>Model).
    • Add the lowercase name to the get_physicalai_policy_class(...) / get_policy(...) dispatch in policies/__init__.py.
    • Done when: from physicalai.policies import <Name>, get_policy works, get_policy("<name>") returns an instance, and --model physicalai.policies.<Name> resolves.

  5. Prove direct API construction before adding CLI config:

    python
    from physicalai.policies import get_policy

policy = get_policy("<name>")
    • Done when: direct construction, config round-trip, and synthetic forward(...) / predict_action_chunk(...) shape checks pass.

  6. Add a training config under library/configs/physicalai/<policy>/<embodiment>/ when the policy is user-facing from the CLI. Wire model.class_path, a data.class_path (usually physicalai.data.lerobot.LeRobotDataModule), and trainer.*. Mirror configs/physicalai/pi05/aloha/default.yaml.

    • Done when: physicalai fit --config configs/physicalai/<policy>/<embodiment>/<config>.yaml --trainer.fast_dev_run=true completes one step.

  7. Wire export only when ready. Add ExportablePolicyMixin and a valid sample input, then follow the physicalai-train-exporting-and-validating skill. If export is intentionally unsupported, say so explicitly in the policy docstring.

  8. Add tests under library/tests/unit/policies/ next to existing policy tests: at least one construction/config path and one shape-validation test.

    • Done when: uv run --no-sync pytest tests/unit/policies -k <name> passes.

  9. Update docs if the policy is user-visible: library/docs/explanation/policy/ and any config/API examples.

Show full SKILL.md (117 more words)Show less

Required checks

Account for every item below (not just "looks fine"):

  • Action shape semantics — batch, horizon/chunk length, and action dimension are correct and unchanged from the family's convention.
  • Observation features — feature names align with dataset/config conventions (data/observation.py: Feature, FeatureType).
  • API construction path — imports, get_policy(...), direct constructor use, and synthetic shape checks pass without CLI involvement.
  • Config path — construction works through the jsonargparse CLI path used by physicalai fit (class_path/init_args) when the policy is CLI-visible.
  • Heavy dependencies — gate large families behind an optional extra in library/pyproject.toml and import lazily, matching pi05/pi0/groot/smolvla.
  • No silent contract changes — do not alter action dims, feature names, or preprocessing without coordinating export/Runtime.

Verify

From library/:

bash
uv run --no-sync pytest tests/unit/policies -k <name>
physicalai fit --config configs/physicalai/<policy>/<embodiment>/<config>.yaml --trainer.fast_dev_run=true
prek run --all-files library/

References

  • references/base-classes.md — the Policy/Model contract and file-split expectations.

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/library/physicalai-train-adding-a-policy of open-edge-platform/physical-ai-studio.

  • SKILL.md
  • references/base-classes.md

Open the folder on GitHubat commit a80e54e

Compare with similar skills

Physicalai Train Adding A Policy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Physicalai Train Adding A Policy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Physicalai Train Adding A Policy this skillopen-edge-platform/physical-ai-studio130—~1.4kAutomated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from open-edge-platform/physical-ai-studio

  • Physicalai Train Exporting And Validating

    open-edge-platform/physical-ai-studio

    Exports and validates Physical AI Studio policies for Runtime deployment.

    130 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Physicalai Train Benchmarking A Policy

    open-edge-platform/physical-ai-studio

    Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics.

    130 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Physicalai Train Training A Policy

    open-edge-platform/physical-ai-studio

    Trains, validates, tests, and runs prediction for Physical AI Studio policies via the library Lightning stack.

    130 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Physicalai Train Working With Datasets

    open-edge-platform/physical-ai-studio

    Works with Physical AI Studio datasets and Lightning datamodules built on the LeRobot format.

    130 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Studio Adding Robot Form UI Fields

    open-edge-platform/physical-ai-studio

    Adds a new interactive robot form UI field for plugin payload schemas.

    130 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Studio Creating A Robot Plugin

    open-edge-platform/physical-ai-studio

    Creates or modifies an external Physical AI robot plugin for Studio.

    130 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Physicalai Train Adding A Policy

What does Physicalai Train Adding A Policy do?

Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies. Physicalai Train Adding A Policy is an agent skill from open-edge-platform/physical-ai-studio. Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies.

When should I use Physicalai Train Adding A Policy?

Physicalai Train Adding A Policy fits situations like: creating a new policy family with the config/model/policy split; registering it in the getpolicy factory and package exports; keeping a policy compatible with Lightning training and export.

How do I install Physicalai Train Adding A Policy in Claude Code?

Run `npx skills add open-edge-platform/physical-ai-studio --skill physicalai-train-adding-a-policy -a claude-code`. Or copy the skill folder (skills/library/physicalai-train-adding-a-policy in open-edge-platform/physical-ai-studio) into .claude/skills/physicalai-train-adding-a-policy in your project. Claude Code loads it when a task matches its description.

How do I install Physicalai Train Adding A Policy in Codex?

Run `npx skills add open-edge-platform/physical-ai-studio --skill physicalai-train-adding-a-policy -a codex`. Or copy the skill folder (skills/library/physicalai-train-adding-a-policy in open-edge-platform/physical-ai-studio) into .agents/skills/physicalai-train-adding-a-policy in your project. Codex loads it when a task matches its description.

Can I use Physicalai Train Adding A Policy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/physical-ai-studio --skill physicalai-train-adding-a-policy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/physicalai-train-adding-a-policy, .gemini/skills/physicalai-train-adding-a-policy, .github/skills/physicalai-train-adding-a-policy and .opencode/skills/physicalai-train-adding-a-policy in your project.

What does Physicalai Train Adding A Policy need to run?

Going by SKILL.md and its folder, Physicalai Train Adding A Policy needs the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Physicalai Train Adding A Policy access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Physicalai Train Adding A Policy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Physicalai Train Adding A Policy use?

Physicalai Train Adding A Policy is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Physicalai Train Adding A Policy use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 378 tokens, read only when the agent opens those files.

What are the alternatives to Physicalai Train Adding A Policy?

Skills that share tags, products or a category with Physicalai Train Adding A Policy: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Physicalai Train Adding A Policy?

open-edge-platform (a GitHub organization) maintains it in open-edge-platform/physical-ai-studio, which has 130 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 9, 2026.

Source: open-edge-platform/physical-ai-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.