Acme

Organization

VectorSpaceLab

acme

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`acme`
Stars	341
Forks	26
Bundled files	22
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
22 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by VectorSpaceLab on GitHub. Read the source before you install it.

Installation

Install the Acme AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/acme
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/acme

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git /tmp/AREX-Skill
mkdir -p .claude/skills
cp -r /tmp/AREX-Skill/skills/repositories/repo-skills/acme .claude/skills/acme

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acme in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Acme on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Acme is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Acme Repo Skill

Use this repo skill when a user asks about DeepMind Acme (dm-acme), Acme-style reinforcement-learning agents, dm_env loops, Reverb adders, Acme JAX experiments, or Acme TensorFlow/Sonnet agents.

Start Here

Read references/repo-provenance.md before deciding whether this skill matches a current checkout or should be refreshed.
Read references/package-overview.md for install extras, public dependency groups, repository capability map, and optional-backend expectations.
Read references/troubleshooting.md for cross-cutting install/import, optional dependency, backend, and example-runtime failures.
Run python scripts/check_acme_skill_runtime.py --help for a bundled, dependency-light helper that explains package import checks and available sub-skill helper scripts.

Route By Task

Core loops/specs/wrappers: use sub-skills/core-workflows/SKILL.md for dm_env specs, Actor/Learner, EnvironmentLoop, wrappers, loggers, counters, observers, and simple custom loop debugging.
Replay and data: use sub-skills/replay-and-data/SKILL.md for Adder contracts, Reverb adders, replay tables, dataset iterators, TFDS/offline data, and transition/sequence/episode shape decisions.
JAX agents: use sub-skills/jax-agents/SKILL.md for Acme JAX algorithms, acme.jax.experiments, Haiku/Optax/RLax networks, online/offline/distributed JAX workflows, and JAX multiagent examples.
TensorFlow agents: use sub-skills/tf-agents/SKILL.md for Acme TensorFlow/Sonnet algorithms, TF losses, TF savers/snapshotters, Launchpad TF examples, and TF learner debugging.

Install Baseline

Distribution name: dm-acme; import package: acme; snapshot version: 0.4.1.
Minimal package metadata lists core requirements: absl-py, dm-env, dm-tree, numpy, pillow, and typing-extensions.
Real agent execution usually needs optional extras: dm-acme[jax] for JAX agents, dm-acme[tf] for TensorFlow/Reverb/Launchpad agents, and dm-acme[envs] for example environments.
Treat optional extras as backend/runtime choices, not as always-required imports. Many examples require Gym, bsuite, Control Suite, Atari ROMs, OpenSpiel, Reverb servers, Launchpad launch modes, or long training budgets.

Minimal Import Check

bash
python - <<'PY'
import acme
from acme import specs
print(acme.__version__)
print(specs.Array((2,), float))
PY

If this fails with ModuleNotFoundError for jax, tensorflow, reverb, launchpad, gym, bsuite, or environment packages, read references/troubleshooting.md before broadening installs.

Skill Boundaries

This skill is for using, adapting, troubleshooting, and explaining Acme as an RL framework; it is not a benchmark reproduction plan and does not verify long training results.
Do not route generic RL theory questions here unless the task names Acme APIs, Acme examples, or Acme-style builders/adders/loops.
Do not tell future agents to open or run original repository files. This skill distills the repo evidence into bundled references and scripts.
For source drift, compare current commit, dirty state, package metadata, and evidence paths with references/repo-provenance.md, then run refresh-repo-skill if they differ.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Acme AI skill do?

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

Why use Acme on TypingMind?

Because you install it once and use it with any model. Acme is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Acme in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/acme. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Acme?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Acme?

As many as you like. As long as a model supports skills, you can use Acme with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Acme AI skill free?

Yes. It is published on GitHub by VectorSpaceLab under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Deslop

openclaw

OrganizationPopular

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Discrawl

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Acme Repo Skill

Start Here

Route By Task

Install Baseline

Minimal Import Check

Skill Boundaries

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now