Core Workflows

Organization

VectorSpaceLab

core-workflows

Build and debug Acme core dm_env loops, specs, wrappers, logging, counting, observers, and simple custom Actor/Learner components.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`core-workflows`
Stars	341
Forks	26
Bundled files	4
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.
4 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 Core Workflows 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/sub-skills/core-workflows
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/sub-skills/core-workflows

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/sub-skills/core-workflows .claude/skills/core-workflows

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

Use it in TypingMind

Enable Core Workflows 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 Core Workflows 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 Core Workflows 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 Core Workflows

Use this sub-skill when an agent needs to assemble or debug the framework-level Acme loop before choosing a JAX, TensorFlow/Sonnet, or distributed backend.

Read First

Start with Core API contracts for exact signatures, method ordering, and import surfaces.
Use Core workflows for adapting Gym-like environments, building a minimal Actor, wiring EnvironmentLoop, wrappers, loggers, counters, and observers.
Use Core troubleshooting when loop bounds, specs, dtypes, wrapper behavior, logger timing, or optional backend imports fail.
Run check_core_imports.py to inspect the local Acme installation without requiring JAX/TF/Reverb/Launchpad execution.

Scope

This sub-skill covers:

acme.core.Actor, Learner, VariableSource, Saveable, and Worker component contracts.
acme.specs aliases and make_environment_spec(environment) for dm_env environments.
acme.EnvironmentLoop and acme.environment_loop.EnvironmentLoop single-environment interaction.
Core wrappers from acme.wrappers, especially GymWrapper, SinglePrecisionWrapper, CanonicalSpecWrapper, EnvironmentWrapper, and wrap_all.
acme.utils.counting.Counter, acme.utils.loggers, acme.utils.observers, and signal-safe loop termination basics.

Route elsewhere:

Replay adders, Reverb tables, datasets, and iterator pipelines belong in replay-and-data.
JAX networks, builders, experiments, and agent-specific JAX behavior belong in jax-agents.
TensorFlow/Sonnet agents and Launchpad-backed TF examples belong in tf-agents.

Quick Routing

If the user has a custom environment, first make it implement dm_env.Environment or wrap it with acme.wrappers.GymWrapper, then verify observation_spec(), action_spec(), reward_spec(), and discount_spec().
If the user has a loop failure, check EnvironmentLoop.run() bounds, action/spec dtype compatibility, and whether optional imports are failing before the loop starts.
If the user needs metrics, prefer Counter, a Logger implementation, and EnvLoopObserver instances instead of modifying EnvironmentLoop internals.
If the user asks for a complete learning agent, keep this sub-skill focused on the Actor/Learner interface and route backend-specific network or replay decisions to the backend/data sub-skills.

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 Core Workflows AI skill do?

Build and debug Acme core dm_env loops, specs, wrappers, logging, counting, observers, and simple custom Actor/Learner components.

Why use Core Workflows on TypingMind?

Because you install it once and use it with any model. Core Workflows 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 Core Workflows 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/sub-skills/core-workflows. 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 Core Workflows?

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 Core Workflows?

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

Is the Core Workflows 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

Prototype Openclaw Tui

openclaw

OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

Slacrawl

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Obsidian Vault Maintainer

openclaw

OrganizationPopular

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

Control Ui

Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Acme Core Workflows

Read First

Scope

Quick Routing

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now