TypingMindTypingMindThe best frontend for AI
Replay And Data logo

Replay And Data

Organization
VectorSpaceLab
replay-and-data

Use Acme adders, Reverb replay tables and datasets, offline data iterators, image augmentation, and replay shape troubleshooting.

Overview

PublisherVectorSpaceLab
RepositoryAREX-Skill
Skill namereplay-and-data
Stars
341
Forks
26
Bundled files
4
LicenseApache-2.0
Links
Skill sourceRepository
  • 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 Replay And Data AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/acme/sub-skills/replay-and-data
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/replay-and-data .claude/skills/replay-and-data
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Replay And Data 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 Replay And Data 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 Replay And Data 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.

Replay and Data

Use this sub-skill when an Acme task involves collecting actor experience, writing it to Reverb, reading replay samples into a learner, adapting offline demonstrations, or diagnosing replay/data structure mismatches.

Read First

  • Replay API: Adder contracts, Reverb adder families, signatures, dataset helpers, and expected shapes.
  • Replay workflows: choose transition/sequence/episode/structured adders, build Reverb/TFDS/numpy iterators, and connect learner data.
  • Troubleshooting: optional dependency failures, Reverb table signature errors, sequence/period pitfalls, extras mismatches, and invalid offline data paths.
  • Replay structure helper: validate a JSON description of observation/action/reward/discount/extras nesting and print an adder-family recommendation without importing Reverb.

Route Boundaries

  • Stay here for acme.adders.base, acme.adders.wrappers, acme.adders.reverb.*, acme.datasets.reverb, acme.datasets.tfds, acme.datasets.numpy_iterator, acme.datasets.image_augmentation, and acme.utils.reverb_utils.
  • Use the sibling core-workflows sub-skill for environment-loop basics, wrapper selection, dm_env conversion, experiment scaffolding, or actor/learner process layout before replay details matter.
  • Use the sibling jax-agents or tf-agents sub-skill when the question is which algorithm-specific builder, config, or learner expects a particular replay table or iterator shape.

Fast Choices

  • Pick NStepTransitionAdder for feed-forward learners that train on (observation, action, reward, discount, next_observation, extras) transitions.
  • Pick SequenceAdder for recurrent learners, sequence losses, overlapping unrolls, or learner code that expects time-major/batched trajectories.
  • Pick EpisodeAdder for full-episode imitation/offline pipelines or algorithms that need complete trajectories.
  • Pick StructuredAdder when one actor stream must populate multiple tables or custom item patterns with Reverb structured_writer configs.
  • For offline demonstrations, adapt data into types.Transition batches or Reverb-compatible samples, then expose an iterator matching the learner constructor.

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 Replay And Data AI skill do?

Use Acme adders, Reverb replay tables and datasets, offline data iterators, image augmentation, and replay shape troubleshooting.

Why use Replay And Data on TypingMind?

Because you install it once and use it with any model. Replay And Data 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 Replay And Data 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/replay-and-data. 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 Replay And Data?

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 Replay And Data?

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

Is the Replay And Data 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.

Related AI Skills

View all
anthropics logo

Pdf

anthropics
OrganizationPopular

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart,…

21.8K
184K
10 files
View
nextlevelbuilder logo

Ui Styling

nextlevelbuilder
OrganizationPopular

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user…

15K
141.1K
95 files
View
garrytan logo

Landing Report

garrytan
CommunityPopular

Read-only queue dashboard for workspace-aware ship. (gstack)

19.9K
133.5K
1 files
View
garrytan logo

Gstack Openclaw Ceo Review

garrytan
CommunityPopular

Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.

19.9K
133.5K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇