REPLACE WITH WORKFLOW NAME

Organization

NVIDIA-TAO

REPLACE-WITH-WORKFLOW-NAME

Top-level workflow orchestrator for <use case>. Runs an end-to-end pipeline of <N> stages: <stage 1> → <stage 2> → … → <stage N>. Use when the user asks to "REPLACE-WITH-INTENT-1", "REPLACE-WITH-INTENT-2", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases.

Overview

Publisher	NVIDIA-TAO
Repository	`tao-skill-bank`
Skill name	`REPLACE-WITH-WORKFLOW-NAME`
Stars	98
Forks	28
Bundled files	Instructions only
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by NVIDIA-TAO on GitHub. Read the source before you install it.

Installation

Install the REPLACE WITH WORKFLOW NAME 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/NVIDIA-TAO/tao-skill-bank/tree/main/templates/skill-skeleton/workflow
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/NVIDIA-TAO/tao-skill-bank/tree/main/templates/skill-skeleton/workflow

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/NVIDIA-TAO/tao-skill-bank.git /tmp/tao-skill-bank
mkdir -p .claude/skills
cp -r /tmp/tao-skill-bank/templates/skill-skeleton/workflow .claude/skills/REPLACE-WITH-WORKFLOW-NAME

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

Use it in TypingMind

Enable REPLACE WITH WORKFLOW NAME 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 REPLACE WITH WORKFLOW NAME 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 REPLACE WITH WORKFLOW NAME 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.

Skill Name

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

High-level description of what this workflow accomplishes end-to-end.

External dependencies

Dependency	Purpose	Install
docker	Run sub-skill containers	https://docs.docker.com/engine/install/

Plus everything the sub-skills require — see "Related skills" below.

Related skills

This workflow invokes:

tao-skill-bank:<skill-1> —
tao-skill-bank:<skill-2> —
tao-skill-bank:<platform> — platform execution

Quick start

Default run


> Run the <workflow-name> workflow on <user-data-description>.

The orchestrator collects inputs, validates them, then dispatches the stages below.

With custom KPI / parameters


> Run the <workflow-name> workflow with KPI <metric < target>, max_iterations=3.

Resume after crash


> Resume the in-progress <workflow-name> run at <storage_root>.

State persists in <storage_root>/<state_file>.json — orchestrator reads on startup.

Inputs

Input	Required	Description
`<input-1>`	Yes	...
`<input-2>`	No	...

Stages

Stage 1:

Skill: tao-skill-bank:<skill>
Input:
Output:
Condition: when this stage runs (always / conditional)

Stage 2:

(similar structure)

Storage layout


<storage_root>/
├── stage_1_output/
└── stage_2_output/

Iteration control (if applicable)

Termination condition: KPI / metric / turn count.
State management: how iteration N's output flows into iteration N+1.
Checkpointing: how to resume after a crash.

Instructions

When the user asks to run this workflow, follow these steps in order:

Step 1 — Gather inputs

Confirm with the user:

<input-1>: Path / value.
<input-2>: Path / value (optional, default <value>).

Verify inputs exist:

bash
ls <path>

Step 2 — Run the pipeline

Dispatch each stage in order. Read each sub-skill's SKILL.md for its specific invocation.

Step 3 — Report results

After completion, report metrics + output path to the user.

Known pitfalls

Stage	Symptom	Cause	Fix
	...	...	...

Frequently asked questions

What does the REPLACE WITH WORKFLOW NAME AI skill do?

Why use REPLACE WITH WORKFLOW NAME on TypingMind?

Because you install it once and use it with any model. REPLACE WITH WORKFLOW NAME 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 REPLACE WITH WORKFLOW NAME in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NVIDIA-TAO/tao-skill-bank/tree/main/templates/skill-skeleton/workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use REPLACE WITH WORKFLOW NAME?

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 REPLACE WITH WORKFLOW NAME?

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

Is the REPLACE WITH WORKFLOW NAME AI skill free?

Yes. It is published on GitHub by NVIDIA-TAO 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

Feishu Drive

openclaw

OrganizationPopular

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

Feishu Wiki

Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.

Wacli

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

Himalaya

Himalaya CLI for IMAP/SMTP mail: list, read, search, compose, reply, forward, copy, move, delete.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Skill Name

External dependencies

Related skills

Quick start

Default run

With custom KPI / parameters

Resume after crash

Inputs

Stages

Stage 1:

Stage 2:

Storage layout

Iteration control (if applicable)

Instructions

Step 1 — Gather inputs

Step 2 — Run the pipeline

Step 3 — Report results

Known pitfalls

Frequently asked questions

Related AI Skills

Set up your own AI workspace now