Automationbench Eval

OrganizationPopular

bionic-gpt

automationbench-eval

Load the repository's AutomationBench OpenAPI catalogue and run evaluations against the local simulator.

Overview

Publisher	bionic-gpt
Repository	`bionic-gpt`
Skill name	`automationbench-eval`
Stars	2.4K
Forks	247
Bundled files	1
License	Apache-2.0
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by bionic-gpt on GitHub. Read the source before you install it.

Installation

Install the Automationbench Eval 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/bionic-gpt/bionic-gpt/tree/main/.agents/skills/automationbench-eval
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.

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/bionic-gpt/bionic-gpt.git /tmp/bionic-gpt
mkdir -p .claude/skills
cp -r /tmp/bionic-gpt/.agents/skills/automationbench-eval .claude/skills/automationbench-eval

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

Use it in TypingMind

Enable Automationbench Eval 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 Automationbench Eval 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 Automationbench Eval 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.

AutomationBench evaluation

Use this skill when the user asks to load AutomationBench specs or run an AutomationBench evaluation.

Source of truth

The OpenAPI source files are committed under:

text
crates/integration-simulator/specs/*.openapi.json

The loader normalizes every imported spec to the local simulator at http://integration-simulator:8080/api/<service>. It also removes OpenAPI security declarations, security schemes, and explicit access-token parameters because the simulator is authentication-free. Business parameters are kept.

Load the global spec catalogue

Run the repository loader from the repository root:

bash
bash .agents/skills/automationbench-eval/scripts/load-specs.sh

The script uses DATABASE_URL, falling back to APP_DATABASE_URL. A custom spec directory can be supplied as its first argument:

bash
bash .agents/skills/automationbench-eval/scripts/load-specs.sh \
  crates/integration-simulator/specs

It upserts global rows in integrations.openapi_specs using each file's filename, info.title, info.description, and info.x-logo.url. Rows are active Application specs and are deliberately non-system so they appear in the existing integration selection screen. The loader does not need a team ID or user ID, does not create team integrations, and does not create API-key or OAuth connections.

The loader is safe to rerun. It updates only rows with matching AutomationBench slugs and does not delete unrelated specs or integrations.

After loading, open the Bionic integrations selection screen and select only the services required for the evaluation. The selection screen creates the team-specific integrations using the already-loaded global definitions.

Simulator

The AutomationBench API is provided by the integration-simulator service by the local Stack dev profile. Bionic reaches it inside the cluster at http://integration-simulator:8080. It has one shared deterministic world.

Reset the world before each evaluation:

bash
curl -X POST http://localhost:8880/benchmark/reset \
  -H 'Content-Type: application/json' \
  -d '{"task":"simple.email_sf_contact_phone_update"}'

Use the host port exposed by the local deployment when it differs from 8880. The reset replaces the shared simulator world for all callers.

Bundled files

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

scripts/load-specs.sh3 KB

Frequently asked questions

What does the Automationbench Eval AI skill do?

Load the repository's AutomationBench OpenAPI catalogue and run evaluations against the local simulator.

Why use Automationbench Eval on TypingMind?

Because you install it once and use it with any model. Automationbench Eval 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 Automationbench Eval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bionic-gpt/bionic-gpt/tree/main/.agents/skills/automationbench-eval. 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 Automationbench Eval?

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 Automationbench Eval?

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

Is the Automationbench Eval AI skill free?

Yes. It is published on GitHub by bionic-gpt 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

Bear Notes

openclaw

OrganizationPopular

Create, search, and manage Bear notes via grizzly CLI.

Gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Healthcheck

Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.

Change Impact

Perform evidence-backed impact analysis before changing code, data, interfaces, or governance documents, then compare the planned impact with the actual diff after implementation. Covers call paths,…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

AutomationBench evaluation

Source of truth

Load the global spec catalogue

Simulator

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now