Testdriver:Changelog logo

Testdriver:Changelog

Organization
testdriverai
testdriver:changelog

Product updates and announcements

Overview

Publishertestdriverai
Repositorytestdriverai
Skill nametestdriver:changelog
Stars
465
Forks
39
Bundled files
Instructions only
Links
  • 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 testdriverai on GitHub. Read the source before you install it.

Installation

Install the Testdriver:Changelog 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/testdriverai/testdriverai/tree/main/ai/skills/testdriver-changelog
  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/testdriverai/testdriverai.git /tmp/testdriverai
mkdir -p .claude/skills
cp -r /tmp/testdriverai/ai/skills/testdriver-changelog .claude/skills/testdriverai-testdriver-changelog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Testdriver:Changelog 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 Testdriver:Changelog 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 Testdriver:Changelog 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.

<Update label="v7.9.51-canary" description="April 2026" tags={["canary"]}>

🚀 Canary release

This release promotes changes from v7.9.4-test through v7.9.51-test to canary, rolling up all updates since v7.9.3.

✨ New features

  • (Internal) Autoscaling
  • (Internal) End-to-end distributed tracing

🔧 Improvements

  • Faster image matching
  • Storage and infra hardening
  • Sentry environment consistency
  • Chrome extension interaction reliability
  • Docs and onboarding refresh — Updated v7 docs, SDK examples, and VS Code onboarding/init flows.

🐛 Bug fixes

  • Windows AMI build stability — Fixed chrome.exe startup/build failures.
  • Realtime cleanup reliability — Fixed connection cleanup leaks in session shutdown paths.
  • Environment and deployment fixes

<Update label="v7.8.0-test.22" description="March 2026" tags={["test"]}>

Releases test.11 through test.22 include version bumps and internal CI improvements across all packages. No new user-facing changes — see v7.8.0-test.10 for the latest updates in this release stream.

<Update label="v7.8.0-test.10" description="March 2026" tags={["test"]}>

🔧 Improvements

  • Parallel test concurrency — Concurrency limits are now enforced with atomic slot tracking, eliminating a race condition where multiple tests launching at the same time could all bypass the limit. If you hit your concurrency cap, the SDK waits and retries automatically.
  • Dashboard access for all plans — Test recordings and metrics on the dashboard are now visible to all users, including those on the Free plan.
  • Sandbox message throttling — High-frequency interactions no longer risk hitting connection limits. The SDK automatically paces outgoing messages during fast command sequences.
  • Windows Dashcam stability — Web log tracking on Windows sandboxes now handles errors gracefully instead of failing the test.

<Update label="v7.8.0-test.9" description="March 2026" tags={["test"]}>

🔧 Improvements

  • Stable release promotion — Fixed an issue where promoting a test or canary release to stable could be incorrectly skipped. Stable releases now proceed reliably regardless of the prior pre-release channel.
  • Example docs sync — Example documentation now updates more reliably, continuing even when individual example tests fail so that passing examples still get refreshed.

<Update label="v7.8.0-test.8" description="March 2026" tags={["test"]}>

🔧 Improvements

  • VS Code environment switching — The TestDriver VS Code extension now includes a status bar indicator and a new TestDriver: Switch Environment command. You can switch between stable, canary, and test environments directly from VS Code, and your MCP server configuration updates automatically.
  • Plan rename: Starter → Pro — The "Starter" plan has been renamed to Pro. No changes to pricing or features — just a clearer name. The "Self-Hosted" tier is now labeled Enterprise.
  • SDK network resilience — API requests now automatically retry on transient server errors (500, 502, 503, 504) with exponential backoff, reducing flaky test failures caused by brief infrastructure hiccups.
  • Pricing page refresh — The hosted plans page now shows plan cards with included minutes, concurrency limits, and pricing at a glance.

📚 Docs updates

  • Quickstart redesign — The quickstart now has tabbed setup paths for CLI, GitHub Copilot, and manual installation.
  • Deployment section — "Cloud" is now Hosted and the previous Enterprise page has been consolidated into Self-Hosted, which covers both standard and air-gapped deployments.

<Update label="v7.8.0-test.7" description="March 2026" tags={["test"]}> This release includes all changes from v7.8.0-test.6 with version bumps across all packages. No additional user-facing changes.

<Update label="v7.8.0-test.6" description="March 2026" tags={["test"]}>

🔧 Improvements

  • Sandbox spawning reliability — Sandbox creation now uses a 3-minute timeout to handle slow infrastructure, then immediately switches to a 60-second orphan timeout for fast cleanup. This reduces sandbox creation failures during high-traffic periods.
  • Command deadline timeouts — Sandbox commands now enforce a hard deadline that terminates execution if the connection drops mid-command, preventing tests from hanging indefinitely.
  • Real-time channel cleanup — Fixed a compatibility issue with the real-time messaging layer that could cause channel cleanup to fail during shutdown.
  • Dashboard timestamp tooltips — Extended UTC date tooltips to the test history sidebar. Hovering over any relative timestamp (e.g., "5 minutes ago") across the dashboard now shows the full UTC date and time.

<Update label="v7.8.0-test.4" description="March 2026" tags={["test"]}>

✨ New features

🔧 Improvements

  • Sandbox reliability — Linux sandboxes now use a longer creation timeout to handle slow infrastructure, then immediately switch to a short orphan timeout for fast cleanup of disconnected sessions.
  • Command execution timeouts — Sandbox commands now have deadline timeouts that prevent hangs if the connection drops mid-execution.
  • Real-time connection stability — Updated the real-time messaging layer for better compatibility and more reliable channel cleanup during shutdown.
  • Dashboard date display — Hovering over relative timestamps (e.g., "5 minutes ago") now shows the full UTC date and time.

<Update label="v7.8.0-canary.5" description="March 2026" tags={["canary"]}> This release includes all changes from v7.8.0-canary.4 with version bumps.

✨ New features

  • Cache API — Speed up repeated test runs with screenshot-based caching. The system compares screenshots to cached results and reuses element positions when the screen hasn't changed, reducing AI calls.
  • Custom error classes — New ElementNotFoundError class with rich debugging info including screenshot paths, pixel diffs, and detailed messages.
  • Events system — Listen to SDK lifecycle events with wildcard support via testdriver.emitter. Uses colon-delimited namespaces (e.g., command:start, log:*).
  • Provision API — Launch browsers, desktop apps, VS Code, and Chrome extensions in your sandbox before tests run. Access via testdriver.provision.*.
  • Redraw detection — Wait for screens to stabilize after interactions using two-phase detection with pixel comparison and z-score analysis.
  • Screenshots API — Capture screenshots manually with testdriver.screenshot() or automatically before/after every command.

📚 New examples

🔧 Improvements

  • Improved console URL mapping for canary and test environments
  • Enhanced Ably channel cleanup for better resource management
  • Updated release workflow with improved changelog generation

<Update label="v7.5.26" description="March 2026" tags={["stable"]}> 🚀 Stable release

This release promotes v7.5.25 to stable with deployment channel improvements.

✨ Features

  • Deployment channels — SDK now supports stable and canary release channels. Stable releases use the latest npm tag, while canary releases use the canary tag. Install canary with npm install testdriverai@canary.

🔧 Improvements

  • Improved cache hit debugging and logging
  • Enhanced element location reliability
  • Better error handling during test execution

🐛 Bug fixes

  • Fixed restart behavior during auto-updates
  • Fixed console URL routing for various environments

<Update label="v7.5.25" description="March 2026" tags={["stable"]}> 🐛 Bug fixes

  • Fixed restart update behavior

<Update label="v7.5.24" description="March 2026" tags={["stable"]}> 🔧 Improvements

  • Disabled auto-update restart to improve CI stability

<Update label="v7.5.22" description="March 2026" tags={["stable"]}> 🔧 Improvements

  • Added markdown-to-HTML rendering for marketing content

<Update label="v7.5.19" description="March 2026" tags={["stable"]}> 🔧 Improvements

  • Enhanced debugging output for cache hits
  • Improved element location reliability

<Update label="v7.5.17" description="March 2026" tags={["stable"]}> 🔧 Improvements

  • Improved codespace scaling and development environment setup
  • Updated VS Code extension version

Frequently asked questions

What does the Testdriver:Changelog AI skill do?

Product updates and announcements

Why use Testdriver:Changelog on TypingMind?

Because you install it once and use it with any model. Testdriver:Changelog 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 Testdriver:Changelog in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/testdriverai/testdriverai/tree/main/ai/skills/testdriver-changelog. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Testdriver:Changelog?

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 Testdriver:Changelog?

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

Is the Testdriver:Changelog AI skill free?

It is published on GitHub by testdriverai. Check the repository for licensing terms. 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

Set up your own AI workspace now

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