Maintainer of this skill?
Automated security scan — not a certification.
by maxritter
Plan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE.
# Add to your Claude Code skills
git clone https://github.com/maxritter/qualitylayerLast scanned: 10/22/2026
{
"issues": [
{
"file": "README.md",
"line": 73,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://qualitylayer.dev/install.sh | bash\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-10-22T09:10:55.514Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how qualitylayer compares with popular alternatives.
qualitylayer is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by maxritter. Plan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE. It has 2,097 GitHub stars.
Yes. qualitylayer passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/maxritter/qualitylayer" and add it to your Claude Code skills directory (see the Installation section above).
qualitylayer is primarily written in PowerShell. It is open-source under maxritter on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh qualitylayer against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Plan each change visually, then let your agents build and verify it. Work side by side in the App or browser, or use your favourite terminal or IDE.
Download the App for macOS, Windows or Linux. 7-day trial.
“With QualityLayer, developing software with agents finally feels like doing real engineering again.”
An engineer who uses QualityLayer
QualityLayer keeps design decisions and verification visible while your agents work.
| You get | How it works |
|---|---|
| A design you can review | Comment on diagrams and clickable screens, then approve the Plan before code changes. |
| Small, tested changes | Your agent builds in slices, each starting with a failing test. |
| An independent check | Agents that did not write the code check it against your request. Anything they cannot verify stays open for your decision. |
| Code health checks | Local checks flag complex functions and deeply nested code for your agent to review. Ask for a wider check to find duplication. Code health. |
| Visible decisions and effort | Each step records its decisions and results in your repository, with time and estimated model cost shown in the App. |
Made for medium and large changes. Small requests keep a short Plan and one slice; ask for a ready prompt if you prefer your plain agent.
Download the App and open it. Setup activates your licence or starts the trial, installs the qualitylayer command and connects your agents. On a server, in WSL or in a container:
curl -fsSL https://qualitylayer.dev/install.sh | bash # macOS, Linux, WSL
irm https://qualitylayer.dev/install.ps1 | iex # Windows PowerShell
The App updates itself; without it, run qualitylayer update. Installation guide.
qualitylayer uninstall undoes what the installer changed; your plans stay. On Windows, even when the App is gone:
& ([scriptblock]::Create((irm https://qualitylayer.dev/install.ps1))) -Uninstall
Run pilot update to install QualityLayer v12, or download it directly. Keep Pilot Shell 11 alongside it until you are ready to remove it; your paid licence works with both. Import memories per project when you are ready. Moving from Pilot Shell.
In the App or browser, choose + New, pick your repository and agent, and describe the change:
Plan retries for failed webhooks and stop after a few tries.
| Where you work | How to start |
|---|---|
| App or browser | Choose In QualityLayer to keep the agent beside the task. |
| Your terminal or IDE | Choose In my terminal, app or IDE to copy the request, or ask there: “Using QualityLayer, plan retries for failed webhooks.” |
| Another agent | Agents that run shell commands can use the CLI. Supported agents. |
To continue elsewhere, stop the active run, then ask: “Using QL, continue verification of task retry-webhooks.” Your Plan, changes and evidence stay with the task.
QualityLayer runs only when you ask for it. Your first task.
Each step writes a Markdown file in your repository. Read questions, decisions and results in the App. You approve the Plan and the finished change; QualityLayer pushes only with your approval and leaves merging to you.
| Step | What happens |
|---|---|
| Discuss | Settles what done means and clarifies a bug report |
| Research | Agents read how your code works today; a bug is reproduced and diagnosed here |
| Plan | Artifact, diagrams and checks, approved by you |
| Outline | The build session splits the approved Plan into small slices |
| Implement | Each slice starts with a failing test |
| Verify | Every point of your request, with its evidence |
| Review | A walkthrough of the change, approved by you |
| Pull request | Failing checks fixed; the task stays open until you merge |
Engineering starts with a technical plan. Product starts with a brief that becomes a product requirements document. Choose at Setup or change it in Settings › Workflow or the task header. How they differ.
Ask your agent for a mockup, diagram or clickable artifact. Compare versions in the App, pin feedback and restore earlier versions. Keep the artifacts every task builds on in your repository. Artifacts.
| In the App | What you can do |
|---|---|
| Agent workspace | Read artifacts beside the conversation. Answer questions and pin feedback. |
| Run controls | Choose agent, model, effort and branch. Set defaults in Settings. |
| Project memory | Reuse lessons across tasks and share them through Git. Project memory. |
| Team review | Ask teammates over Slack and review shared work with a Team plan. |
QualityLayer keeps task files on your computer and encrypts shared tasks first. Your coding agent uses its own provider. Files and privacy.
Guides for getting started, commands and settings.
See the changelog or GitHub Releases.
Found a bug or missing a feature? Open an issue.
See LICENSE.
Quality by design. The software factory with you in the loop.
Made by Max Ritter