qa-copilot
v0.3.1Secret-blind QA automation. Plan tests against identity aliases; a trusted local layer resolves credentials and drives the browser.
By QA CopilotLicense: MIT0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 6 skill or MCP entries
- Source updated
- Sep 8, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install qa-copilot for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install qa-copilot@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/kesav-aot/qa-copilotClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .claude-plugin/plugin.json├── skills/qa-analyze-failure/SKILL.md├── skills/qa-automate-test-case/SKILL.md├── skills/qa-generate-test/SKILL.md├── skills/qa-run-test/SKILL.md├── skills/qa-write-test/SKILL.md└── .mcp.json
Included Skills5
Diagnose a failed QA Copilot run from its sanitised report, screenshot, and audit trail, and propose a root cause with a confidence level. Use when a test fails and someone asks why, or asks whether a failure is a real defect or a flaky test.
Turn existing manual test cases (Markdown, CSV, Excel, Gherkin, Jira exports) into reviewed, runnable Test DSL plans. Use when someone asks to automate a backlog of test cases, convert a spreadsheet or Jira export, or asks "what can we automate?".
Turn a prompt, requirement, or an existing manual test case into a QA Copilot Test DSL plan that references identity aliases instead of credentials. Use when someone asks to automate a test, convert a test case from Jira/TestRail/CSV/Gherkin, or write a new browser or API test.
Validate, gate, and execute a QA Copilot Test DSL plan against a configured environment, then report the sanitised result. Use when someone asks to run, execute, or re-run a test plan.
Write a browser or API test in plain English from a description of what to check. Use whenever someone asks for a test, a check, or "can you test that…" — this is the default way to author tests, because the person who owns the test must be able to read it.
MCP servers1
- command
- ${CLAUDE_PLUGIN_ROOT}/packaging/launcher/qa-copilot-launch
Plugin manifests1
{
"name": "qa-copilot",
"version": "0.3.1",
"description": "Secret-blind QA automation. Plan tests against identity aliases; a trusted local layer resolves credentials and drives the browser.",
"author": {
"name": "QA Copilot"
},
"homepage": "https://github.com/kesav-aot/qa-copilot",
"repository": "https://github.com/kesav-aot/qa-copilot",
"license": "MIT",
"keywords": [
"qa",
"testing",
"automation",
"playwright",
"security"
],
"mcpServers": {
"qa-copilot": {
"command": "${CLAUDE_PLUGIN_ROOT}/packaging/launcher/qa-copilot-launch"
}
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[qa-copilot on Agent Plugins Marketplace](https://pluginsmp.com/plugins/qa-copilot)