QA Pilot — DevOps skill for Claude Code
Evidence-first feature testing for Claude Code.
How to install QA Pilot
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open SandeepTakasi/qa-pilot and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What QA Pilot does
Evidence-first feature testing for Claude Code. Verdicts only from committed Playwright runs, with a trace and deploy SHA per case, a write guard for production, and ClickUp or local files as the record.
Alternatives in DevOps
- Composio Split — Manage Split feature flags and experiments 44.6k ★
- 16 Testing — Prompt 16: Add Test Infrastructure & Smoke Tests 2.3k ★
- Terraform Skill For Claude — Comprehensive Terraform and OpenTofu guidance covering testing, modules, CI/CD, and production patterns 1.4k ★
README
QA-Pilot
**Evidence-first feature testing for Claude Code.** A verdict you can open, not a claim.
QA-Pilot runs feature tests against a deployed environment and publishes a verdict only after a script has checked its evidence. Every executed case leaves a committed Playwright spec, a trace, and the deploy SHA read from the running environment, so QA reviews evidence instead of re-running the tests. ClickUp holds the record, or plain local files when you run without a tracker.
**Documentation:** [sandeeptakasi.github.io/qa-pilot](https://sandeeptakasi.github.io/qa-pilot/)
Install
claude plugin marketplace add https://github.com/SandeepTakasi/qa-pilot
claude plugin install qa-pilot
Requires Node 20 or newer and, in the repo you test, Playwright 1.51 or newer. Then run `/qa-pilot:qa-init` in that repo to write its host profile: [Setting up a project](https://sandeeptakasi.github.io/qa-pilot/docs/qa-init/).
Why
"Claude clicked through it and it looked fine" is a sentence, not evidence. It names no build, holds no recording, and gives a second person nothing to open. QA-Pilot replaces it with three things that can be checked: a committed spec that produced the verdict and regresses the feature in CI later, one `trace.zip` per case (video, console, DOM snapshots and network log in one file), and the deployed build the run was against, read before and after the run.
How it works
Six commands, with QA approving between design and execution:
/qa-pilot:qa-init write the project's host profile (once)
/qa-pilot:setup-profiles save a login per account (once per developer)
/qa-pilot:generate-tests author the feature's cases from its task and code
QA approves the scenarios, the write policy and the cases
/qa-pilot:run-tests run committed specs against a deployed build
/qa-pilot:publish-results validate the run, then publish verdicts
/qa-pilot:qa-review approve, reject with a reason, or retest
What it ref
Related Skills
Compliance Evidence Skills
Claude Code skills for compliance evidence: a plugin with five skills that pack GitHub, AWS and Microsoft 365
Hol Guard AWS Preflight
Fail-closed pre-execution HOL Guard skill for agents running aws CLI commands. Implements the aws/agent-toolki
Publish GitHub
Scan for secrets, push the project to GitHub, deploy GitHub Pages via Actions, screenshot the live site with P
M Playwright Fulltest
Full cycle: test plan -> deploy -> testing via a browser MCP -> fixing -> re-deploy. No confirmations, no paus
Railway Operator Public
Claude Code plugin: autonomous Railway infrastructure agent. CLI-first, GraphQL when needed, Playwright for da
Full Stack Feature
Orchestrate full-stack feature development across backend, frontend, and infrastructure layers with modern API
Related Agents
DevOps Triage
Triages a production error alert (service name, error sample, optional deploy sha) into a bounded root-cause v
QA Compliance Guard
Reviews the final deliverables (4 pilot / 5 full) for compliance (banned language, four-state conclusions, sou
Clickup Sync
Pushes a local Markdown file to a ClickUp Doc page, overwriting it. Receives a file path, workspace ID, doc ID