Manual QA — Testing skill for Claude Code
Generate a manual QA procedure from this session's changes and walk through it interactively.
How to install Manual QA
Installs to ~/.claude/skills/diegovogel-claude-code-tools-manual-qa/SKILL.md
mkdir -p ~/.claude/skills/diegovogel-claude-code-tools-manual-qa && curl -fsSL https://raw.githubusercontent.com/diegovogel/claude-code-tools/HEAD/commands/manual-qa.md -o ~/.claude/skills/diegovogel-claude-code-tools-manual-qa/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Manual QA does
Generate a manual QA procedure from this session's changes and walk through it interactively. The user drives the UI; you verify backend signals (logs, DB, network). Phase 0 makes sure the app under test is actually serving the changed code (critical when the session works in an isolated agent environment), then three phases: build the procedure, walk it through together, clean up.
When NOT to use
If the change has no UI surface — CLI-only, API-only, pure backend, library code — REFUSE the
Alternatives in Testing
- Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
- L Debug Trace — Analytically debug issues by tracing data flow through code - no logs, no test-and-see 3k ★
- Regen API — Regenerate the OpenAPI spec and web API client after server API changes 2.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Test Example
When we make significant changes to the codebase, we want to make sure everything is running as intended. To d
Specstride
Spec-driven autonomous coding orchestrator: drives your agent through GitHub Spec Kit phases behind an LLM cri
QA Phase
Run QAPhase — the autonomous acceptance-and-ship QA gauntlet. Proves a finished story end-to-end (spec-gap/gri
Add Test
Interactively add a new test definition to the test suite
Decisionbench
One public test, any typed-decision model: accuracy, latency, cost, and accuracy when it is sure. Jev vs Claud
RocketSimApp
RocketSim — 30+ tools for Xcode's iOS Simulator. Testing, debugging, network monitoring, captures, accessibili
Related Agents
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
Browser Operator
Drives a REAL browser to verify deployments + operate the product like a user. Use after any deploy, for golde
Run Issues Verify Gate
Adversarial verify gate for one /run-issues issue — drives the acceptance path in the running app and rejects