Result Checker — Testing & QA agent for Claude Code
Use this agent right after test-runner executes a group of test cases, to decide per case whether each genuinely passed or failed and what happens next.
How to install Result Checker
Installs to ~/.claude/agents/rikkipanwar-qa-agent-toolkit-result-checker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rikkipanwar/qa-agent-toolkit/HEAD/agents/result-checker.md -o ~/.claude/agents/rikkipanwar-qa-agent-toolkit-result-checker.md Restart Claude Code, or start a new session, for it to be picked up.
What Result Checker does
name: result-checker description: Use this agent right after test-runner executes a group of test cases, to decide per case whether each genuinely passed or failed and what happens next. It reads the runner's structured per-case result, confirms each pass is real rather than masked, classifies failures by kind, and keeps a per-case attempt count so one stubborn case escalates without stopping its group. It names which agent each case should route to but does not invoke it. Do not use this ag
Alternatives in Testing & QA
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Logic Hacker — Red Team persona for Business Logic and Auth manipulation 548 ★
- Bowser QA Agent — UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots 222 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Suite Reporter
Use this agent only after every individual test case has passed via the script-generator/test-runner/result-ch
Script Generator
Use this agent to write or fix the Playwright TypeScript specs for a GROUP of related test cases (one feature)
PR Validator
Validates a pull request before release by running its test suite and reporting pass/fail results. Use proacti
Eval Failure Diagnoser
Diagnoses promptfoo skill-eval failures for sumo-qa. Use after npm run eval or npm run eval:all returns any FA
Verify Boss
OPTIONAL independent RE-EXECUTOR. Use on request as a last-stage second witness for L2+/high-risk runs to re-r
Spec
Three-phase spec subagent. Phase 0 = read spec, decide which agents need views (free judgment). Phase 1 = cont
Related Skills
Verdict
End the cross-examination and render the verdict. PASSED only if every objection was resolved; otherwise FAILE
Willow
Willow — a companion narrator that gives blind developers situational awareness while an AI coding agent (e.g.
Novelty Hunt
Claude Code skill: search a solution space for genuinely original candidates and score them without killing th