Claude Grader — Testing & QA agent for Claude Code
Grades one extension test run against its assertions and writes grading.json.
How to install Claude Grader
Installs to ~/.claude/agents/syncwin-ai-extender-claude-grader.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/syncwin/ai-extender/HEAD/agents/claude-grader.md -o ~/.claude/agents/syncwin-ai-extender-claude-grader.md Restart Claude Code, or start a new session, for it to be picked up.
What Claude Grader does
name: claude-grader description: Grades one extension test run against its assertions and writes grading.json. Use after an eval run finishes, when each assertion needs a pass/fail with quoted evidence. model: inherit color: green tools: ["Read", "Grep", "Glob", "Write"] metadata: displayName: "AI Extender Grader" version: 1.0.0 author: "@wasimness" company: SyncWin plugin: ai-extender
You are the Claude implementation of the AI Extender grader.
Read `${CLAUDE_PLUGIN_ROOT}/sk
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 ★
- Review Test Quality — Reviews test code for behavior-driven quality and completeness: whether tests verify real behavior vs chasing 432 ★
- Extension Smoke Test — Pre-reload smoke test for the WXT browser extension 189 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Print QA
Gates a 3MF before anything prints, with PASS/FAIL per item of templates\preprint-checklist.md, the evidence q
Eval Failure Diagnoser
Diagnoses promptfoo skill-eval failures for sumo-qa. Use after npm run eval or npm run eval:all returns any FA
Fpm QA Grader
Grades transcript quality. Checks coverage, confidence distribution, gaps, speaker consistency. Produces A-F g
Code Grader
Independent read-only reviewer that grades finished SDD work against its approved SPEC.md and the project's co
Story QA
Verify-phase crew member that runs a story's eval set against the DEV story through ./scripts/storyline eval-r
Squad QA
Operate as the squad's behavioral QA gate — verify observable behavior against acceptance criteria and risk, r
Related Skills
Citation Verifier
Round-trip every citation and quoted phrase in a legal output against the source document. Flag mismatches, fa
Performance Marketing Eval
15 performance marketing tasks for evaluating AI agents, with simulated tools, a shared grader, and baseline t
Review Test Quality
Audit test suite quality: coverage gaps, weak assertions, missing negative cases, over-mocking, and tests that