Story QA — Testing & QA agent for Claude Code
Verify-phase crew member that runs a story's eval set against the DEV story through ./scripts/storyline eval-run, grades deterministic and model-graded cases (pass^k), records the credits each AI Agen.
How to install Story QA
Installs to ~/.claude/agents/ad-ipp-tines-agentic-story-factory-starter-kit-story-qa.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ad-ipp-tines/Agentic-Story-Factory-Starter-Kit/HEAD/.claude/agents/story-qa.md -o ~/.claude/agents/ad-ipp-tines-agentic-story-factory-starter-kit-story-qa.md Restart Claude Code, or start a new session, for it to be picked up.
What Story QA does
name: story-qa description: Verify-phase crew member that runs a story's eval set against the DEV story through ./scripts/storyline eval-run, grades deterministic and model-graded cases (pass^k), records the credits each AI Agent action used, and writes a self-contained verification prompt for the human QA sign-off, returned as an output baton. Use when ./scripts/storyline next names story-qa for a story in verify. tools: Read, Grep, Glob, Bash(./scripts/storyline eval-run *), Bash(./scripts
Alternatives in Testing & QA
- Logic Hacker — Red Team persona for Business Logic and Auth manipulation 548 ★
- QA Manual Tester — Use this agent when you need to perform manual quality assurance testing through browser interactions 394 ★
- Eval Improver — Improver role of the D365FO agent eval loop 136 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Claude Grader
Grades one extension test run against its assertions and writes grading.json. Use after an eval run finishes,
Lw Story Developer
Runs the leanwheel dev-story workflow for one story in an isolated context. Spawned by /story-flywheel Phase 2
Team Mattpocock
Dev-team builder, based on Matt Pocock's skills. Implements the plan test-first and diagnoses bugs methodicall
Render QA
Renders a built artboard, records deterministic visual/GIF evidence, and applies render, contrast, seam, motio
Local Coder
Use for local code generation: implementing a function against a spec or failing test, refactor snippets, boil
Test
QA role for one type:user-story issue whose E2E trace is already green in CI. Executes the manual test script
Related Skills
Always Okay MCP
Creative-direction lens reconstructed from 125 public records of Min Hee-jin's work (interviews, talks, credit
Superpowers Evals
Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Ge
Sw Eval
Run Specwright eval suite. Spawns subagents to run skills in fixture workdirs, then grades results.