Stx Reviewer — Testing & QA agent for Claude Code
Multi-agent wave Reviewer persona.
How to install Stx Reviewer
Installs to ~/.claude/agents/sudiptosen-stx-skills-stx-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sudiptosen/stx-skills/HEAD/.claude/agents/stx-reviewer.md -o ~/.claude/agents/sudiptosen-stx-skills-stx-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Stx Reviewer does
name: stx-reviewer description: Multi-agent wave Reviewer persona. Reads the Dev's diff plus the task spec from architecture-verse.html and emits a structured verdict {approved, concerns[], suggested_revisions[]}. Sits between Dev (implementer) and QA (test rerunner) in the wave loop. Forbidden from editing any file — read-only review only. Detects test-file edits by Dev and halts the loop entirely. Consumed by /stx-feature. version: 1.11.0 author: STX role: reviewer inputs:
- Dev's diff (
Alternatives in Testing & QA
- Component Config Reader — Extracts the test surface (properties, styles, events, defaults, nested variants) from a ToolJet app-builder c 41k ★
- Perf Test Sync — Use this agent when the user needs to synchronize performance test cases between development (dev) and QA dire 14.5k ★
- Logic Hacker — Red Team persona for Business Logic and Auth manipulation 548 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Stx QA
Shared QA persona used by /stx-feature (wave context — writes failing tests per task, supervises Dev loop) and
Debate Judge
L0.97 Adversarial Verification — reads all 3 rounds of prosecution and defense transcripts plus the original d
Stx Coder
Single-bug Coder persona for /stx-fix. Reads a failing test, implements the smallest change that makes it pass
Confluence Spec Analyst
Read full Confluence spec page (+ children + images) and produce structured Spec Research Report with requirem
Mp Planner
Turns an approved spec into an executable masterplan plan — tasks with wave assignments, routing annotations,
Live Evaluator
Phase 3 of the grounded-persona-eval method — drives one persona through a real, live interaction with the pro
Related Skills
Claude Devils Advocate
Claude Code slash command that simulates a multi-round code review between an Author and Reviewer before openi
Fix PR
by metabase - Fetches and fixes unresolved PR comments by automatically retrieving feedback, addressing review
Gc Exploratory
Exploratory review — find concerns lint/golden-rules/docs-reviewer cannot catch, then create tq actions for ea