Uefn Skeptic — Testing & QA agent for Claude Code
Gauntlet adversarial reviewer for UEFN - tries to prove a "done" task is actually broken (edge cases, multiplayer, rejoin/persistence, race conditions, crash modes, spec gaps the tests miss).
How to install Uefn Skeptic
Installs to ~/.claude/agents/viggojonssonf-uefn-claude-automation-uefn-skeptic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ViggoJonssonF/uefn-claude-automation/HEAD/agents/uefn-skeptic.md -o ~/.claude/agents/viggojonssonf-uefn-claude-automation-uefn-skeptic.md Restart Claude Code, or start a new session, for it to be picked up.
What Uefn Skeptic does
name: uefn-skeptic description: Gauntlet adversarial reviewer for UEFN - tries to prove a "done" task is actually broken (edge cases, multiplayer, rejoin/persistence, race conditions, crash modes, spec gaps the tests miss). Use as the last review before a task can close. Never implements. disallowedTools: Edit, Write, NotebookEdit skills:
- uefn-mcp-automation model: claude-opus-5-5 effort: high color: red
Your job is to break the claim that this task is done. Assume the builder and t
Alternatives in Testing & QA
- Logic Hacker — Red Team persona for Business Logic and Auth manipulation 548 ★
- Review Test Concurrency — Reviews test code for concurrency testing quality: whether multi-threaded behavior is properly verified, race 432 ★
- Prod Incident Responder — Reads recent prod logs, picks the highest-impact recurring error, drafts a minimal fix PR with a regression te 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Uefn Spec Reviewer
Gauntlet reviewer that checks a finished UEFN task against its SPEC acceptance criteria using gate evidence, p
Uefn Test Author
Gauntlet test author for UEFN - writes in-game Verse AutoTest scenarios from the SPEC (not from the implementa
Bizlogic Hunter
Delegates to this agent when the user wants to test for business logic flaws, find workflow bypass vulnerabili
Edge Case QA
Read-only QA agent that thinks like a breaker. Examines every changed function for boundary conditions, null/u
Plan Checker
Outcome-driven verification of docs/plan.md + docs/todo.md against docs/SPEC.md goals. Catches plans that look
Review Verify
Tries to disprove one review finding by checking it against the code, a test run or a screenshot. Only finding
Related Skills
QA Phase
Run QAPhase — the autonomous acceptance-and-ship QA gauntlet. Proves a finished story end-to-end (spec-gap/gri
Concurrency Atomicity
Run a concurrency-correctness and atomicity review against a diff, PR, or branch — race conditions, TOCTOU, de
Pair Verify
Use after you fix a bug and before you claim it fixed — it spawns ONE skeptic sibling session via CCC that mus