loop2-stress-test

Orchestrate Loop 2 stress-test rounds and evaluate exit checks.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/YurainSoon/research-director --skill loop2-stress-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: loop2-stress-test
Source: https://github.com/YurainSoon/research-director/tree/main/.claude/skills/loop2-stress-test
Command: npx skills add https://github.com/YurainSoon/research-director --skill loop2-stress-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Researchers require reliable orchestration for Loop 2 stress testing, coordinating the Tester workflows, capturing results, and guiding retreat or proceed decisions across rounds.

Core Features & Use Cases

  • Orchestrates Round execution: prepares context, invokes the Tester, evaluates the exit checks, and branches on pass or fail.
  • Manages Tester reports and adversarial literature outputs under phase_0_ideation/stress_test/.
  • Guides retreat decisions when issues are found, clearly presenting options and required actions to the user.
  • Tracks round progression with a hard cap (3 rounds) and maintains a cumulative history of Tester outputs for re-tests.

Quick Start

Run a new stress-test round by invoking the idea-pressure-tester and save the result as phase_0_ideation/stress_test/tester_report_{n}.md.

Frequently Asked Questions about loop2-stress-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate a Loop 2 stress test and manage Tester cycles?

You can orchestrate Loop 2 stress testing by invoking the tester, evaluating exit checks, and branching execution based on pass or fail outcomes. It coordinates context propagation and manages cumulative history across rounds.

What happens when an adversarial evaluation fails during a stress test round?

When an adversarial evaluation fails during a stress test, the system guides retreat decisions by clearly presenting options and required actions to the user. It applies to re-tests after Loop 1 retreats, managing reports under the stress test directory.

How many rounds can I run for idea pressure testing before hitting a limit?

Idea pressure testing enforces a hard cap of 3 rounds for tracking round progression. It maintains a cumulative history of tester outputs across these rounds to support re-tests and end-to-end orchestration.

How are stress test reports and literature outputs saved during testing?

Stress test reports and adversarial literature outputs are saved as markdown files under the phase_0_ideation/stress_test/ directory. You run a new round by invoking the idea-pressure-tester and saving the result with a numbered tester report naming convention.

Do I need any external dependencies to coordinate end-to-end stress testing?

No external dependencies are required to coordinate end-to-end stress testing. The system internally manages context propagation, tester invocation, and user-facing continue or retreat decisions across all rounds without external modules.

When should I use a dedicated stress test orchestrator instead of manual testing?

You should use a stress test orchestrator when you need reliable coordination of multiple testing rounds, cumulative output tracking, and structured retreat decisions. It ensures end-to-end context propagation that manual testing cannot easily maintain.