loop2-exit-check

Evaluate the latest Tester report against four criteria and return a PASS/FAIL verdict.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Exit rubric for Loop 2 (stress testing) to decide if the current idea has survived adversarial scrutiny and is ready to proceed to the Experimental Setup Module, by evaluating the latest Tester report against a standardized four-criterion rubric and returning PASS or FAIL with explicit failing criteria.

Core Features & Use Cases

  • Evaluates the most recent tester report against four formal criteria (soundness, novelty, internal consistency, and importance).
  • Performs a soundness pre-check to discount paper-based attacks and surfaces a transparent doubt log.
  • Produces a deterministic PASS/FAIL verdict with a structured criteria matrix and a list of any remaining serious attacks to track risk.

Quick Start

Query the latest tester report, run the loop2-exit-check, and return a deterministic PASS or FAIL with the accompanying criteria notes.

Frequently Asked Questions about loop2-exit-check

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

FAQPage Schema
How do I evaluate a stress-test tester report to decide if an idea is ready for experimental setup?

To evaluate a stress-test tester report, you run a loop2-exit-check against a four-criterion rubric covering soundness, novelty, internal consistency, and importance, returning a deterministic PASS or FAIL verdict with explicit failing criteria.

What criteria are used for stress-testing exit checks in research workflows?

Stress-testing exit checks evaluate the latest tester report against four formal criteria: soundness, novelty, internal consistency, and importance, applying a soundness pre-check to discount paper-based attacks before producing a PASS or FAIL verdict.

How do I check if an idea has survived adversarial scrutiny before moving to the next research phase?

You check if an idea survived adversarial scrutiny by running a loop2-exit-check on the most recent phase_0_ideation stress_test data, which produces a deterministic verdict and a transparent doubt log of any demoted or discarded attacks.

Does the loop2-exit-check provide a log of discarded attacks during the stress-test evaluation?

Yes, the loop2-exit-check provides a transparent doubt log that surfaces any demoted or discarded paper-based attacks during the soundness pre-check, alongside a structured criteria matrix and a list of remaining serious attacks to track risk.

What happens if an idea fails the stress-test exit criteria evaluation?

If an idea fails the stress-test exit criteria evaluation, the loop2-exit-check returns a FAIL verdict with an explicit list of which of the four criteria failed, along with a structured matrix and remaining serious attacks to guide further refinement.

Can I use the loop2-exit-check without dependencies or external components?

Yes, you can use the loop2-exit-check without dependencies or external components, as it independently queries the latest tester report and applies its standardized four-criterion rubric to return a deterministic PASS or FAIL verdict.