Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

result-validation-loop

Validate results through statistical testing, ROPE judgment, reproducibility re-runs, and final synthesis

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

reviewer2-hat

Hostile reviewer perspective — find fatal flaws, logical gaps, and missing evidence in a solution.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

robustness-design

Design experiments to identify failure boundaries and robustness limits

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

screening-then-decomposition

Two-phase sensitivity — Morris quick screening to eliminate unimportant factors, then Sobol precise decomposition on survivors. Efficient allocation of analytical effort.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

severity-scoring

Rate failure mode severity 1-10 based on end-effect impact. Follows AIAG-VDA severity scale calibrated for research artifacts.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

steel-manning

Steel-Manning Campaign — adversarial verification of convergence decisions through resurrection advocacy, winner stress-testing, criteria interrogation, and multi-perspective attack using Devil's Advocacy, Pre-mortem, Red Teaming, Dialectical Inquiry methods.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

stress-test-saturation-detection

Determines whether validation has reached saturation — no new weaknesses or failure modes being discovered. Used by all 5 campaigns as termination signal.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub

systematic-factor-ablation

Tactic: List all factors, remove one at a time, assess conclusion stability, rank factors by load-bearing importance.

386 repo starsObserved in 1 repos
Testing & Quality
GitHub