Results for “adversarial-analysis”

VS-Enhanced Theoretical Framework Architect with Critique & Visualization Full VS 5-Phase process: Modal theory avoidance, Long-tail exploration, differentiated framework presentation Absorbed A3 (Devil's Advocate) critique and A6 (Conceptual Framework Visualizer) capabilities Use when: building theoretical foundations, designing conceptual models, deriving hypotheses, critiquing frameworks, visualizing models Triggers: theoretical framework, 이론적 프레임워크, conceptual model, 개념적 모형, hypothesis derivation, critique, devil's advocate, 반론, visualization, diagram

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for races, locks, optimistic conflicts, or worker overlap; never task owner; skip without concurrency impact.

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

`analysis-agent`/`task-agent`/`review-agent`: use when repeated failure needs a new hypothesis or proof path; skip an initial failure with verified cause and a different action.

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Advanced data analysis, pattern detection, and insight generation from structured and unstructured datasets. Use when the user wants to analyze data, perform statistical analysis, find insights, detect patterns, identify anomalies, compare segments, test hypotheses, or generate data-driven recommendations. Triggers on phrases like 'analyze data', 'data analysis', 'find insights', 'analyze dataset', 'statistical analysis', 'find patterns', 'compare groups', 'test hypothesis', 'correlation analysis', or 'trend analysis'.

`analysis-agent`/`task-agent`/`review-agent`: use when retryable, terminal, timeout, partial-failure, or fallback semantics change across boundaries; skip unchanged failures.

Runs a multi-agent adversarial verification loop where two independent reviewers must both pass before output ships, with a fix cycle for convergence.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

Analyzes game AI systems in a codebase, covering behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering, perception, difficulty adaptation, NPC dialogue, and AI debugging tools for Unity, Unreal, and Godot projects.

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.