How do I install the Stress Test Perspective Rotation skill?

Run npx skillmds@latest add yogsoth-ai/stress-test-perspective-rotation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Stress Test Perspective Rotation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Stress Test Perspective Rotation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Stress Test Perspective Rotation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Stress Test Perspective Rotation?

yogsoth-ai (@yogsoth-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Stress Test Perspective Rotation by yogsoth-ai

Name: Stress Test Perspective Rotation
Author: yogsoth-ai

File contents

Perspective Rotation Tactic

Sequential multi-perspective evaluation followed by divergence analysis and deliberation.

Orchestration

debate-architect assigns N perspectives (domain expert, skeptic, practitioner, theorist, etc.)
[Parallel] Each perspective-critic evaluates artifact from assigned viewpoint
divergence-detection compares all evaluations:
- Identifies consensus points (agreement across >70% of perspectives)
- Identifies divergence points (disagreement across >50% of perspectives)
[Deliberation] Perspective-critics respond to divergence points
divergence-detection re-evaluates — tracks convergence trend
confidence-calibration determines if further rounds needed

Perspective Types

Domain Expert (technical validity)
Methodological Skeptic (rigor and reproducibility)
Practitioner (real-world applicability)
Theorist (conceptual coherence)
Adversary (strongest possible objection)
Novice (clarity and accessibility)

Subagents Dispatched

debate-architect (perspective assignment)
perspective-critic × N (evaluation from viewpoint)
divergence-detection (agreement/disagreement mapping)
confidence-calibration (convergence assessment)

Termination Conditions

Convergence reached (divergence points < 2)
Max deliberation rounds exhausted
Saturation detected (no position changes between rounds)
Irreconcilable disagreement identified (flagged for human review)

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOP	When to use
confidence-calibration	Calibrates confidence scores based on debate progression. Determines whether to escalate, continue, or terminate based on cumulative evidence.
debate-architect	Designs debate structure based on artifact type — selects attack vectors, assigns perspectives, determines escalation ladder, and configures round parameters.
divergence-detection	Identifies agreement and disagreement patterns across multiple perspective evaluations. Maps consensus clusters and persistent divergence points.
perspective-critic	Evaluates artifact from a specific assigned perspective. Produces assessment grounded in that viewpoint's values, priorities, and expertise.

---name: stress-test-perspective-rotationdescription: Tactic: Sequential perspective evaluation with divergence aggregation. Each agent evaluates from a distinct viewpoint, then disagreements are surfaced and resolved.---# Perspective Rotation TacticSequential multi-perspective evaluation followed by divergence analysis and deliberation.## Orchestration1. **debate-architect** assigns N perspectives (domain expert, skeptic, practitioner, theorist, etc.)2. [Parallel] Each **perspective-critic** evaluates artifact from assigned viewpoint3. **divergence-detection** compares all evaluations: - Identifies consensus points (agreement across >70% of perspectives) - Identifies divergence points (disagreement across >50% of perspectives)4. [Deliberation] Perspective-critics respond to divergence points5. **divergence-detection** re-evaluates — tracks convergence trend6. **confidence-calibration** determines if further rounds needed## Perspective Types- Domain Expert (technical validity)- Methodological Skeptic (rigor and reproducibility)- Practitioner (real-world applicability)- Theorist (conceptual coherence)- Adversary (strongest possible objection)- Novice (clarity and accessibility)## Subagents Dispatched- debate-architect (perspective assignment)- perspective-critic × N (evaluation from viewpoint)- divergence-detection (agreement/disagreement mapping)- confidence-calibration (convergence assessment)## Termination Conditions- Convergence reached (divergence points < 2)- Max deliberation rounds exhausted- Saturation detected (no position changes between rounds)- Irreconcilable disagreement identified (flagged for human review)## Available SOPsOptional, no fixed order; the final leaf is always a sop.| SOP | When to use || --- | --- || confidence-calibration | Calibrates confidence scores based on debate progression. Determines whether to escalate, continue, or terminate based on cumulative evidence. || debate-architect | Designs debate structure based on artifact type — selects attack vectors, assigns perspectives, determines escalation ladder, and configures round parameters. || divergence-detection | Identifies agreement and disagreement patterns across multiple perspective evaluations. Maps consensus clusters and persistent divergence points. || perspective-critic | Evaluates artifact from a specific assigned perspective. Produces assessment grounded in that viewpoint's values, priorities, and expertise. |

Frequently asked questions

Stress Test Perspective Rotation