
from wizards-of-the-ghosts93
Activate a high-integrity conversation mode where claims must be sourced, uncertainty is labeled, and speculation is explicitly flagged.
Zone of Truth provides a conversational discipline for agents: when activated, every factual claim must include an explicit source or a confidence label. The skill defines the activation phrase, the expected behaviors (re-auditing prior assertions, labelling inference vs. fact), and guardrails to reduce unsourced statements. It helps teams and agents maintain epistemic rigor during high-stakes decision making, compliance checks, or vendor claim validation.
Use Zone of Truth when discussions require evidence-backed assertions: product roadmaps, compliance reviews, vendor evaluations, legal or research conversations, or any time the conversation drifts into speculation and needs a reset to verified ground. Activate with the configured phrase to trigger the mode.
This is an instruction-style skill suitable for general chat agents and assistant frameworks that support user-invocable modes (GPT-based assistants, Hermes-style agent runtimes, and pipeline orchestrators).
This skill has not been reviewed by our automated audit pipeline yet.
Symbol — Policy Tagging / Semantic Marker
Define and apply named policy 'symbols' (machine-readable tags) that trigger enforcement actions like audit logging, throttling or compliance gates when conditi
Arcana (Technical Mechanism Analysis)
Explain how systems, protocols, or architectures actually work under the hood and surface non-obvious implications and failure modes.
History — Temporal Investigation
Performs structured reconstruction of how a system, decision, or codebase arrived at its current state: timelines, key decision points, and contextual analysis
Hypnotic Pattern
Design short-lived attention-capture patterns (progress indicators, micro-rewards, visual anchors) to hold focus during bounded flows without creating addictive
Fear (Pre-mortem & Risk Amplifier)
Structured pre-mortem generator that amplifies plausible worst-case scenarios, ranks failure modes, and produces concrete mitigation recommendations.
Greater Invisibility
Plan and execute live changes with minimal user-visible noise using feature flags, shadow writes, progressive rollout, and operator-visible signals.
Power Word Kill
Emergency containment skill: guidance and guarded procedure for immediate hard termination of processes, services, or accounts when graceful options are unavail
Disguise Self
Adapt voice, tone, and presentation of existing content for a target audience without changing facts or meaning.
Locate Animals or Plants
Discover live services, background jobs, data stores, and hidden dependencies in an environment and return a prioritized map with confidence notes.