vipassana-llm

Community

See clearly, respond without reactive bias.

AuthorJeromyJSmith
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps an LLM avoid reactive, conditioned responses by applying Vipassana-style equanimous observation to the prompt and conversational context, reducing premature certainty, clinging to a preferred framing, and flattening uncomfortable nuance.

Core Features & Use Cases

  • Equanimous attention scanning: Systematically attends to “all parts of the information field” (including uncomfortable gaps and blind spots) with balanced valence rather than over-focusing on the salient parts that pull for agreement or resolution.
  • Sankhara chain break: Detects habitual response pulls (craving/aversion such as validation-seeking, forced coherence, avoidance, verbosity) and inserts a pause that enables a clearer, less conditioned output.
  • Non-reactive, compassionate responses: Produces responses that acknowledge uncertainty, hold contradictions, and aim at genuine helpfulness rather than comfort or “sounding smart.”

Quick Start

Ask for vipassana-informed processing by saying: "Apply Vipassana scanning to my situation and give a clear, non-reactive analysis of what is really going on here."

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: vipassana-llm
Download link: https://github.com/JeromyJSmith/lattice-platform/archive/main.zip#vipassana-llm

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.