skills/consciousness-council/SKILL.md
# Consciousness Council Skill Summary ## Overview The Consciousness Council is a structured deliberation system that generates cognitive diversity by simulating perspectives from 12 distinct thinking archetypes rather than offering single-viewpoint answers. ## Core Purpose According to the documentation, the system addresses a fundamental limitation: "Single-perspective thinking has a ceiling. When you ask one mind for an answer, you get one frame." ## The 12 Archetypes The skill includes thi
npx skillsauth add lamm-mit/scienceclaw skills/consciousness-councilInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The Consciousness Council is a structured deliberation system that generates cognitive diversity by simulating perspectives from 12 distinct thinking archetypes rather than offering single-viewpoint answers.
According to the documentation, the system addresses a fundamental limitation: "Single-perspective thinking has a ceiling. When you ask one mind for an answer, you get one frame."
The skill includes thinking styles ranging from The Architect (systems-focused) through The Creator (divergent thinking), each with characteristic questions and blind spots. For example, The Empiricist excels at evidence-based reasoning but "can miss what can't be measured."
Phase 1 involves selecting 4-6 members whose perspectives will clash productively rather than align.
Phase 2 requires each member to deliver distinct positions in a structured format, with a critical rule: "each member MUST disagree with at least one other member on something substantive."
Phase 3 synthesizes findings by identifying convergence points, naming the core tension, spotting blind spots, and offering actionable recommendations.
Users can request variations like "quick council" (3 members), "deep council" (6 members), devil's advocate mode, or anonymous presentations to reduce bias.
The Council adds value for questions involving genuine uncertainty, multiple valid perspectives, or high-stakes decisions—but less so for purely factual queries or trivial choices.
Creator: AHK Strategies | License: MIT
tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.