decipon

Perform full NCI manipulation analysis on content (text or URL) with 20-category scoring and dual perspectives

Red team adversarial critique of a document or claim

Conduct deep research using Time-Tested Diffusion methodology

Quick research with source verification (lighter than /deep-research)

Generate formal NCI analysis report in JSON or Markdown format for sharing and archiving

Quick NCI manipulation score (0-100) with severity indicator and top findings - use for rapid content triage

Verify factual claims in content using deep research methodology - fact-checks key assertions and updates NCI scores

Use after NCI analysis to fact-check key claims and update manipulation scores based on verification results. Auto-invoked by /decipon:verify command.

Use PROACTIVELY for complex research questions requiring multiple sources, comparisons, due diligence, or thorough analysis. MUST BE USED when user asks for "deep research", "thorough analysis", "comprehensive report", or "investigate".

Use PROACTIVELY when claims need independent verification, sources disagree, or user asks to "verify", "fact-check", or "confirm". Resolves contradictions across sources.

Use when user asks to analyze content for manipulation, propaganda, disinformation patterns, or requests NCI scoring. Auto-invoked by /decipon:analyze command.

Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.

Use when asked for "deep research", "thorough analysis", "comprehensive report", "investigate", "due diligence", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.

Use when asked to analyze content for manipulation, propaganda, disinformation patterns, or when user provides a URL or text asking "is this manipulative?", "analyze this for bias", "check for propaganda", or similar requests. Detects emotional manipulation, suspicious timing, uniform messaging, tribal division, and missing information across 20 categories.