private-intelligence-reader

Build private intelligence readers from feeds, notes, and transcripts with validated evidence.

Updated Jul 17, 2026
One-click install
npx skills add https://github.com/kartikkabadi/skills --skill private-intelligence-reader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: private-intelligence-reader
Source: https://github.com/kartikkabadi/skills/tree/main/private-intelligence-reader
Command: npx skills add https://github.com/kartikkabadi/skills --skill private-intelligence-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you turn scattered personal source material into a private reading experience that stays grounded in evidence, avoids hallucinated context, and clearly separates validated content from follow-up actions.

Core Features & Use Cases

  • Source-grounded summaries: Convert feeds, notes, transcripts, and research into reader-facing posts with explicit source references and validation notes.
  • Validation gates: Require confidence levels, blocked states, and claim checks so the output does not present unverified material as fact.
  • Reader-first presentation: Shape the result into a clean, editorial reading surface with quiet metadata, actionable takeaways, and clear publishing boundaries.
  • Use case: A researcher can aggregate newsletters, X threads, and local notes into one private reader that shows what matters today and what still needs verification.

Quick Start

Ask the Skill to build a private intelligence reader for your source bundles and return validated posts with confidence labels, source references, and action items.

Frequently Asked Questions about private-intelligence-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a private intelligence reader from scattered research notes and transcripts?

To build a private intelligence reader, aggregate feeds, notes, transcripts, and source bundles into reader-facing posts. The output provides source-grounded summaries with explicit references, validation notes, and actionable takeaways without inventing hidden context.

What is the best way to prevent AI hallucinations when summarizing research workflows?

Preventing hallucinations in research summarization requires validation gates that enforce confidence levels, blocked states, and claim checks. This source-grounded approach ensures the private reader output separates validated evidence from unverified material.

Can I aggregate newsletters and X threads into a single private reader with confidence labels?

Yes, you can aggregate newsletters and X threads into a single private reader. The process generates reader-facing posts that display what matters today, complete with confidence labels, source references, and identified action items.

How do I add validation gates to ensure content curation stays grounded in source evidence?

Adding validation gates to content curation requires explicit source references and confidence levels for every generated claim. This mechanism blocks unverified material from being presented as fact, maintaining strict boundaries between private content and public publishing.

Does this approach work for tracking follow-up actions separately from validated summaries?

Yes, tracking follow-up actions is supported by shaping the reader output into a clean editorial surface. It clearly separates validated private reader content with quiet metadata from actionable takeaways and items still needing verification.