confidence-research

Community

Confidence-weighted research with explicit sources.

Authorhainamchung
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Research outputs with explicit confidence levels and source hierarchy. Halts hallucination propagation by tagging unverified claims.

Core Features & Use Cases

  • Source Hierarchy: Priority context7, official docs, verified WebSearch, and explicit inference checks to ensure reliable sourcing.
  • Research Output Format: Structured Markdown with executive summaries, findings, confidence levels, sources, and evidence.
  • Verification Protocol: Per-finding validation rules, cross-source checks, and explicit attribution to minimize unverified claims.
  • Anti-Hallucination Discipline: Systematic checks that prioritize evidence over assumption and flag uncertainty for validation.

Quick Start

Provide a topic and request a confidence-weighted research report with source citations.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: confidence-research
Download link: https://github.com/hainamchung/agent-assistant/archive/main.zip#confidence-research

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.