skills.rest
bogheorghiu
bogheorghiuCOMMUNITY
Explore all skills by this author →
GitHub

self-improving-investigation

A meta-search and -rescue framework for locating missing Android devices, regardless of whether they are online or offline, and regardless of the type of device lost (smartphone, tablet, watch, laptop, TV, etc.) or the platform it runs onbbaazzaazz.

Updated Aug 23, 2026
Search Tags:#investigation#iterative-loop#bias-correction#multiperspective#dialectic-synthesis#source-diversity#blind-workers
One-click install
npx skills add https://github.com/bogheorghiu/ex-cog --skill self-improving-investigation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: self-improving-investigation
Source: https://github.com/bogheorghiu/ex-cog/tree/main/vasana-system/skills/self-improving-investigation
Command: npx skills add https://github.com/bogheorghiu/ex-cog --skill self-improving-investigation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Am I investigating, or just confirming what I already believe? Self-correcting research methodology combining blind worker agents, nested iteration loops, and dialectic synthesis. Use when (1) research requires factual certainty not just plausibility, (2) topic has high bias risk, (3) multiple perspectives must be systematically tested, (4) user explicitly requests deep/thorough investigation, (5) previous single-pass research proved insufficient. Integrates with iterative-loop-engine and deep-investigation-protocol.

Core Features & Use Cases

  • Blind worker agents to reduce orchestration bias and keep iterations objective.
  • Nested loop architecture to structure multi-dimensional research.
  • Dialectic synthesis: thesis → antithesis → synthesis to surface nuance and counterarguments.
  • Integration with iterative-loop-engine and deep-investigation-protocol to trace evidence and bias.
  • Logging and improvement notes to capture methodology evolution.

Quick Start

Define completion criteria, spawn blind workers, collect findings, and synthesize with dialectic method.

Frequently Asked Questions about self-improving-investigation

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

FAQPage Schema
How do I reduce bias when doing deep research on controversial topics?▼

Dialectic synthesis combines thesis, antithesis, and synthesis to systematically surface counterarguments and nuance during investigative research. It forces multi-perspective testing by structuring findings into opposing views, ensuring high-bias topics receive factual certainty instead of mere plausibility.

When should I use blind workers in an iterative research loop?▼

Start a self-correcting investigation by defining explicit completion criteria, spawning blind worker agents to gather diverse sources, and synthesizing their findings using the dialectic method. This structured approach ensures evidence is labeled and auditable throughout the nested iteration loops.

What is dialectic synthesis and how does it work for multi-perspective research?▼

Dialectic synthesis combines thesis, antithesis, and synthesis to systematically surface counterarguments and nuance during investigative research. It forces multi-perspective testing by structuring findings into opposing views, ensuring high-bias topics receive factual certainty instead of mere plausibility.

How do I structure multi-dimensional research to ensure factual certainty?▼

Structure multi-dimensional research using nested loop architecture to organize iterations and enforce dialectic synthesis across diverse sources. This approach systematically tests multiple perspectives against explicit completion criteria, shifting findings from mere plausibility to factual certainty.

What are the limitations of single-pass research for high-bias topics?▼

Single-pass research lacks nested iteration loops and blind worker agents, making it insufficient for high-bias topics where orchestration bias can skew results. Without dialectic synthesis and explicit completion criteria, single-pass methods risk confirming existing beliefs rather than establishing factual certainty.

Related Skills

Explore More Education & Research Skills→
martindzejkymartindzejky
1

verification-before-completion

Run tests, lint, and builds to gather fresh evidence before reporting completion.

Community
Advanced
diriendirien
19

the-fool

Steelman a user's position and generate structured critiques with challenges and synthesis.

Community
Advanced
pingdiorpingdior
7

universal-system-prompt

Structure multi-dimensional cognitive analysis with hierarchical reasoning and pattern verification.

Community
Advanced
fixpoint-labsfixpoint-labs
2

tech-brief

Research specified technology topics and synthesize concise briefings.

Official
Basic