from-the-other-side-anitta

Applies structured skepticism to challenge assumptions and calibrate claims against evidence quality.

38.5k|4.9k|Updated Jun 11, 2025
One-click install
npx skills add https://github.com/github/awesome-copilot --skill from-the-other-side-anitta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: from-the-other-side-anitta
Source: https://github.com/github/awesome-copilot/tree/main/skills/from-the-other-side-anitta
Command: npx skills add https://github.com/github/awesome-copilot --skill from-the-other-side-anitta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analytical work often suffers from unexamined assumptions, overconfident claims, and reasoning gaps that lead to poor decisions. This Skill provides a rigorous challenge profile that stress-tests reasoning before conclusions are finalized.

Core Features & Use Cases

  • Assumption Surfacing: Makes implicit assumptions about data quality, causality, and stability explicit before analysis proceeds.
  • Claim Calibration: Matches language strength (suggests, indicates, demonstrates) to actual evidence quality.
  • Three-Phase Review Lens: Systematically reviews reasoning and logic, interpretation and narrative, then rigor checks and counterfactuals.
  • Use Case: Before presenting a data-driven recommendation to leadership, run the analysis through Anitta's rigor prompt bank to identify weak assumptions, test counterfactuals, and ensure conclusions are defensible.

Quick Start

Ask the assistant to act as Anitta and challenge the reasoning and evidence behind your current analysis or proposal.

Frequently Asked Questions about from-the-other-side-anitta

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

FAQPage Schema
How do I stress-test assumptions in a data analysis?

Use structured challenge prompts that ask what is being assumed about data quality, causality, and stability. Then test counterfactuals by asking what observation would change the conclusion, and check whether each reasoning step follows logically.

How to calibrate claim strength to evidence quality?

Match your language to evidence strength: use 'suggests' for weak correlations, 'indicates' for moderate support, and 'demonstrates' only for strong, replicated evidence. Avoid claims stronger than the available data supports.

When should I use a rigorous challenge profile for analysis?

Use it when the cost of being wrong is meaningful, such as high-stakes decisions, leadership presentations, or analyses with significant uncertainty. It is less necessary for low-stakes exploratory work where speed matters more.

What is the difference between challenging reasoning and challenging interpretation?

Challenging reasoning tests whether logic steps follow and assumptions hold. Challenging interpretation examines whether the narrative and framing accurately represent the evidence. This profile addresses reasoning first, interpretation second, and rigor checks third.

Can this profile work alongside other collaboration personas?

Yes, it is designed to coordinate with complementary profiles: one drives momentum and deliverables, another refines narrative clarity, while this one validates that underlying reasoning holds. Handoffs occur when uncertainty in assumptions arises.