prove-it

Test absolute claims through iterative rounds with auditable reports.

66|2|Updated Feb 18, 2015
One-click install
npx skills add https://github.com/tkersey/dotfiles --skill prove-it-tkersey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prove-it
Source: https://github.com/tkersey/dotfiles/tree/main/codex/skills/prove-it
Command: npx skills add https://github.com/tkersey/dotfiles --skill prove-it-tkersey

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prove-It provides a structured, repeatable process to challenge and refine absolute claims, reducing bias and ensuring claims survive rigorous examination.

Core Features & Use Cases

  • Round Cadence & Autoloop: enforces continuous, deterministic evaluation across turns and automatic progression.
  • Round Ledger & Knowledge Delta: preserves auditable records of each round and the evolution of the claim.
  • Boundary Synthesis & Oracle: derives a refined claim with explicit boundaries after iterative testing.
  • Use Case: test a bold assertion under edge cases, adversarial inputs, and policy constraints to validate its reliability.

Quick Start

Initiate Prove-It by restating the claim and its scope, then run Round 1 to publish the Round Ledger and Knowledge Delta. If confidence remains low, proceed with additional rounds.

Frequently Asked Questions about prove-it

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

FAQPage Schema
How do I rigorously test an absolute claim against boundary cases?

To rigorously test an absolute claim, you restate the claim and its scope, then run iterative rounds of devil's-advocate and boundary-case evaluations. This enforces continuous deterministic testing to validate the claim's reliability under edge cases and policy constraints.

What is a Knowledge Delta report in claims verification?

A Knowledge Delta report in claims verification records the evolution of a claim across iterative testing rounds. It works alongside an auditable Round Ledger to preserve transparent records of how the claim is challenged and refined.

How do I apply a devil's advocate scenario to validate a bold assertion?

You apply a devil's advocate scenario to validate a bold assertion by enforcing a fixed autoloop cadence that challenges the claim with adversarial inputs. After iterative rounds, the Boundary Oracle synthesizes a refined claim with explicit boundaries.

When do I need iterative boundary-case evaluation for critical thinking?

You need iterative boundary-case evaluation for critical thinking when a bold assertion must survive rigorous examination without bias. It is required when validating absolute claims under edge cases, adversarial inputs, and policy constraints to ensure reliability.

What is the best way to maintain an auditable trail during claims verification?

The best way to maintain an auditable trail during claims verification is to enforce a fixed autoloop cadence that publishes a Round Ledger and Knowledge Delta report for every iteration. This preserves auditable records of each testing round.

What are the limitations of using a fixed cadence for proof requests?

The limitation of using a fixed cadence for proof requests is that automatic progression enforces continuous evaluation, meaning the process requires additional rounds if confidence remains low. It relies on deterministic evaluation rather than stopping early.