proving-claims

What problem does it solve?

Maps claims to evidence, statuses, gaps, tests, evals, reviews, and traces to ensure every important claim can be traced and any unsupported claims are made explicit. The skill turns each claim into a traceable proof and keeps six things apart: a fact, an assumption, an unknown, a source claim, local proof, and decision authority. The approach supports disciplined decision-making by linking claims to artifacts and clarifying release implications.

Core Features & Use Cases

• Converts each material claim into a traceable claim-to-evidence row that records its basis, control or design feature, and the evidence type.
• Distinguishes between fact, assumption, unknown, source claim, local proof, and decision authority to keep evidence organized.
• Enables release posture decisions by recording evidence statuses (pass, fail, gap, deferred, not applicable) and explicit residual risks.
• Supports outputs that connect claims to basis, evidence, and artifacts in trace.md and verification.md, with clear links to tests, reviews, and logs.

Quick Start

Provide a packet and its list of claims, and run the mapping to produce claim-to-evidence rows with statuses and an explicit release posture.