legitimacy-block

Append claim status, disputes, gaps, and self-grade to analytical output.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/robwestz/memoryporter --skill legitimacy-block
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: legitimacy-block
Source: https://github.com/robwestz/memoryporter/tree/main/knowledge/meta-skills/legitimacy-block
Command: npx skills add https://github.com/robwestz/memoryporter --skill legitimacy-block

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, yaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill appends an epistemic structure to analytical output, ensuring traceability of claims, dispute surfacing, and gap reporting.

Core Features & Use Cases

  • Claims Table: Maps every claim to its status, confidence, and sources.
  • Disputes: Identifies and surfaces disagreements between sources or claims.
  • Gaps: Lists what was not examined and why it might matter.
  • Grade Block: Provides a self-grade YAML block with coverage, confidence, verdict, and loop-back count.
  • Optional Delta Summary: Includes assumptions, risks, and what was not verified.
  • Use Case: When wrapping the output of a research report to ensure transparency and traceability of the analysis.

Quick Start

Trigger the legitimacy-block by using the command "add legitimacy block" on the output of the skill 'systematic-research'.

Frequently Asked Questions about legitimacy-block

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

FAQPage Schema
How do I add traceable epistemic structure to analytical research output?

To add epistemic structure to analytical research output, you can use the legitimacy-block Skill. It wraps your report with claim statuses, dispute reporting, gap identification, and a self-grade YAML block to ensure downstream traceability.

What is the best way to track claim status and dispute reporting in decision-grade analysis?

Tracking claim status and dispute reporting in decision-grade analysis involves mapping every claim to its confidence level and sources. This Skill generates a claims table and surfaces disagreements between sources to provide analytical transparency.

How do I identify gaps in research reports using Python data analytics tools?

To identify gaps in research reports using Python data analytics tools, this Skill parses your analytical output to list what was not examined and explains why it matters. It requires pandas, numpy, and yaml libraries to perform the parsing and analysis.

Do I need specific Python dependencies to generate a self-grade YAML block for my analysis?

Yes, you need the Python dependencies pandas, numpy, and yaml to generate a self-grade YAML block. These libraries are required by the Skill to parse analytical output and calculate coverage, confidence, verdict, and loop-back count.

When should I append gap identification and confidence grading to a research report?

You should append gap identification and confidence grading to a research report whenever a downstream consumer will act on its claims. This ensures transparency by surfacing assumptions, risks, and what was not verified before decisions are made.