evidence-ledger
CommunityBuilds a deterministic evidence ledger for paper analysis.
Authorwanshuiyin
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the construction of a deterministic evidence ledger, ensuring accurate and reproducible analysis of paper content.
Core Features & Use Cases
- Artifact Manifest: Generates a manifest of observable artifacts and their observability level (L0, L1, L2).
- Claims Extraction: Extracts span-anchored, hashed claims from the paper text.
- Enrichment Pass: Optionally adds semantic claims extracted by a separate model for additional context.
- Use Case: Before conducting an audit on a research paper, use this Skill to build a comprehensive ledger of its claims and artifacts, providing a solid foundation for the audit process.
Quick Start
Build the evidence ledger for the paper located at 'path/to/paper' using the evidence-ledger skill.
Dependency Matrix
Required Modules
BashReadWriteGrepGlobmcp__codex__codex
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: evidence-ledger Download link: https://github.com/wanshuiyin/Anti-Autoresearch/archive/main.zip#evidence-ledger Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.