Does this skill modify my research artifacts or notes?

No, this is an analysis-only skill. It reads your current artifacts and writes a TODO report, but it does not edit your evidence bank or writing drafts.

What is the primary purpose of the Evidence Self-loop skill?

Its primary purpose is to ensure research papers or surveys are not written with 'hollow' or generic prose by verifying that sufficient evidence and citations exist in the pipeline first.

When should I use the evidence-selfloop skill?

Use it when you have generated evidence bindings or drafts but find the support is thin, or when you want a diagnostic report on why a writing task is currently blocked.

What does a 'FAIL' status in the report indicate?

A FAIL status indicates that critical inputs are missing or there are 'blocking_missing' signals that require you to fix upstream artifacts before proceeding to write.

Evidence Self-Loop Router

Name: Evidence Self-Loop Router
Author: WILLOSCAR

byWILLOSCAR

•

コンテンツ管理

Analyzes research pipelines for evidence gaps and generates actionable recovery plans to prevent hollow writing.

The Evidence Self-loop skill acts as a quality gate for research-intensive writing pipelines, ensuring that every claim is backed by rigorous data. By auditing intermediate artifacts like evidence bindings, subsection briefs, and paper notes, it identifies precisely where evidence is thin or missing. Instead of allowing the AI to generate generic filler prose, this skill produces a structured TODO report that routes the user to specific upstream fixes—such as re-extracting paper details or expanding literature mapping—to ensure the final output is grounded and authoritative.

主な機能

01Identifies evidence gaps and 'blocking missing' signals in research artifacts

02Provides a semantic routing matrix to map symptoms to root cause upstream fixes

03Generates a structured EVIDENCE_SELFLOOP_TODO.md with actionable fix paths

04Enforces a strict evidence-first contract to prevent the invention of facts

05Evaluates citation-backed anchors, evaluation metrics, and comparison density

0696 GitHub stars

ユースケース

01Automating the audit of research pipelines to ensure high-quality intermediate artifacts

02Unblocking academic survey writing when evidence bindings are insufficient

03Routing agents to rerun specific extraction skills when empirical data is missing

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add willoscar/research-units-pipeline-skills evidence-selfloop

For use in Claude.ai and ChatGPT

Download Skill