draft-polisher

Refine survey draft prose by removing boilerplate and anchoring citations.

497|38|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill draft-polisher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: draft-polisher
Source: https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/draft-polisher
Command: npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill draft-polisher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of turning raw, machine-generated draft text into polished, human-readable prose by removing boilerplate, improving flow, and ensuring citations are correctly anchored and formatted.

Core Features & Use Cases

  • Boilerplate Removal: Eliminates repetitive template phrases and generator voice.
  • Coherence Improvement: Enhances the logical flow and readability of the text.
  • Citation Anchoring: Ensures citations remain correctly linked to their corresponding claims and do not drift across sections.
  • Terminology Normalization: Standardizes key terms for consistency.
  • Use Case: After an AI generates a first draft of a literature survey, use this Skill to clean up the language, make it sound like a single author wrote it, and verify that all citations are correctly placed before final review or conversion to LaTeX.

Quick Start

Run the draft polisher skill on the current draft to improve its prose and citation integrity.

Frequently Asked Questions about draft-polisher

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

FAQPage Schema
How do I remove boilerplate and improve coherence in AI-generated research survey drafts?

Citation anchoring ensures citations remain correctly linked to their corresponding claims and do not drift across sections. This process maintains evidence integrity by enforcing strict handling of citation keys during post-generation editing.

How do I standardize terminology and enforce citation anchoring in machine-generated literature surveys?

This Skill standardizes key terms for consistency and enforces citation anchoring to keep evidence correctly linked. It applies post-generation editing to research survey drafts, ensuring all citations are correctly placed before final review.

Does this prose refinement approach work for converting drafts to LaTeX format?

Yes, this prose refinement approach prepares drafts for final review or conversion to LaTeX. By cleaning up the language and verifying that all citations are correctly placed, it ensures a consistent, human-readable output ready for formatting.

What is the best way to ensure a single author voice in a generated literature survey?

The best way to ensure a single author voice is to apply post-generation editing that eliminates boilerplate and normalizes terminology. This Skill refines draft survey prose to make the text sound like a single author wrote it.

When should I not use automated prose refinement on research drafts?

You should avoid automated prose refinement when your draft lacks established citation keys or requires preserving original generator voice. This Skill requires careful handling of citation anchors and targets drafts needing coherence improvement and boilerplate removal.