Content Refinement Agent

Content Refinement Agent is an AI Engineering skill for Claude Code, published by Ar9av in PaperOrchestra.

644 stars91 forkson Ar9av/PaperOrchestraAdded 2026/08/24+1% in starsRepository updated 2026/08/09

agentic-aiai-researchanthropicantigravityarxivautomated-paper-writingclaude-codeclaude-skillscoding-agentscursorlatexliterature-reviewllm-agentsmulti-agentpaper-orchestrapaperorchestraresearch-papersemantic-scholarskill-pack

Install in seconds

Install Content Refinement Agent

Copy Content Refinement Agent into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Ar9av/PaperOrchestra/tree/main/skills/content-refinement-agent ~/.claude/skills/content-refinement-agent

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Ar9av/PaperOrchestra.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/content-refinement-agent/SKILL.md in Ar9av/PaperOrchestra
Installs to: ~/.claude/skills/content-refinement-agent
Collection: One of 9 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Content Refinement Agent does

Content Refinement Agent refines a paper draft by simulating peer review, applying targeted revisions, and stopping only when the scoring rules or iteration cap are met. It is used for Step 5 of the PaperOrchestra pipeline and keeps snapshots and a worklog so accepted changes can be reverted reliably.

Content Refinement Agent is cataloged under AI Engineering on DirSkills. Content Refinement Agent comes from a repository tagged agentic-ai, ai-research, anthropic, antigravity and arxiv.

Documentation

README

Excerpt

Content Refinement Agent (Step 5)

Faithful implementation of the Content Refinement Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 5, App. F.1 pp. 49–51).

Cost: ~5–7 LLM calls (App. B), typically ~3 refinement iterations, each consisting of one reviewer call and one revision call.

The paper highlights this step as one of the largest contributors to overall quality: refinement alone accounts for +19% (CVPR) and +22% (ICLR) absolute acceptance-rate improvement (Fig. 4). Get this step right.

Inputs

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Content Refinement Agent

What else does Ar9av publish alongside Content Refinement Agent?
Content Refinement Agent is one of 9 skills that DirSkills catalogs from Ar9av/PaperOrchestra, the repository it ships in. Its siblings there include Agent Research Aggregator, Literature Review Agent and Outline Agent. Each one is a separate skill with its own page in this directory, installs the same way Content Refinement Agent does, and is maintained by Ar9av in that same repository. The rest of the collection is listed on the Ar9av/PaperOrchestra page.
How does Content Refinement Agent compare to other AI Engineering skills?
Content Refinement Agent ranks #1862 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Content Refinement Agent against them. Open each page to compare what they document and how they install.