🧩
AI EngineeringPython

Outline Agent

by Ar9av

Outline 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 Outline Agent
Copy Outline 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/outline-agent ~/.claude/skills/outline-agent

Requires Node.js. Downloads this skill only β€” not the rest of the repository β€” 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/outline-agent/SKILL.md in Ar9av/PaperOrchestra
Installs to
~/.claude/skills/outline-agent
Collection
One of 9 skills cataloged from this repository
Category
AI Engineering β€” 2451 skills

What Outline Agent does

Outline Agent converts idea notes, experiment logs, a LaTeX template, and conference guidelines into a strict JSON paper outline. It is used when drafting the structure, plotting plan, related work plan, and section plan for PaperOrchestra Step 1.

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

Documentation

README

Outline Agent (Step 1)

Faithful implementation of the Outline Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, App. F.1, pp. 40–44).

Cost: 1 LLM call.

Your task

Read four input files from the workspace and produce a single JSON object at workspace/outline.json with three top-level keys:

  • plotting_plan β€” array of figure objects
  • intro_related_work_plan β€” object with introduction_strategy and related_work_strategy
  • section_plan β€” array of section objects, each with section_title and subsections[]

How to do it

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

Frequently asked about Outline Agent

  • What else does Ar9av publish alongside Outline Agent?

    Outline Agent is one of 9 skills that DirSkills catalogs from Ar9av/PaperOrchestra, the repository it ships in. Its siblings there include Agent Research Aggregator, Content Refinement Agent and Literature Review Agent. Each one is a separate skill with its own page in this directory, installs the same way Outline 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 Outline Agent compare to other AI Engineering skills?

    Outline Agent ranks #1863 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 Outline Agent against them. Open each page to compare what they document and how they install.

More from Ar9av/PaperOrchestra

Outline Agent is one of 9 skills cataloged on DirSkills from Ar9av/PaperOrchestra.

See all 9 skills β†’
πŸ§ͺ
1w ago

Agent Research Aggregator

Agent Research Aggregator scans AI agent cache directories or a chosen folder for experiment logs and turns them into PaperOrchestra-ready idea and experimental log inputs. Use it before PaperOrchestra when your evidence is scattered across agent histories.
AI Engineering
64491
πŸ“
1w ago

Content Refinement Agent

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.
AI Engineering
64491
πŸ“š
1w ago

Literature Review Agent

Literature Review Agent finds and verifies paper citations, builds a BibTeX file, and drafts Introduction and Related Work sections from the verified sources. Use it for literature searches, bibliography building, or related work drafting in the PaperOrchestra pipeline.
Writing
64491
πŸ“„
1w ago

Paper Autoraters

Paper Autoraters runs PaperOrchestra’s four LLM-as-judge evaluators for paper quality, citation coverage, and side-by-side comparisons. Use it to score a draft, compare two papers, or validate a paper-writing pipeline.
AI Engineering
64491
🎼
1w ago

Paper Orchestra

Paper Orchestra orchestrates a five-agent pipeline that turns research notes, experiment logs, templates, guidelines, and figures into a LaTeX manuscript and compiled PDF. Use it when you want to generate a conference submission from unstructured research materials.
AI Engineering
64491
πŸ“
1w ago

Paper Writing Bench

Paper Writing Bench reverse-engineers a research paper into sparse and dense idea notes plus an experimental log for benchmark cases. Use it when you need to evaluate a paper-writing pipeline against a paper-orchestra-style benchmark.
AI Engineering
64491