Skip to content
Agentmart
Submit a tool

content-refinement-agent

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018).

Skill by rcrede

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rcrede-content-refinement-agent

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".

Use cases: data, writing, research, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/content-refinement-agent

What's inside

Skill name
content-refinement-agent
Description
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".
License
unknown
Instructions
387 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (15)

  • SKILL.md
  • ai-failure-modes.md · references/
  • da-reviewer.md · references/
  • halt-rules.md · references/
  • prompt.md · references/
  • reviewer-rubric.md · references/
  • safe-revision-rules.md · references/
  • writing-quality-check.md · references/
  • apply_worklog.py · scripts/
  • concession_guard.py · scripts/
  • decision_band.py · scripts/
  • score_delta.py · scripts/
  • score_trajectory.py · scripts/
  • snapshot.py · scripts/
  • update_critique_memory.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from rcrede/antigravity-config

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 18, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/rcrede/antigravity-config
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from rcrede

Cite this page

content-refinement-agent skill. Agent Mart. https://agentmart.dev/skills/rcrede-content-refinement-agent (last updated 2026-10-24)