Home / ar9av / paperorchestra · skills/content-refinement-agent/SKILL.md · GitHub

content-refinement-agent skillA

content-refinement-agent is agent-read markdown (skill) from ar9av/paperorchestra: 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 orche.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# 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

- `workspace/drafts/paper.tex` — output of Step 4
- `workspace/inputs/conference_guidelines.md`
- `workspace/inputs/experimental_log.md` — used as ground truth for the
  hallucination check
- `workspace/citation_pool.json` / `workspace/refs.bib` — the allowed
  bibliography

## Outputs

- `workspace/refinement/iter1/`, `iter2/`, `iter3/` — per-iteration snapshots
  containing `paper.tex`, `paper.pdf`, `review.json`, `score.json`
- `workspace/refinement/worklog.json` — append-only history of decisions
- `workspace/final/paper.tex` and `workspace/final/paper.pdf` — copy of the
  best accepted snapshot

## The refinement loop

```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ar9av/paperorchestra/content-refinement-agent@git:20260921.79998c1
Exact content
mdr add ar9av/paperorchestra/content-refinement-agent@sha256:63c19099b720d189

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ucqsr4wyysqibz5g.svg)](https://markdownregistry.com/a/art_ucqsr4wyysqibz5g)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.79998c1 latest2026-09-21 79998c1 19,770 BA view · diff
git:20260921.9c4e2392026-09-21 9c4e239 18,369 BA view · diff
git:20260921.6186a452026-09-21 6186a45 18,943 BA view · diff
git:20260921.399121f2026-09-21 399121f 18,220 BA view · diff
git:20260921.e2940d62026-09-21 e2940d6 17,691 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19770 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ar9av/paperorchestra · 664 stars · license NOASSERTION · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ucqsr4wyysqibz5g
GET https://markdownregistry.com/api/v1/resolve?ref=ar9av/paperorchestra/content-refinement-agent
GET https://markdownregistry.com/api/v1/blob/63c19099b720d1890e0cdc5ef78e639450e17dd346db078e3022695e66f63659

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from ar9av/paperorchestra

agent-research-aggregator skill
ar9av/paperorchestra · skills/agent-research-aggregator/SKILL.md · Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any…
git:20260417.cc469cc · audit A · 664 stars
literature-review-agent skill
ar9av/paperorchestra · skills/literature-review-agent/SKILL.md · Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json —…
git:20260921.e2940d6 · audit A · 664 stars
outline-agent skill
ar9av/paperorchestra · skills/outline-agent/SKILL.md · Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex…
git:20260602.770a879 · audit A · 664 stars
paper-autoraters skill
ar9av/paperorchestra · skills/paper-autoraters/SKILL.md · Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition +…
git:20260409.c2de31b · audit A · 664 stars
paper-orchestra skill
ar9av/paperorchestra · skills/paper-orchestra/SKILL.md · Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured…
git:20260602.770a879 · audit A · 664 stars
paper-writing-bench skill
ar9av/paperorchestra · skills/paper-writing-bench/SKILL.md · Reverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build…
git:20260409.c2de31b · audit A · 664 stars
plotting-agent skill
ar9av/paperorchestra · skills/plotting-agent/SKILL.md · Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render…
git:20260921.8d6fd97 · audit A · 664 stars
section-writing-agent skill
ar9av/paperorchestra · skills/section-writing-agent/SKILL.md · Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining…
git:20260921.79e9bd8 · audit A · 664 stars

Every file in ar9av/paperorchestra

Browse by kind, by grade A, or by owner.