content-refinement-agent SKILL.md skillA
content-refinement-agent from ar9av/paperorchestra is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ar9av/paperorchestra/content-refinement-agent@git:20260921.79998c1Pins git:20260921.79998c1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ar9av/paperorchestra
- Path
skills/content-refinement-agent/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260921.79998c1, committed Sep 21, 2026
- First version recorded
- Sep 21, 2026
- Size
- 19,770 bytes
- Repository stars
- 697
- License
- a license file GitHub does not identify
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…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file 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
mdr add ar9av/paperorchestra/content-refinement-agent@sha256:63c19099b720d189The line at the top of this page pins the label git:20260921.79998c1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ucqsr4wyysqibz5g)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Sep 21, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.79998c1 latest | 2026-09-21 | 79998c1 | 19,770 B | A | view · diff |
| git:20260921.9c4e239 | 2026-09-21 | 9c4e239 | 18,369 B | A | view · diff |
| git:20260921.6186a45 | 2026-09-21 | 6186a45 | 18,943 B | A | view · diff |
| git:20260921.399121f | 2026-09-21 | 399121f | 18,220 B | A | view · diff |
| git:20260921.e2940d6 | 2026-09-21 | e2940d6 | 17,691 B | A | view |
Audit of the latest version
- 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
ar9av/paperorchestra · 697 stars · license a license file GitHub does not identify · pushed 2026-11-04 · 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 AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.