auto-paper-improvement-loop SKILL.md skillA
auto-paper-improvement-loop from wanshuiyin/auto-claude-code-research-in-sleep is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop@git:20260928.3e7691bPins git:20260928.3e7691b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wanshuiyin/auto-claude-code-research-in-sleep
- Path
skills/auto-paper-improvement-loop/SKILL.md- Versions recorded
- 6
- Latest version
- git:20260928.3e7691b, committed Sep 28, 2026
- First version recorded
- Jul 10, 2026
- Size
- 41,176 bytes
- Repository stars
- 17,793
- License
- MIT
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
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
# Auto Paper Improvement Loop: Review → Fix → Recompile > 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It > already loops internally (review → fix → recompile) with its own round > structure and a deliberate fresh-reviewer bias guard each round (no > `codex-reply`). Re-asking it to "improve the paper" on a > wall-clock timer produces no new signal — quality changes when the *review* > changes, not when the clock ticks — and a timed re-run that also accepts its > own output to decide when to stop crosses into self-acquittal > (`acceptance-gate.md`). Schedule the *external wait that precedes it*, not the > improvement loop. See > [`shared-references/external-cadence.md`](../shared-references/external-cadence.md). Autonomously improve the paper at: **$ARGUMENTS** ## Context This skill is designed to run **after** Workflow 3 (`/paper-plan` → `/paper-figure` → `/paper-write` → `/paper-compile`). It takes a compiled paper and iteratively improves it through external LLM review. …
Read the whole file at its exact version.
How to install
mdr add wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop@sha256:e0179353625706eaThe line at the top of this page pins the label git:20260928.3e7691b, 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_hdwcvbdhvi56jclb)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 10, 2026 and Sep 28, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260928.3e7691b latest | 2026-09-28 | 3e7691b | 41,176 B | A | view · diff |
| git:20260906.0472e53 | 2026-09-06 | 0472e53 | 41,169 B | A | view · diff |
| git:20260903.e59008d | 2026-09-03 | e59008d | 41,169 B | A | view · diff |
| git:20260826.e9e51ff | 2026-08-26 | e9e51ff | 39,233 B | A | view · diff |
| git:20260714.3c58cac | 2026-07-14 | 3c58cac | 37,363 B | A | view · diff |
| git:20260710.6142715 | 2026-07-10 | 6142715 | 37,176 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 (41176 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
wanshuiyin/auto-claude-code-research-in-sleep · 17,793 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hdwcvbdhvi56jclb GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop GET https://markdownregistry.com/api/v1/blob/e0179353625706ea567a1ecc849cbc84c2f41503cf8bfb71744a7b9078e2f938
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.
More from wanshuiyin/auto-claude-code-research-in-sleep
Every file in wanshuiyin/auto-claude-code-research-in-sleep