auto-paper-improvement-loop
Auto Paper Improvement Loop runs 2 rounds of autonomous review-fix-recompile cycles to enhance paper quality. Each round uses fresh LLM review to catch structural issues, theoretical inconsistencies, and presentation gaps, then implements fixes and recompiles. Optional style reference and edit whitelist let you steer structural choices or constrain which files the loop modifies.
Auto Paper Improvement Loop autonomously refines papers through 2 rounds of GPT review, fix implementation, and recompilation.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-22
Auto Paper Improvement Loop autonomously refines papers through 2 rounds of GPT review, fix implementation, and recompilation. Auto Paper Improvement Loop runs 2 rounds of autonomous review-fix-recompile cycles to enhance paper quality. Each round uses fresh LLM review to catch structural issues, theoretical inconsistencies, and presentation gaps, then implements fixes and recompiles. Optional style reference and edit whitelist let you steer structural choices or constrain which files the loop modifies.
Use it when
- Yes.
- Auto Paper Improvement Loop performs review, fix, and recompile steps in each cycle.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
wanshuiyin/Auto-claude-code-research-in-sleep/auto-paper-improvement-loop · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does auto-paper-improvement-loop improve my paper automatically?
Auto Paper Improvement Loop runs 2 rounds of autonomous review-fix-recompile cycles. Each round uses fresh LLM review to identify structural issues, theoretical inconsistencies, and presentation gaps, then automatically implements fixes and recompiles your manuscript. This iterative approach progressively enhances paper quality without manual intervention between rounds.
Can I polish my paper with AI review using this tool?
Yes. Auto Paper Improvement Loop applies AI-driven review feedback to polish writing, fix claims, and enhance presentation. The tool autonomously identifies weaknesses in each cycle and applies targeted improvements, letting you refine your manuscript from draft to submission-ready state through iterative enhancement.
What happens during each improvement cycle?
Auto Paper Improvement Loop performs review, fix, and recompile steps in each cycle. The LLM reviews your paper to spot issues, generates fixes for those problems, and recompiles the updated manuscript. With 2 full rounds, you get multiple passes of fresh review and refinement to progressively strengthen your paper's quality.
Can I constrain which files the loop modifies?
Yes. Auto Paper Improvement Loop supports an edit whitelist that lets you constrain edits to specific paths or operations during resubmit or camera-ready phases. This gives you fine-grained control over which sections the tool can modify, protecting critical content while allowing targeted refinement elsewhere.
Does auto-paper-improvement-loop track changes across review rounds?
Auto Paper Improvement Loop maintains an audit trail of all review rounds and fixes, enabling state recovery if needed. This record-keeping lets you understand what changed across cycles and recover previous manuscript states if necessary during your iterative refinement process.
How can I steer the improvement process?
Auto Paper Improvement Loop offers optional style reference and edit whitelist parameters to guide structural choices and control which files the loop modifies. These steering mechanisms let you align the autonomous improvement process with your preferences while maintaining the efficiency of multi-round review-fix cycles.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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
>
(truncated - see the full file via the links below)
File tree — 1 file
skills/auto-paper-improvement-loop/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Autonomously improve paper quality through multi-round review and fix cycles”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Paper-writing chains five specialized sub-skills into a single end-to-end workflow: outline planning, figure generation, LaTeX authoring, PDF compilation, and iterative review. Feed it a research narrative or existing plan, specify your target venue (ICLR, NeurIPS, ICML, CVPR, ACL, AAAI, ACM, IEEE), and optionally reference a style guide—the skill handles the rest, producing a polished paper directory with source and compiled output.
Paper Plan transforms your research narrative and experimental findings into a section-by-section outline tailored to your target venue. It maps evidence to outline slots, respects page limits for conferences like ICLR and NeurIPS, and optionally aligns structural choices with reference papers via style guidance. The skill surfaces gaps where evidence is missing, helping you plan what to write before drafting.
Paper Slides transforms your research paper into a polished conference presentation, outputting both Beamer LaTeX and editable PPTX formats. Customize by talk type (oral, spotlight, poster, or invited), venue (NeurIPS, ICML, ICLR, CVPR, and others), and duration to automatically structure your slides with the right pacing and content depth. Speaker notes and full talk scripts are included.
Paper Compile automates the LaTeX-to-PDF workflow, handling multi-pass compilation, diagnosing common errors, and applying fixes across multiple attempts. It verifies page counts against conference limits, checks for undefined references and citations, and confirms submission readiness including anonymity and font embedding.
lab:autoresearch runs a self-improving loop that mutates plugin skills one change at a time, scores each against deterministic criteria, and commits improvements while reverting failures. Target the weakest skill or run a full sweep overnight with /loop.
Power Iterate is a fully autonomous skill that handles repetitive development work without interruption, managing time and token budgets while executing iteratively toward completion. It understands requirements automatically, designs evaluation criteria, and executes tasks in cycles—stopping only when budgets run out or quality gates are met. Ideal for sustained coding sessions where you set parameters and let the skill drive progress.
More skills feishu-notify (MIT) · arxiv (MIT) · research-lit (MIT)