agentleFS
YulivuYulivu/debuffer-skills/skills/skills-codex-gemini-review/auto-paper-improvement-loop/SKILL.md

auto-paper-improvement-loop

Skill9 starsChanged 3 months agoMITView on GitHub

Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Autonomously improve a generated paper via Gemini review through gemini-review MCP → 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.

4 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 6 are distinctive, and 10 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.

    line 14
  2. Distinctive:

    Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.

    line 16
  3. Very specific:

    Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the …

    line 18
  4. Distinctive:

    Keep heavy experiments AutoDL/HPC-gated and user-approved.

    line 20
  5. Very specific:

    If the context window fills up mid-loop, Codex auto-compacts.

    line 49
  6. Very specific:

    On startup: if PAPER_IMPROVEMENT_STATE.json exists with "status": "in_progress" AND timestamp is within 24 hours, read it + …

    line 61
  7. Very specific:

    After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …

    line 111
  8. Distinctive:

    Verify: 0 undefined references, 0 undefined citations.

    line 163
  9. Very specific:

    Use mcp__gemini-review__review_reply_start with the saved completed threadId:

    line 167
  10. Distinctive:

    Add controlled synthetic experiments validating theory

    line 193
  11. Distinctive:

    After the final recompilation, run a format compliance check:

    line 207
  12. Distinctive:

    If any overfull hbox > 10pt is found, fix it and recompile before documenting.

    line 237
  13. Very specific:

    Create PAPER_IMPROVEMENT_LOG.md in the paper directory:

    line 241
  14. Very specific:

    After each round's review AND at final completion, check ~/.codex/feishu.json:

    line 298
  15. Very specific:

    If config absent or mode "off": skip entirely (no-op)

    line 301
  16. Very specific:

    Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.

    line 323

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Override for Codex users who want Gemini, not a second Codex agent, to act as the reviewer. Install this package after skills/skills-codex/*.

Customized Pack Defaults

This reviewer overlay is opt-in transport only. In the customized lightweight pack, default to prompt-only review unless the user explicitly asks to use this overlay reviewer backend:

  • Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.
  • Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
  • Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the skill-specific log.
  • Keep heavy experiments AutoDL/HPC-gated and user-approved; local work stays at edits, tests, lint, dry-runs, and tiny smoke checks.

Auto Paper Improvement Loop: Review → Fix → Recompile

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.

Unlike /auto-review-loop (which iterates on research — running experiments, collecting data, rewriting narrative), this skill iterates on paper writing quality — fixing theoretical inconsistencies, softening overclaims, adding missing content, and improving presentation.

Constants

  • MAX_ROUNDS = 2 — Two rounds of review→fix→recompile. Empirically, Round 1 catches structural issues (4→6/10), Round 2 catches remaining presentation issues (6→7/10). Diminishing returns beyond 2 rounds for writing-only improvements.
  • REVIEWER_MODEL = gemini-review — Gemini reviewer invoked through the local gemini-review MCP bridge. Set GEMINI_REVIEW_MODEL if you need a specific Gemini model override.
  • REVIEW_LOG = PAPER_IMPROVEMENT_LOG.md — Cumulative log of all rounds, stored in paper directory.
  • HUMAN_CHECKPOINT = false — When true, pause after each round's review and present score + weaknesses to the user. The user can approve fixes, provide custom modification instructions, skip specific fixes, or stop early. When false (default), runs fully autonomously.

💡 Override: /auto-paper-improvement-loop "paper/" — human checkpoint: true

Inputs

  1. Compiled paper — paper/main.pdf + LaTeX source files
  2. All section .tex files — concatenated for review prompt

State Persistence (Compact Recovery)

If the context window fills up mid-loop, Codex auto-compacts. To recover, this skill writes PAPER_IMPROVEMENT_STATE.json after each round:

{
  "current_round": 1,
  "thread_id": "019ce736-...",
  "last_score": 6,
  "status": "in_progress",
  "timestamp": "2026-03-13T21:00:00"
}

On startup: if PAPER_IMPROVEMENT_STATE.json exists with "status": "in_progress" AND timestamp is within 24 hours, read it + PAPER_IMPROVEMENT_LOG.md to recover context, then resume from the next round. Otherwise (file absent, "status": "completed", or older than 24 hours), start fresh.

After each round: overwrite the state file. On completion: set "status": "completed".

Workflow

Step 0: Preserve Original

cp paper/main.pdf paper/main_round0_original.pdf

Step 1: Collect Paper Text

Concatenate all section files into a single text block for the review prompt:

# Collect all sections in order
for f in paper/sections/*.tex; do
    echo "% === $(basename $f) ==="
    cat "$f"
done > /tmp/paper_full_text.txt

Step 2: Round 1 Review

Send the full paper text to Gemini review:

mcp__gemini-review__review_start:
  prompt: |
    You are reviewing a [VENUE] paper. Please provide a detailed, structured review.

    ## Full Paper Text:
    [paste concatenated sections]

    ## Review Instructions
    Please act as a senior ML reviewer ([VENUE] level). Provide:
    1. **Overall Score** (1-10, where 6 = weak accept, 7 = accept)
    2. **Summary** (2-3 sentences)
    3. **Strengths** (bullet list, ranked)
    4. **Weaknesses** (bullet list, ranked: CRITICAL > MAJOR > MINOR)
    5. **For each CRITICAL/MAJOR weakness**: A specific, actionable fix
    6. **Missing References** (if any)
    7. **Verdict**: Ready for submission? Yes / Almost / No

    Focus on: theoretical rigor, claims vs evidence alignment, writing clarity,
    self-containedness, notation consistency.

After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.

Save the returned jobId, poll mcp__gemini-review__review_status until done=true, then save the completed threadId for Round 2.

Step 2b: Human Checkpoint (if enabled)

Skip if HUMAN_CHECKPOINT = false.

Present the review results and wait for user input:

📋 Round 1 review complete.

Score: X/10 — [verdict]
Key weaknesses (by severity):
1. [CRITICAL] ...
2. [MAJOR] ...
3. [MINOR] ...

Reply "go" to implement all fixes, give custom instructions, "skip 2" to skip specific fixes, or "stop" to end.

Parse user response same as /auto-review-loop: approve / custom instructions / skip / stop.

Step 3: Implement Round 1 Fixes

Parse the review and implement fixes by severity:

Priority order:

  1. CRITICAL fixes (assumption mismatches, internal contradictions)
  2. MAJOR fixes (overclaims, missing content, notation issues)
  3. MINOR fixes (if time permits)

Common fix patterns:

IssueFix Pattern
Assumption-model mismatchRewrite assumption to match the model, add formal proposition bridging the gap
OverclaimsSoften language: "validate" → "demonstrate practical relevance", "comparable" → "qualitatively competitive"
Missing metricsAdd quantitative table with honest parameter counts and caveats
Theorem not self-containedAdd "Interpretation" paragraph listing all dependencies
Notation confusionRename conflicting symbols globally, add Notation paragraph
Missing referencesAdd to references.bib, cite in appropriate locations
Theory-practice gapExplicitly frame theory as idealized; add synthetic validation subsection

Step 4: Recompile Round 1

cd paper && latexmk -C && latexmk -pdf -interaction=nonstopmode -halt-on-error main.tex
cp main.pdf main_round1.pdf

Verify: 0 undefined references, 0 undefined citations.

Step 5: Round 2 Review

Use mcp__gemini-review__review_reply_start with the saved completed threadId:

mcp__gemini-review__review_reply_start:
  threadId: [saved from Round 1]
  prompt: |
    [Round 2 update]

    Since your last review, we have implemented:
    1. [Fix 1]: [description]
    2. [Fix 2]: [description]
    ...

    Please re-score and re-assess. Same format:
    Score, Summary, Strengths, Weaknesses, Actionable fixes, Verdict.

After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.

Step 5b: Human Checkpoint (if enabled)

Skip if HUMAN_CHECKPOINT = false. Same as Step 2b — present Round 2 review, wait for user input.

Step 6: Implement Round 2 Fixes

Same process as Step 3. Typical Round 2 fixes:

  • Add controlled synthetic experiments validating theory
  • Further soften any remaining overclaims
  • Formalize informal arguments (e.g., truncation → formal proposition)
  • Strengthen limitations section

Step 7: Recompile Round 2

cd paper && latexmk -C && latexmk -pdf -interaction=nonstopmode -halt-on-error main.tex
cp main.pdf main_round2.pdf

Step 8: Format Check

After the final recompilation, run a format compliance check:

# 1. Page count vs venue limit
PAGES=$(pdfinfo paper/main.pdf | grep Pages | awk '{print $2}')
echo "Pages: $PAGES (limit: 9 main body for ICLR/NeurIPS)"

# 2. Overfull hbox warnings (content exceeding margins)
OVERFULL=$(grep -c "Overfull" paper/main.log 2>/dev/null || echo 0)
echo "Overfull hbox warnings: $OVERFULL"
grep "Overfull" paper/main.log 2>/dev/null | head -10

# 3. Underfull hbox warnings (loose spacing)
UNDERFULL=$(grep -c "Underfull" paper/main.log 2>/dev/null || echo 0)
echo "Underfull hbox warnings: $UNDERFULL"

# 4. Bad boxes summary
grep -c "badness" paper/main.log 2>/dev/null || echo "0 badness warnings"

Auto-fix patterns:

IssueFix
Overfull hbox in equationWrap in \resizebox or split with \split/aligned
Overfull hbox in tableReduce font (\small/\footnotesize) or use \resizebox{\linewidth}{!}{...}
Overfull hbox in textRephrase sentence or add \allowbreak / \- hints
Over page limitMove content to appendix, compress tables, reduce figure sizes
Underfull hbox (loose)Rephrase for better line filling or add \looseness=-1

If any overfull hbox > 10pt is found, fix it and recompile before documenting.

Step 9: Document Results

Create PAPER_IMPROVEMENT_LOG.md in the paper directory:

# Paper Improvement Log

## Score Progression

| Round | Score | Verdict | Key Changes |
|-------|-------|---------|-------------|
| Round 0 (original) | X/10 | No/Almost/Yes | Baseline |
| Round 1 | Y/10 | No/Almost/Yes | [summary of fixes] |
| Round 2 | Z/10 | No/Almost/Yes | [summary of fixes] |

## Round 1 Review & Fixes

<details>
<summary>Gemini Review (Round 1)</summary>

[Full raw review text, verbatim]

</details>

### Fixes Implemented
1. [Fix description]
2. [Fix description]
...

## Round 2 Review & Fixes

<details>
<summary>Gemini Review (Round 2)</summary>

[Full raw review text, verbatim]

</details>

### Fixes Implemented
1. [Fix description]
2. [Fix description]
...

## PDFs
- `main_round0_original.pdf` — Original generated paper
- `main_round1.pdf` — After Round 1 fixes
- `main_round2.pdf` — Final version after Round 2 fixes

Step 9: Summary

Report to user:

  • Score progression table
  • Number of CRITICAL/MAJOR/MINOR issues fixed per round
  • Final page count
  • Remaining issues (if any)

Feishu Notification (if configured)

After each round's review AND at final completion, check ~/.codex/feishu.json:

  • After each round: Send review_scored — "Round N: X/10 — [key changes]"
  • After final round: Send pipeline_done — score progression table + final page count
  • If config absent or mode "off": skip entirely (no-op)

Output

paper/
├── main_round0_original.pdf    # Original
├── main_round1.pdf             # After Round 1
├── main_round2.pdf             # After Round 2 (final)
├── main.pdf                    # = main_round2.pdf
└── PAPER_IMPROVEMENT_LOG.md    # Full review log with scores

Output Protocols

Follow these shared protocols for all output files:

  • Output Versioning Protocol — write timestamped file first, then copy to fixed name
  • Output Manifest Protocol — log every output to docs/project/OUTPUT_MANIFEST.md
  • Output Language Protocol — respect the project's language setting

Key Rules

  • Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently.
  • Preserve all PDF versions — user needs to compare progression
  • Save FULL raw review text — do not summarize or truncate Gemini reviewer responses
  • Use mcp__gemini-review__review_reply_start plus mcp__gemini-review__review_status for Round 2 to maintain conversation context
  • Always recompile after fixes — verify 0 errors before proceeding
  • Do not fabricate experimental results — synthetic validation must describe methodology, not invent numbers
  • Respect the paper's claims — soften overclaims rather than adding unsupported new claims
  • Global consistency — when renaming notation or softening claims, check ALL files (abstract, intro, method, experiments, theory sections, conclusion, tables, figure captions)

Typical Score Progression

Based on end-to-end testing on a real theory-paper run:

RoundScoreKey Improvements
Round 04/10 (content)Baseline: assumption-model mismatch, overclaims, notation issues
Round 16/10 (content)Fixed assumptions, softened claims, added interpretation, renamed notation
Round 27/10 (content)Added synthetic validation, formal truncation proposition, stronger limitations
Round 35→8.5/10 (format)Removed hero fig, appendix, compressed conclusion, fixed overfull hbox

+4.5 points across 3 rounds (2 content + 1 format) is typical for a well-structured but rough first draft. Final state at submission: clean overfull-hbox count and venue-format-compliant length.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.