paper-writing
Skill9 starsChanged 3 months agoMITView on GitHub
Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Workflow 3: evidence-gated paper writing pipeline. Requires audited formal experiment evidence and an accepted paper plan before manuscript drafting. If only smoke, pilot, toy, or validation results exist, stop and produce next actions or a gap report. Use when user says \\\"\u5199\u8bba\u6587\u5168\u6d41\u7a0b\\\", \\\"write paper pipeline\\\", \\\"\u4ece\u62a5\u544a\u5230PDF\\\", \\\"paper writing\\\", or wants complete paper generation from audited evidence.
- Reads credentials
38 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- DragonGong/skillstheir own version, first seen Nov 16, 2026
- DrNbnonono/skillstheir own version, first seen Nov 15, 2026
- kinhluan/skillstheir own version, first seen Nov 8, 2026
- 70asunflower/70asunflower-skillstheir own version, first seen Nov 8, 2026
- SNL-UCSB/paper-writing-skilltheir own version, first seen Nov 4, 2026
- VeryMath/AI4Math-Writingtheir own version, first seen Nov 3, 2026
Used with
Projects with it also use ml-training-recipe, replication and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
getcompanion-aiSkillml-training-recipe
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.
Also in 3 projects that use this
getcompanion-aiSkillreplication
Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.
Also in 3 projects that use this
brainbytes-devSkillalpha-research
Also in 3 projects that use this
JaimeParkerSkillpaper-code-audit
Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.
Also in 3 projects that use this
JimLiuSkillpdf-explore
Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.
Also in 4 projects that use this
Yusong-EnceladusSkillproof-writer
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
Also in 3 projects that use this
- +1 more from getcompanion-ai
Other versions38 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k11% same
- Chanw-research/claude-code-paper-writing★ 4224% same
- catalsqlb-cmd/Prism-H★ 1623% same
- Yusong-Enceladus/claude-skills★ 868% same
- raja21068/AutoResearch★ 224% same
- Shri-Phnx/claude-skills★ 210% same
- talhaMah56/claude_skills★ 010% same
Wrote their own version · 31
- advaitpaliwal/feynman★ 10ksame name
- companion-inc/feynman★ 10ksame name
- getcompanion-ai/feynman★ 10ksame name
- MLNLP-World/Paper-Writing-Tips★ 4.7ksame name
- ZimoLiao/scholaraio★ 589same name
- EvoScientist/EvoSkills★ 486same name
- SNL-UCSB/paper-writing-skill★ 249same name
- voidful/academic-skills★ 126same name
- TenureAI/PhD-Zero★ 52same name
- HughYau/pengsida-learning-research-skills★ 27same name
21 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- autodl-hpcSkill
- experiment-bridgeSkill
- experiment-planSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
- autodl-hpcSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- experiment-bridgeSkill
- experiment-planSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- grant-proposalSkill
- idea-creatorSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-posterSkill
- paper-slidesSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 8 are distinctive, and 9 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.
- Distinctive: line 16
Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
- Very specific: line 18
Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the …
- Distinctive: line 20
Keep heavy experiments AutoDL/HPC-gated and user-approved.
- Very specific: line 38
Default manuscript package target follows ../../skills-codex/shared-references/icde-yu-memory-paper-structure.md.
- Very specific: line 71
Before Phase 1, inspect PROJECT_STATUS.md, docs/project/BLUEPRINT_GATE.md, docs/paper/PAPER_PLAN.md, docs/evidence/EVIDENCE_LEDGER.md, …
- Very specific: line 126
Read figure plan from PAPER_PLAN.md
- Very specific: line 129
Create figures/latex_includes.tex for easy insertion
- Very specific: line 138
If the paper plan includes architecture diagrams, pipeline figures, or method illustrations, invoke /paper-illustration:
- Distinctive: line 173
Write each section following the plan, with proper LaTeX formatting
- Distinctive: line 242
Add missing interpretations and notation
- Distinctive: line 244
Add theory-aligned experiments if needed
- Very specific: line 306
Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.
- Very specific: line 309
Checkpoint between phases: when AUTO_PROCEED=false. Present results and wait for approval.
- Distinctive: line 310
Manual figures first: If the paper needs architecture diagrams or qualitative results, the user must provide them before Phase 3.
- Distinctive: line 311
Compilation must succeed: before entering the improvement loop.
- Distinctive: line 314
Respect page limits: If the paper exceeds the venue limit, suggest specific cuts before the improvement loop.
“Common” is measured: kept by at least 6 in 10 of the 28 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.
Files
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.
Workflow 3: Evidence-Gated Paper Writing Pipeline
Orchestrate an evidence-gated paper writing workflow for: $ARGUMENTS
Overview
This skill chains five sub-skills into a single automated pipeline:
/paper-plan → /paper-figure → /paper-write → /paper-compile → /auto-paper-improvement-loop
(outline) (plots) (LaTeX) (build PDF) (review & polish ×2)Each phase builds on the previous one's output. The final deliverable is a polished, reviewed paper/ directory with LaTeX source and compiled PDF.
Default manuscript package target follows
../../skills-codex/shared-references/icde-yu-memory-paper-structure.md.
For new IEEE/Overleaf starts, prefer thin main.tex, Content/, Figure/,
and IEEE.bib; preserve sections/, figures/, and references.bib for
existing projects.
Constants
- VENUE =
ICLR— Target venue. Options:ICLR,NeurIPS,ICML. Affects style file, page limit, citation format. - MAX_IMPROVEMENT_ROUNDS = 1 — Number of review→fix→recompile rounds in the improvement loop.
- REVIEWER_MODEL =
gemini-review— Gemini reviewer invoked through the localgemini-reviewMCP bridge for plan review, figure review, writing review, and the improvement loop. - AUTO_PROCEED = false — Pause between phases unless the user explicitly opts into auto-continue.
- HUMAN_CHECKPOINT = true — Pause after each improvement review so the user can inspect the score and provide custom modification instructions. Passed through to
/auto-paper-improvement-loop.
Override inline:
/paper-writing "NARRATIVE_REPORT.md" — venue: NeurIPS, human checkpoint: true
Inputs
This pipeline accepts one of:
- Accepted
docs/paper/PAPER_PLAN.mdplus audited formal evidence — best. NARRATIVE_REPORT.mdplus audited formal evidence — allowed only if the entry gate passes.- Research direction + validation results — not enough for manuscript
drafting; produce
docs/project/NEXT_ACTIONS.mdordocs/paper/GAP_REPORT.mdand stop.
The more detailed the input (especially figure descriptions and quantitative results), the better the output.
Pipeline
Phase 0: Manuscript Entry Gate
Before Phase 1, inspect PROJECT_STATUS.md, docs/project/BLUEPRINT_GATE.md,
docs/paper/PAPER_PLAN.md, docs/evidence/EVIDENCE_LEDGER.md,
CLAIMS_FROM_RESULTS.md, docs/experiments/EXPERIMENT_LOG.md, and raw result
folders when present.
Proceed only if formal runs exist, raw evidence is auditable, and
docs/evidence/EVIDENCE_LEDGER.md / CLAIMS_FROM_RESULTS.md maps claims to raw
evidence and unresolved gaps. If any check fails, stop before Phase 1. Do not
create paper/, LaTeX section files, or docs/paper/PAPER_GUIDE.md; write
docs/project/NEXT_ACTIONS.md or docs/paper/GAP_REPORT.md instead.
Smoke, pilot, toy, or validation runs never satisfy this gate.
Phase 1: Paper Plan
Invoke /paper-plan to create the structural outline:
/paper-plan "$ARGUMENTS"What this does:
- Parse NARRATIVE_REPORT.md for claims, evidence, and figure descriptions
- Build a Claims-Evidence Matrix — every claim maps to evidence, every experiment supports a claim
- Design section structure (5-8 sections depending on paper type)
- Plan figure/table placement with data sources
- Scaffold citation structure
- Gemini reviews the plan for completeness via the
/paper-planoverlay
Output: PAPER_PLAN.md with section plan, figure plan, citation scaffolding.
Checkpoint: Present the plan summary to the user.
📐 Paper plan complete:
- Title: [proposed title]
- Sections: [N] ([list])
- Figures: [N] auto-generated + [M] manual
- Target: [VENUE], [PAGE_LIMIT] pages
Shall I proceed with figure generation?- User approves (or AUTO_PROCEED=true) → proceed to Phase 2.
- User requests changes → adjust plan and re-present.
Phase 2: Figure Generation
Invoke /paper-figure to generate data-driven plots and tables:
/paper-figure "PAPER_PLAN.md"What this does:
- Read figure plan from PAPER_PLAN.md
- Generate matplotlib/seaborn plots from JSON/CSV data
- Generate LaTeX comparison tables
- Create
figures/latex_includes.texfor easy insertion - Gemini reviews figure quality and captions via the
/paper-figureoverlay
Output: figures/ directory with PDFs, generation scripts, and LaTeX snippets.
Phase 2b: AI Illustration Generation (when illustration: true)
Skip this step entirely if illustration is not set or is false.
If the paper plan includes architecture diagrams, pipeline figures, or method illustrations, invoke /paper-illustration:
/paper-illustration "[method description from PAPER_PLAN.md or NARRATIVE_REPORT.md]"What this does:
- Codex plans the layout → Gemini optimizes → Nano Banana Pro renders → Codex reviews (score ≥ 9)
- Output:
figures/ai_generated/*.png— publication-quality method diagrams - Requires
GEMINI_API_KEYenvironment variable
Without
illustration: true: Architecture diagrams must still be created manually (draw.io, Figma, TikZ) and placed infigures/before proceeding — same as before.
Checkpoint: List generated vs manual figures.
📊 Figures complete:
- Data plots (auto): [list]
- AI illustrations (auto): [list, if illustration: true]
- Manual (need your input): [list]
- LaTeX snippets: figures/latex_includes.tex
[If manual figures needed]: Please add them to figures/ before I proceed.
[If all auto]: Shall I proceed with LaTeX writing?Phase 3: LaTeX Writing
Invoke /paper-write to generate section-by-section LaTeX:
/paper-write "PAPER_PLAN.md"What this does:
- Write each section following the plan, with proper LaTeX formatting
- Insert figure/table references from
figures/latex_includes.tex - Build
references.bibfrom citation scaffolding - Clean stale files from previous section structures
- Automated bib cleaning (remove uncited entries)
- De-AI polish (remove "delve", "pivotal", "landscape"...)
- Gemini reviews each section for quality via the
/paper-writeoverlay
Output: paper/ directory with main.tex, sections/*.tex, references.bib, math_commands.tex.
Checkpoint: Report section completion.
✍️ LaTeX writing complete:
- Sections: [N] written ([list])
- Citations: [N] unique keys in references.bib
- Stale files cleaned: [list, if any]
Shall I proceed with compilation?Phase 4: Compilation
Invoke /paper-compile to build the PDF:
/paper-compile "paper/"What this does:
latexmk -pdfwith automatic multi-pass compilation- Auto-fix common errors (missing packages, undefined refs, BibTeX syntax)
- Up to 3 compilation attempts
- Post-compilation checks: undefined refs, page count, font embedding
- Precise page verification via
pdftotext - Stale file detection
Output: paper/main.pdf
Checkpoint: Report compilation results.
🔨 Compilation complete:
- Status: SUCCESS
- Pages: [X] (main body) + [Y] (references) + [Z] (appendix)
- Within page limit: YES/NO
- Undefined references: 0
- Undefined citations: 0
Shall I proceed with the improvement loop?Phase 5: Auto Improvement Loop
Invoke /auto-paper-improvement-loop to polish the paper:
/auto-paper-improvement-loop "paper/"What this does (2 rounds):
Round 1: Gemini reviews the full paper → identifies CRITICAL/MAJOR/MINOR issues → Codex implements fixes → recompile → save main_round1.pdf
Round 2: Gemini re-reviews with conversation context → identifies remaining issues → Codex implements fixes → recompile → save main_round2.pdf
Typical improvements:
- Fix assumption-model mismatches
- Soften overclaims to match evidence
- Add missing interpretations and notation
- Strengthen limitations section
- Add theory-aligned experiments if needed
Output: Three PDFs for comparison + PAPER_IMPROVEMENT_LOG.md.
Format check (included in improvement loop Step 8): After final recompilation, auto-detect and fix overfull hboxes (content exceeding margins), verify page count vs venue limit, and ensure compact formatting. Any overfull > 10pt is fixed before generating the final PDF.
Phase 6: Final Report
# Paper Writing Pipeline Report
**Input**: [NARRATIVE_REPORT.md or topic]
**Venue**: [ICLR/NeurIPS/ICML]
**Date**: [today]
## Pipeline Summary
| Phase | Status | Output |
|-------|--------|--------|
| 1. Paper Plan | ✅ | PAPER_PLAN.md |
| 2. Figures | ✅ | figures/ ([N] auto + [M] manual) |
| 3. LaTeX Writing | ✅ | paper/sections/*.tex ([N] sections, [M] citations) |
| 4. Compilation | ✅ | paper/main.pdf ([X] pages) |
| 5. Improvement | ✅ | [score0]/10 → [score2]/10 |
## Improvement Scores
For ICDE-style IEEE/Overleaf drafts, interpret `paper/sections/*.tex` in the
summary above as `paper/Content/*.tex`, and `references.bib` as `IEEE.bib`.
| Round | Score | Key Changes |
|-------|-------|-------------|
| Round 0 | X/10 | Baseline |
| Round 1 | Y/10 | [summary] |
| Round 2 | Z/10 | [summary] |
## Deliverables
- paper/main.pdf — Final polished paper
- paper/main_round0_original.pdf — Before improvement
- paper/main_round1.pdf — After round 1
- paper/main_round2.pdf — After round 2
- paper/PAPER_IMPROVEMENT_LOG.md — Full review log
## Remaining Issues (if any)
- [items from final review that weren't addressed]
## Next Steps
- [ ] Visual inspection of PDF
- [ ] Add any missing manual figures
- [ ] Submit to [venue] via OpenReview / CMT / HotCRPOutput 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
- Note: paper content is always written in English regardless of project 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. - Don't skip phases. Each phase builds on the previous one — skipping leads to errors.
- Checkpoint between phases when AUTO_PROCEED=false. Present results and wait for approval.
- Manual figures first. If the paper needs architecture diagrams or qualitative results, the user must provide them before Phase 3.
- Compilation must succeed before entering the improvement loop. Fix all errors first.
- Preserve all PDFs. The user needs round0/round1/round2 for comparison.
- Document everything. The pipeline report should be self-contained.
- Respect page limits. If the paper exceeds the venue limit, suggest specific cuts before the improvement loop.
Composing with Other Workflows
/idea-discovery "direction" -> find/refine ideas
/research-blueprint -> freeze theory, method, and experiment gates
/autodl-hpc or /experiment-plan -> formal runs, not local heavy compute
/experiment-audit or evidence ledger update -> map formal results to claims
/paper-plan "docs/paper/NARRATIVE_REPORT.md" -> plan only after evidence gate passes
/paper-writing "docs/paper/PAPER_PLAN.md" -> draft only after manuscript entry gate passes
If the project has only smoke, pilot, toy, or validation results, stay in the
experiment/audit phases and do not run this skill.Typical Timeline
| Phase | Duration | Can sleep? |
| 1. Paper Plan | 5-10 min | No |
| 2. Figures | 5-15 min | No |
| 3. LaTeX Writing | 15-30 min | Yes ✅ |
| 4. Compilation | 2-5 min | No |
| 5. Improvement | 15-30 min | Yes ✅ |
Total: ~45-90 min for a full paper from narrative report to polished PDF.
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
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.

