paper-plan
Skill9 starsChanged 3 months agoMITView on GitHub
Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Generate a structured paper outline from audited formal experiment results and review conclusions. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\", \"论文规划\", or wants a paper plan after formal runs and evidence audit. If only smoke, pilot, toy, or validation results exist, produce a gap report or next actions instead of routing to manuscript drafting.
12 other projects use a version of this, 6 of them edited.
Adopted by
Most recently taken up by
- PKU-DAIR/AutoScitheir own version, first seen Oct 25, 2026
- DAIR-AutoResearch/AutoScitheir own version, first seen Oct 15, 2026
- wangyi0403/dl-research-workflowtheir own version, first seen Oct 13, 2026
- skyllwt/OmegaWikitheir own version, first seen Oct 8, 2026
- skyllwt/AutoScitheir own version, first seen Sep 28, 2026
- talhaMah56/claude_skillsedited, first seen Sep 12, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 9 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.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
raja21068Skillpaper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says \"生成图表\", \"画架构图\", \"AI绘图\", \"paper illustration\", \"generate diagram\", or needs visual figures for papers.
Also in 6 projects that use this
raja21068Skilldeepxiv
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
Also in 4 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
- +5 more from Lambenthan
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k36% same
- Chanw-research/claude-code-paper-writing★ 4252% same
- catalsqlb-cmd/Prism-H★ 1653% same
- Yusong-Enceladus/claude-skills★ 889% same
- raja21068/AutoResearch★ 252% same
- talhaMah56/claude_skills★ 037% same
Wrote their own version · 6
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- Lambenthan/empiricalwiki★ 85same name
- wangyi0403/dl-research-workflow★ 4same name
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-posterSkill
- paper-slidesSkill
- paper-writeSkill
- paper-writingSkill
- 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
14 rules. 0 are common, 8 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
6
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 22
Keep the manuscript-entry gate from the base paper-plan: formal runs plus docs/evidence/EVIDENCE_LEDGER.md or CLAIMS_FROM_RESULTS.md are …
- Distinctive: line 45
If none exist, ask the user to describe the paper's contribution in 3-5 sentences.
- Distinctive: line 54
Run the paper-plan entry gate before drafting the outline:
- Very specific: line 59
If either check fails, do not produce a normal paper plan and do not list /paper-write or /paper-writing as a next step.
- Distinctive: line 63
Read all available narrative documents and extract:
- Distinctive: line 210
NEVER generate BibTeX from memory — always verify via search or existing .bib files
- Distinctive: line 211
Every citation must be verified: correct authors, year, venue
- Distinctive: line 213
Prefer published versions over arXiv preprints when available
- Very specific: line 236
After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …
- Very specific: line 295
Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.
“Common” is measured: kept by at least 6 in 10 of the 11 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.
- Keep the manuscript-entry gate from the base
paper-plan: formal runs plusdocs/evidence/EVIDENCE_LEDGER.mdorCLAIMS_FROM_RESULTS.mdare required before a normaldocs/paper/PAPER_PLAN.mdmay hand off to drafting.
Paper Plan: From Review Conclusions to Paper Outline
Generate a structured, section-by-section paper outline from: $ARGUMENTS
Constants
- REVIEWER_MODEL =
gemini-review— Gemini reviewer invoked through the localgemini-reviewMCP bridge. SetGEMINI_REVIEW_MODELif you need a specific Gemini model override. - TARGET_VENUE =
ICLR— Default venue. User can override (e.g.,/paper-plan "topic" — venue: NeurIPS). Supported:ICLR,NeurIPS,ICML. - MAX_PAGES — Main body page limit, measured from first page to end of Conclusion section (excluding references, appendix, and acknowledgements). ICLR=9, NeurIPS=9, ICML=8.
Inputs
The skill expects one or more of these in the project directory:
- NARRATIVE_REPORT.md or STORY.md — research narrative with claims and evidence
- review-stage/AUTO_REVIEW.md — auto-review loop conclusions (fall back to
./AUTO_REVIEW.mdif not found) - Experiment results — JSON files in
figures/, screen logs, tables - idea-stage/IDEA_REPORT.md — from idea-discovery pipeline (if applicable) (fall back to
./IDEA_REPORT.mdif not found)
If none exist, ask the user to describe the paper's contribution in 3-5 sentences.
For regular paper planning, results must be formal and auditable. Smoke, pilot, toy, or validation runs are blockers for manuscript handoff.
Workflow
Step 1: Extract Claims and Evidence
Run the paper-plan entry gate before drafting the outline:
- Confirm formal run evidence exists for paper-level claims.
- Confirm
docs/evidence/EVIDENCE_LEDGER.md,CLAIMS_FROM_RESULTS.md, or an equivalent audit maps claims to raw evidence and unresolved gaps. - If either check fails, do not produce a normal paper plan and do not list
/paper-writeor/paper-writingas a next step. Producedocs/project/NEXT_ACTIONS.mdordocs/paper/GAP_REPORT.mdand stop.
Read all available narrative documents and extract:
- Core claims (3-5 main contributions)
- Evidence for each claim (which experiments, which metrics, which figures)
- Known weaknesses (from reviewer feedback)
- Suggested framing (from review conclusions)
Build a Claims-Evidence Matrix:
| Claim | Evidence | Status | Section |
|-------|----------|--------|---------|
| [claim 1] | [exp A, metric B] | Supported | §3.2 |
| [claim 2] | [exp C] | Partially supported | §4.1 |Step 2: Determine Paper Type and Structure
Based on TARGET_VENUE and paper content, classify and select structure.
IMPORTANT: The section count is FLEXIBLE (5-8 sections). Choose what fits the content best. The templates below are starting points, not rigid constraints.
For systems, memory, query-processing, benchmark, IEEE, or Overleaf papers,
read ../../skills-codex/shared-references/icde-yu-memory-paper-structure.md
and prefer its ICDE_YU_Memory section topology when it fits the evidence.
Empirical/Diagnostic paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Method / Setup (1.5 pages)
4. Experiments (3 pages)
5. Analysis / Discussion (1 page)
6. Conclusion (0.5 pages)Theory + Experiments paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Preliminaries & Modeling (1.5 pages)
4. Experiments (1.5 pages)
5. Theory Part A (1.5 pages)
6. Theory Part B (1.5 pages)
7. Conclusion (0.5 pages)
— Total: 9 pagesTheory papers often need 7 sections (splitting theory into estimation + optimization, or setup + analysis). The total page budget MUST sum to MAX_PAGES.
Theory papers should:
- Include proof sketch locations (not just theorem statements)
- Plan a comparison table of prior theoretical bounds vs. this paper's bounds
- Identify which proofs go in appendix vs. main body
Method paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Method (2 pages)
4. Experiments (2.5 pages)
5. Ablation / Analysis (1 page)
6. Conclusion (0.5 pages)Step 3: Section-by-Section Planning
For each section, specify:
### §0 Abstract
- **One-sentence problem**: [what gap this paper addresses]
- **Approach**: [what we do, in one sentence]
- **Key result**: [most compelling quantitative finding]
- **Implication**: [why it matters]
- **Estimated length**: 150-250 words
- **Self-contained check**: can a reader understand this without the paper?
### §1 Introduction
- **Opening hook**: [1-2 sentences that motivate the problem]
- **Gap**: [what's missing in prior work]
- **Key questions**: [the research questions this paper answers]
- **Contributions**: [numbered list, matching Claims-Evidence Matrix]
- **Hero figure**: [describe what Figure 1 should show — MUST include clear comparison if applicable]
- **Estimated length**: 1.5 pages
- **Key citations**: [3-5 papers to cite here]
### §2 Related Work
- **Subtopics**: [2-4 categories of related work]
- **Positioning**: [how this paper differs from each category]
- **Minimum length**: 1 full page (at least 3-4 paragraphs with substantive synthesis)
- **Must NOT be just a list** — synthesize, compare, and position
### §3 Method / Setup / Preliminaries
- **Notation**: [key symbols and their meanings]
- **Problem formulation**: [formal setup]
- **Method description**: [algorithm, model, or experimental design]
- **Formal statements**: [theorems, propositions if applicable]
- **Proof sketch locations**: [which key steps appear here vs. appendix]
- **Estimated length**: 1.5-2 pages
### §4 Experiments / Main Results
- **Figures planned**:
- Fig 1: [description, type: bar/line/table/architecture, WHAT COMPARISON it shows]
- Fig 2: [description]
- Table 1: [what it shows, which methods/baselines compared]
- **Data source**: [which JSON files / experiment results]
### §5 Conclusion
- **Restatement**: [contributions rephrased, not copy-pasted from intro]
- **Limitations**: [honest assessment — reviewers value this]
- **Future work**: [1-2 concrete directions]
- **Estimated length**: 0.5 pagesStep 4: Figure Plan
List every figure and table:
## Figure Plan
| ID | Type | Description | Data Source | Priority |
|----|------|-------------|-------------|----------|
| Fig 1 | Hero/Architecture | System overview + comparison | manual | HIGH |
| Fig 2 | Line plot | Training curves comparison | figures/exp_A.json | HIGH |
| Fig 3 | Bar chart | Ablation results | figures/ablation.json | MEDIUM |
| Table 1 | Comparison table | Main results vs. baselines | figures/main_results.json | HIGH |
| Table 2 | Theory comparison | Prior bounds vs. ours | manual | HIGH (theory papers) |CRITICAL for Figure 1 / Hero Figure: Describe in detail what the figure should contain, including:
- Which methods are being compared
- What the visual difference should demonstrate
- Caption draft that clearly states the comparison
Step 5: Citation Scaffolding
For each section, list required citations:
## Citation Plan
- §1 Intro: [paper1], [paper2], [paper3] (problem motivation)
- §2 Related: [paper4]-[paper10] (categorized by subtopic)
- §3 Method: [paper11] (baseline), [paper12] (technique we build on)Citation rules (from claude-scholar + Imbad0202/academic-research-skills):
- NEVER generate BibTeX from memory — always verify via search or existing .bib files
- Every citation must be verified: correct authors, year, venue
- Flag any citation you're unsure about with
[VERIFY] - Prefer published versions over arXiv preprints when available
Step 6: Cross-Review with REVIEWER_MODEL
Send the complete outline to Gemini review for feedback:
mcp__gemini-review__review_start:
prompt: |
Review this paper outline for a [VENUE] submission.
[full outline including Claims-Evidence Matrix]
Score 1-10 on:
1. Logical flow — does the story build naturally?
2. Claim-evidence alignment — every claim backed?
3. Missing experiments or analysis
4. Positioning relative to prior work
5. Page budget feasibility (MAX_PAGES = main body to Conclusion end, excluding refs/appendix)
For each weakness, suggest the MINIMUM fix.
Be specific and actionable — "add X" not "consider more experiments".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.
Apply feedback before finalizing.
Step 7: Output
Save the final outline to docs/paper/PAPER_PLAN.md:
# Paper Plan
**Title**: [working title]
**Venue**: [target venue]
**Type**: [empirical/theory/method]
**Date**: [today]
**Page budget**: [MAX_PAGES] pages (main body to Conclusion end, excluding references & appendix)
**Section count**: [N] (must match the number of section files that will be created)
## Claims-Evidence Matrix
[from Step 1]
## Structure
[from Step 2-3, section by section]
## Figure Plan
[from Step 4, with detailed hero figure description]
## Citation Plan
[from Step 5]
## Reviewer Feedback
[from Step 6, summarized]
## Next Steps
[Choose exactly one block.]
### Manuscript entry gate PASSED
- [ ] /paper-figure to generate all figures
- [ ] /paper-write to draft LaTeX
- [ ] /paper-compile to build PDF
### Manuscript entry gate NOT PASSED
- [ ] Complete missing formal runs through /autodl-hpc or /experiment-plan
- [ ] Run /experiment-audit or complete docs/evidence/EVIDENCE_LEDGER.md
- [ ] Rerun /paper-plan after the evidence gate passesOutput 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
- No manuscript handoff without formal evidence — if formal runs or the
evidence audit are missing, stop at gap reporting and do not recommend
/paper-write,/paper-writing, or LaTeX drafting. - 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. - Do NOT generate author information — leave author block as placeholder or anonymous
- Be honest about evidence gaps — mark claims as "needs experiment" rather than overclaiming
- Page budget is hard — if content exceeds MAX_PAGES, suggest what to move to appendix
- MAX_PAGES counts main body only — from first page to end of Conclusion. References and appendix are NOT counted.
- Venue-specific norms — all three venues (ICLR/NeurIPS/ICML) use
natbib(\citep/\citet) - Claims-Evidence Matrix is the backbone — every claim must map to evidence, every experiment must support a claim
- Figures need detailed descriptions — especially the hero figure, which must clearly specify comparisons and visual expectations
- Section count is flexible — 5-8 sections depending on paper type. Don't force content into a rigid 5-section template.
Acknowledgements
Outline methodology inspired by Research-Paper-Writing-Skills (claim-evidence mapping), claude-scholar (citation verification), and Imbad0202/academic-research-skills (claim verification protocol).
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.

