Menu
ResearchPilot Research Assistant [Phase G.0]: Paper planning
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
ResearchPilot ็ง็ ๅฉๆ[้ถๆฎต G.0]๏ผ่ฎบๆ่งๅ
Global-installable, project-level academic rebuttal strategy skill for AI/ML/CV/NLP/Robotics papers. Use when authors need a workspace-local .awesome-rebuttal state folder, paper/code/review/venue-rule intake, JSON memory, snapshots, LaTeX/template handling for one-page rebuttals, reviewer stance analysis, strategy planning, experiment triage, safe author response drafting, or AC summaries under confirmed venue rules.
Use when the user has a research question and needs a complete experiment package โ design document, runnable code, results (measured or simulated with honest provenance), publication-grade figures, structured report. Single-stage, no Python runtime.
Use when the user wants a paper audited for integrity issues โ image misuse, numerical anomalies, logical gaps โ and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6โ20 pages, 60+ real citations, 100+ recommended) with LaTeX source, taxonomy figures, and a classified literature table. Single-stage, no Python runtime.
Generate beautiful, high-resolution mindmaps from Markdown unordered lists. Outputs interactive HTML, HD PNG, and PDF with colorful branch themes.
| name | research[G.0]-plan |
| description | ResearchPilot Research Assistant [Phase G.0]: Paper planning |
| version | 2.0.0 |
| license | LICENSE |
user_requirements.md priority: All user constraints in
docs/user_requirements.mdtake precedence over any default instruction in this skill. Always read it before generating output.
| Skill | Responsibility |
|---|---|
/research[G.0]-plan | Update idea_report โ plan structure/figures โ select format |
/research[G.1]-method | Write / revise Method |
/research[G.2]-experiments | Write / revise Experiments |
/research[G.3]-abstract | Write / revise Abstract |
/research[G.4]-introduction | Write / revise Introduction |
/research[G.5]-related | Write / revise Related Works |
/research[G.6]-conclusion | Write / revise Conclusion + References |
/research[G.7]-review | Full-paper review (five dimensions + claim-evidence) |
/research[G.0]-plan
An optional natural-language instruction may follow the command. The AI will treat it as an additional constraint or supplement for this invocation.
Step 1: Update idea_report.md (compare with code, list diffs, user confirms, update in-place)
Step 2: Plan paper structure and figures (outline + per-section detail + figure/table plan)
Step 3: Ask for writing examples (before confirming structure; place in docs/manuscripts/examples/)
Step 4: Select paper format (md / LaTeX)
Step 5: Write detailed architecture comments into manuscript header
Step 6: Generate figure/table notebook cells in notebooks/figures.ipynb
See references/phase-G0.md for full details.
idea_report.md: Edit in-place, no backup. Prepend modification record to file header.
Manuscript (paper.md / paper.tex): Back up before editing, keep original as latest version:
cp paper.tex paper_{mm-dd_hh-mm}.tex
Append to file header after editing:
% Modified: {mm-dd_hh-mm}
% Changes: {what changed}
% Previous backup: paper_{mm-dd_hh-mm}.tex
references/template-flexibility.md take precedence over any specific template instruction.G.0 complete.
- idea_report.md updated
- Architecture comments written into manuscript header
- figures.ipynb: {N} figure/table cells created
- Format: {md/LaTeX}
Recommended writing order (Master-cai):
Method โ Experiments โ Abstract โ Introduction โ Related Works โ Conclusion
โ Use `/research[G.1]-method` to start writing Method.
references/phase-G0.mdreferences/template-flexibility.md