claude-code-research-skills

Generate clean, EDITABLE vector figures (SVG + exact-size PDF) for research papers — method / architecture / pipeline / system-overview diagrams — with AutoFigure-Edit. Use whenever the user wants to create or vectorize a paper figure from a text description OR from a draft/screenshot/draw.io image: it generates a step-1 raster with OpenAI gpt-image-2 by default (nano-banana optional), then runs local SAM3 segmentation + RMBG-2.0 icon extraction + an LLM SVG re-draw with OpenAI gpt-5.5 into an editable SVG, and exports a margin-free PDF for \includegraphics. Triggers: make a paper figure, method/architecture/pipeline/framework diagram, vectorize a diagram, "editable SVG figure", "用 AutoFigure / AutoFigure-Edit 画图", 论文方法图/流程图/架构图.

Generate, edit, describe, or batch-generate images from the terminal using OpenClaw + OpenAI gpt-image-2 (billed to the ChatGPT/Codex subscription, not the API). Use whenever the user asks to create / draw / generate an image, picture, icon, logo, illustration, poster, diagram, architecture figure, flowchart, or infographic — to produce a set / batch of multiple images from several prompts — or to edit an existing image (inpaint / restyle / combine) or describe what is in an image file.

Generate images from the terminal with Google's nano-banana (Gemini image model) via the Antigravity CLI (`agy`), billed to the signed-in Google account. Use whenever the user asks to create / draw / generate an image, picture, icon, logo, illustration, poster, infographic, or diagram specifically with nano-banana / Gemini / Antigravity — or wants rich, text-heavy infographics. For the OpenAI gpt-image-2 path use the separate `gpt-image` skill instead.

Staged, diagnosis-driven academic paper polishing pipeline (bilingual 中文/English). Use to revise a paper from rough draft to final submission across ordered stages: diagnose first, then optimize section by section, derive abstract/contributions from the revised body, polish the language to reduce AI-sounding phrasing, and run a pre-submission/defense risk check. Enforces research-integrity guardrails: no fabricated references/data, no overclaiming, correlation is not causation, limited samples are not universal laws, and missing information is flagged not invented. Works for thesis, journal, course paper, and grant proposal. Also trigger on Chinese phrasings like 论文润色、论文修改、论文诊断、 降AI味、降低AI味、引言重构、文献综述优化、研究方法规范、结果讨论深化、摘要提炼、 创新点提炼、答辩问题预测、投稿前检查、终稿风险检查、毕业论文修改、期刊论文润色.

12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use when the user needs coordinated multi-step literature workflows beyond a single MCP call. Also trigger on general literature-search needs during academic writing even without the word "Nature", such as searching for papers/literature, doing a literature review, verifying a citation, converting citation files, and Chinese phrasings like 文献检索、查文献、找文献、 文献综述检索、查论文、引文核对、参考文献管理、文献去重.

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF.

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF. Also trigger on general academic-writing citation needs even without the word "Nature", such as adding references while writing a paper, finding sources/literature for a claim, building a reference list, citation/referencing for academic writing, and Chinese phrasings like 学术写作引用、写论文加引用、写paper找文献、加参考文献、配文献、引用文献、文献支撑.

Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Best suited when the diagram needs custom styling, rich shape vocabulary, swimlanes, or exportable images (PNG/SVG/PDF/JPG). Generates .drawio XML and exports locally via the native draw.io desktop CLI.

Human-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDIDATE-IMAGE. Use for paper-grounded architecture, pipeline, method overview, agent workflow, system/data-flow, and mechanism figures with generated raster first-round/formal candidates, reviewer-first-glance layout gates, semantic-vs-visual graph separation, edge-label-first carried-variable contracts, internal visual motif planning, cumulative checkpoint recovery, and a strict human-decision boundary after S5. Version 3.2.15b keeps S2 and S5 as image-generation-only public stages, preserves the strict human-decision boundary after terminal S5 candidate generation, adds hard prompt-index/candidate/artifact/checkpoint ID coherence, enforces strict source-grounded modular prompt contracts across all generic projects, places the origin/reply principles at the top of the controller, requires response-time cumulative checkpoint zip validation for every workflow text reply, requires preference-led second-roun