Research

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when user mentions academic research, scholarly writing, papers, or scientific literature.

Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.

从多数据库学术论文检索下载与引文提取（arXiv/PubMed/Semantic Scholar/Google Scholar）、跨平台系统性文献检索（IEEE/ACM/Scopus/Web of Science）与批量PDF下载元数据提取索引生成，到科研文献智能监测与中文摘要定时推送、知网CNKI高级检索自动化与真实参考文献引用规范管理的完整论文检索工作流。覆盖文献搜索、批量下载、智能监测、引用管理全链路。

从透明严谨的双轮深度调研（APA引用/证据分级/用户确认）与专精文献综述论文分析学术写作、12要素结构化论文拆解（研究背景/问题/方法/贡献/不足/展望）与8阶段系统性中英文文献回顾，到论文大纲文献综述框架摘要生成引用格式规范与学术写作文献综述研究方法撰写的完整文献综述工作流。覆盖文献调研、论文拆解、综述撰写、格式规范全链路。

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.

Beginner-friendly workflow for Low-noise observation methodology for anti-hook and anti-instrumentation research. Extracts general methods and evidence practices without depending on any author, private repository, personal path, secret, or branded prompt. Use when a reverse-engineering task needs reliable observation, loader analysis, runtime evidence, dump validation, crash attribution, tool setup, or reproducible reporting.

Beginner-friendly workflow for Detailed reverse-engineering experiment records, timelines, commands, diffs, decisions, and handoff notes. Extracts general methods and evidence practices without depending on any author, private repository, personal path, secret, or branded prompt. Use when a reverse-engineering task needs reliable observation, loader analysis, runtime evidence, dump validation, crash attribution, tool setup, or reproducible reporting.

Beginner-friendly workflow for Windows, Linux, and macOS host differences, paths, ABI, tool discovery, and reproducible lab setup. Extracts general methods and evidence practices without depending on any author, private repository, personal path, secret, or branded prompt. Use when a reverse-engineering task needs reliable observation, loader analysis, runtime evidence, dump validation, crash attribution, tool setup, or reproducible reporting.

Universal document conversion with Pandoc. Use when converting between document formats (Markdown, DOCX, HTML, LaTeX, PDF, EPUB, PPTX, reveal.js, CSV, RST, Org), generating polished deliverables from plain text, batch-converting files, applying custom templates or Lua filters, or producing slide decks from Markdown.

Deep multi-source research synthesis — web, academic, patent, and internal KB cross-referencing

Install or update Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path, then surface any per-skill install.md guidance. Use when a user asks to list installable skills, install a curated skill, update an installed skill, or install a skill from another repo (including private repos).

Store and inspect source-indexed proof material extracted from papers, notes, PDFs, or LaTeX sources. Use when Codex needs stable material IDs, source locations, reusable abstractions, proof skeletons, tags, and public attribution before any proof ideas are cooked into proof-usage.

Synthesize source-indexed proof-material items into the final proof-usage playbook. Use when Codex needs to cluster proof items by proof shape, de-duplicate across sources, design reusable taxonomy entries, update proof-usage indexes and source maps, or preserve material-ID links from cooked proof entries.

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

21-rule prose review workflow for technical and academic Markdown/LaTeX excerpts. Use when the user asks for muxing-style-review, wants a complete agent-style check combining check-human.md with agent-style audit-only evidence, wants a compact-rule check, wants a DeepSeek/Codex manuscript draft checked for clarity, evidence, citation discipline, terminology, AI-tell prose, or wants an A/B draft comparison. Prefer a dedicated review subagent when available for non-trivial reviews. Use the sibl...

Chrome-dependent academic paper fetching and BibTeX curation. Use when the user provides a planNN.md, paper list, citation list, or literature plan and wants Codex to use Google, Google Scholar, publisher pages, DBLP, arXiv, and the user's Chrome-accessible permissions to fetch the best available PDFs and create or update references.bib.

Chrome-dependent academic literature scouting and idea planning. Use when the user gives a research idea, topic, question, or draft direction and wants Codex to browse Google, Google Scholar, and academic sources through the Codex Chrome plugin, identify relevant papers, explain what can be borrowed from them, and write a planNN.md before collecting PDFs or BibTeX.

Orchestrate a full theory-first idea discovery pipeline. Use when the user wants the analysis counterpart of idea-discovery: literature context, proof-oriented idea generation, novelty checking, DeepSeek critique, and an analysis plan instead of an experiment-first workflow.

Generate and rank theory-first or proof-oriented research ideas. Use when the user wants non-experimental research ideas, theoretical methods, proof programs, theorem candidates, impossibility results, convergence/sample-complexity analyses, or "analysis" variants of idea creation.

Call a DeepSeek-backed OpenCode agent as a separate critique, writing, or revision agent from Codex. Use when Codex needs to delegate adversarial research critique, novelty skepticism, method review, manuscript prose, LaTeX section drafting, academic text revision, or paper-writing feedback loops to DeepSeek.

Protocol-level two-agent paper writing workflow. Use when the user wants Codex to plan and review from global context while DeepSeek writes or revises the manuscript through the global deepseek-agent skill, with muxing-style-review used for explicit prose style checks.

Turn a theory-first research idea into a proof-oriented research plan. Use after idea-creator-analysis, or when the user asks for theorem targets, assumptions, proof obligations, impossibility routes, analysis validation, or a non-experimental plan.

- **知識領域**：Decentralized Federated Learning / Distributed Machine Learning - **資料來源數量**：20 份文件 - **最後更新時間**：2026-04-21 - **適用 Agent 類型**：研究助手 / 技術顧問 / 領域問答機器人

Activates for ANY project involving research, design, development, or creation across all domains and all AI platforms. Routes to the appropriate domain workflow (software, physical-creative, hybrid, media, business, events, or scientific) and manages the full lifecycle from discovery through deployment and iteration. Use this skill when starting any new project, when unclear which workflow to follow, or when a project spans multiple domains. Compatible with: Manus, Claude, Claude Code, OpenA...