Research AI Skills

Use when a Research Architect candidate research spine and approved exemplar adaptation need to become a feasible, field-appropriate study design, analysis plan, validation strategy, and user action…

Use this skill any time the user wants to create, draft, or generate a written document or report. This includes: competitive analysis, market research reports, technical design docs, PRDs, project…

Runs the GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. A cheap train-minibatch pre-gate decides whether a proposal is worth an expensive val evaluation, and…

[Activation] Use when the user provides paper markdown file(s) and requests experiment data extraction (methods, datasets, metrics, results). [Scope] For each paper md: preprocess -> GLM sentence…

Call Exa Search directly with cURL or raw HTTP. Use when an agent needs Exa semantic web retrieval from POST /search without an SDK, including ranked results, domain or category filters,…

Use when preparing, drafting, revising, polishing, auditing, or packaging a journal manuscript, abstract, statistical or evaluation report, cover letter, editor-facing submission pack, data…

Plan, build, render, and verify academic presentation decks with citations, accessible visuals, clear argument flow, speaker-ready pacing, and visual QA.

Research the law on a question — find, retrieve, read, and validate the controlling cases, statutes, and regulations; map the citation network and the statutory landscape; and verify everything is…

Lists what changed at an account since a date: funding, exec moves, launches, pricing changes and hiring pushes, each dated and cited, using the Nimble `account-signals` agent template on live web…

Scores a draft against the measurable patterns of recent award-winning and top-cited papers at a target venue, producing a shareable venue-fit scorecard. Use when a researcher asks "score my paper",…

数学建模赛题分析与建模设计合并阶段。用于读取题面和附件，完成子问题拆解、数据理解、假设预检、变量定义、模型公式、目标函数、约束条件、求解策略和可交给代码实现的建模报告。

从论文、代码和评测资源中筛选 AutoResearch 优化面，排除纯调参、不可隔离、不可复算或收益不足的方向，并产出可验证题目合同。用于选优化面和更换失败方向。

Use when creating research figures, paper posters, academic presentation visuals, or conceptual diagrams as an editable draw.io/diagrams.net draft plus PNG export that passes strict visual QA.…

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine…

Plan and scaffold an academic introduction section from source papers, context, or rough notes. Use this skill whenever Ilya wants to structure an intro, outline a paper's opening, map the literature…

Use when verifying AI-generated content, validating claims, checking source credibility, implementing evidence-based reasoning, and preventing AI hallucinations. Includes source verification,…

Run Phase 1 Research only — keyword research, SERP analysis, competitor analysis, content gap analysis, surface targeting. Use when user wants research-only output without writing an article.…

Auto-generated skill for brave-search tools via OneKey Gateway.

Generates falsifiable, testable research hypotheses from notes, documents, and research content. Use when the user asks to brainstorm hypotheses, generate research questions, identify testable…

Build a concrete plan for a founder to get warm introductions to the right VCs and angels instead of cold-emailing them. Analyzes how target funds think (their theses and the founder patterns they…

Validate and scientifically interpret completed research runs, including negative, null, boundary, confounded, failed, and inconclusive outcomes. Use after execution to assess evidence and claim…

Picks the questions to ask interviewers (Galactic reverse-interview guide), then records answers and red flags. Use when the user asks what to ask at an interview or debriefs one.

Use when an OpenClaw workspace task involves UI design, interface craft, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, design audits, component specs, or code…

Former name of the image-deep-research skill, kept so /ultimate-frontend-skills:visual-research still works. Image deep research - reference images, website contact sheets, moodboards. Prefer…

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser…

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews…

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan,…

Set up and check Hindsight long-term memory for this Bot. Use the first time a Bot uses Hindsight, when the user asks to connect or check memory, or whenever a Hindsight tool call fails.

Search literature across sources, verify or manage citations, and build MeSH strategies or citation-impact audits. Use for 文献检索、引文核对、参考文献管理、严格他引 and evidence-backed citer profiles; not for translating…

Improve factual reliability while creating or reviewing a course or supplied content. Use when the user asks to fact-check, verify accuracy, reduce hallucinations, make a reliable course, or mentions…

Ilya Sutskever的思维框架与表达方式。基于12段一手对话、9篇学术论文、10小时宣誓证词、 27篇推荐阅读清单和14个权威二手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用Ilya的视角分析AI技术方向、安全策略、研究品味。 当用户提到「用Ilya的视角」「Ilya会怎么看」「Ilya模式」「ilya perspective」…

Autonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user…

Bing Webmaster Tools + IndexNow extension. Microsoft Copilot citations are fed by the Bing index; this skill makes Bing visibility, link data, and IndexNow URL submission first-class.

AI Berkshire skill: 财报精读团队：四大师并行解读 + 公众号发布. Source: skills/earnings-team.md.

Monthly delta tracking and progress reporting for GEO clients. Compares two GEO audits (baseline vs. current), calculates score improvements across all categories, tracks action item completion, and…

Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file…

杀猪盘检测器。当用户提到"朋友推荐"、"群里说"、"老师带"、"内幕消息"、"小红书 / 抖音看到推荐"等关键词，或显式要求"看看是不是杀猪盘 / 检测一下风险 / 这只票安全吗"时使用。扫描 8 个信号给出风险评级 🟢🟡🟠🔴。

Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards

Research computing toolkit for optoelectronic information science and engineering, MATLAB/Octave, Python scientific analysis, signal processing, image processing, statistics, simulation, optimization,…

Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion analysis, or…

Assess research ideas for value, novelty, insight, and mechanism. Use for 思路审核, 靠谱吗, 值得做吗, 创新够不够, idea review, scoring, and ranking; no numeric-score request is needed. Default to concept-only review…

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

Default, free, and fastest way to search the web — faster and more token-efficient than Claude's built-in web search, returning compact structured results instead of raw pages. Supports flexible…

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account…

Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.

Author a custom writing voice for Lathe tutorials, in session, then persist it via the CLI. Use when the user invokes /lathe-voice (optionally with a name like "/lathe-voice terse") to craft a new…

生成每日 arXiv 与 Semantic Scholar 论文推荐并写入 Obsidian Vault。Use when the user asks to start the day, create today's paper brief, or generate recommendations for a specified date.

Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on…

Narrative discipline for research reports — article-type templates (empirical / feasibility / comparison / policy-zh) and the feedback revision protocol that keeps outline, prose, and figures coherent…

Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.