Research AI Skills

Systematic backlink building for indie founders. Covers 5 channel types ranked by GEO + SEO ROI: Wikipedia (entities), authoritative media (PR), industry reviews (G2/Capterra/Product Hunt),…

法律意见书、法律备忘与合规结论出具前的引用核验工作流，用于把草稿中的法规引用整理成一份可签发前复核的核验底稿，覆盖一致性核验与关键条文回源。Use when：律师或法务在正式出具意见、备忘或合规结论前，需要检查法条引用是否准确、完整、可追溯。NOT for：仅做法规主题检索、案例研究，或不需要交付级引用核验的轻量场景。要求所有核验结论必须来自当次 MCP 返回；未通过核验的引用不得写为确定依据。

Turn articles, notes, transcripts, or research into a consistent series of clean hand-drawn infographics with concise text and visual verification.

Build cited, evidence-labeled Splunk Enterprise upgrade plans and Splunk Cloud support-assisted version-change readiness plans without performing the upgrade. Use for upgrade scope intake,…

Look up WoW Unit and Player APIs — UnitId tokens, GUIDs, health/power/stats, auras, roles, casting, threat, inspection, paper doll, death/resurrection, and player-specific functions. Use when querying…

Simulated-audience Q&A rehearsal for conference talks, thesis defenses, job talks, and poster sessions. Use when a researcher says "rehearse Q&A", "practice questions", "mock Q&A", "grill me on my…

Interactive workshop for designing new skills or agents. Walks through best practices, helps decide between skill vs agent, and outputs a complete SKILL.md or agent .md file.

Mobile-first design: touch targets, gesture systems, thumb zones, responsive layout, mobile forms and navigation, iOS 26 Liquid Glass, Material 3 Expressive, and wearable/IoT patterns. Use when…

Use for authorized wireless security assessment including Wi-Fi capture, WPA handshake analysis, rogue AP detection research, and lab-only deauth testing.

Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV…

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira",…

Synthesize repeated themes from selected research conversations or notes.

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic…

Academic manuscript writing with IMRAD structure, citation formatting, and reporting guidelines. Use when drafting or revising research papers.

Convert normalized multi-search-engine results to minimal BibTeX, preserving real DOI, author, publication year, arXiv ID, source URL, and provenance metadata when available. Unknown years are omitted…

Recommend practical study strategies matched to the material, learning goal, assessment, time, and learner constraints. Use for revision planning, homework routines, independent study, replacing…

Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use…

Semantic Similarity Index for disease research literature using PubMedBERT embeddings

Exhaustively extract UX patterns from a reference web app. Walks every screen, captures screenshots of every state, records interaction patterns, copy verbatim, keyboard shortcuts, responsive…

Guides analysis of eye-tracking reading measures including first fixation, gaze duration, regression path, and total reading time

Search and download arXiv papers (no API key needed)

Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard).

Find which ChatGPT search queries mention a given brand. Tests long-tail queries against ChatGPT's web-search-enabled model and reports which ones surface the brand. Use when the user asks to "find…

Market Oracle for prediction market intelligence - Polymarket and Kalshi research, probability assessments, market sentiment analysis, and arbitrage opportunity identification. Use when users want to…

Optional vendor skill for Parallel CLI — agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring. Prefer JSON output and non-interactive flows.

Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.

Handles difficult colleagues and resolves conflicts using frameworks from Anneka Gupta and workplace dynamics research. Use when dealing with blocking colleagues, toxic dynamics, or maintaining…

Use when looking for a meta-analysis topic before any protocol exists. Starts from a professor's publication profile or from a clinical question, finds gaps, assesses feasibility and returns a ranked…

Readability and rendering audit for figures and tables in academic manuscripts. Computes effective font/marker sizes at display scale from generation scripts, checks label collisions, color/hatch…

Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're…

Papers With Code CLI (`pwc`) for searching and reading AI/ML papers, discovering recent and trending research, finding related work and paper lineage, browsing tasks, methods, conferences,…

Create or review comparison article writer deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for comparison article writer work.

Wibi Style 官方视觉风格：把一张照片转换成纸上人物志·CD版。适合人物日常照片：把动作与穿搭画成橙底日文扁平插画封面，装入透明 CD 盒，生成方形静态产品展示图。适用于用户要求纸上人物志·CD版，或明确调用 $paper-portrait-cd 时。

Build AI agents that automate scientific research — hypothesis generation, experiment design, data analysis, and paper writing using agentic tree search. Use when: automating research workflows,…

围绕既有医学研究结果的具体不确定性，规划、执行或记录替代模型、缺失数据、偏倚假设、分析人群和研究纳入 变化，产出可追溯的稳健性比较与局限性说明。当用户问“结果稳不稳”“换假设会不会变”或明确要求敏感性分析 时使用；原始主分析交给 dyz-med-analyze，临床重要性解释交给 dyz-med-interpret。 Use for approved sensitivity analyses…

Use when interpreting research findings, evaluating scientific evidence, analyzing mechanisms, comparing competing hypotheses, designing experiments, or constructing scientific arguments.

Grounds version-sensitive engineering decisions in authoritative current sources by detecting the installed stack, retrieving official documentation or source, reconciling conflicts, and recording…

DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence…

Build n8n workflows for GTM automation — triggers, webhook-to-enrichment-to-CRM pipelines, error handling, Clay export replacement for complex cases. Use when building n8n workflows or automating GTM…

监管回复函与说明材料的依据核查工作流，用于把回复函、问询答复、说明材料中的法规引用整理成可复核、可回源、可流转的核查底稿。Use when：律师、法务、合规、董办或监管回复支持团队需要在对外或审批前检查引用是否准确、完整、可追溯。NOT for：纯法规主题研究、完整专项法律意见书撰写、以及不需要交付级引用把关的轻量场景。要求先锁定核查范围，再逐条回源与核验；未核验的引用不得写为确定依据。

Drafts or audits a scientific paper's introduction: real-world motivation, evidence audit, theory-to-if-then funnel with a named estimand, bridges across experiments, and calibrated contributions. Use…

Turn an investment podcast episode into a skimmable, citation-backed HTML investment brief for allocators, fund-of-funds analysts, family office CIOs, OCIO analysts, and other investment…

Neural web search, content extraction, company and people research, code search, and deep research via the Exa MCP server. Use when you need to: (1) search the web with semantic understanding — not…

Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your…

Renders the paper-workspace (outputs + lifecycle progress) into a single self-contained HTML dashboard the author can open in a browser, and refreshes it on request. Use when a researcher says "show…

个股核心投资逻辑深度研究，生成接近券商研究员风格的高质量个股分析报告，涵盖投资逻辑、风险提示和操作建议。Invoke when user asks for stock analysis, investment logic, or wants in-depth research on a specific company.

Write one publication-style research-paper section as a bounded, citation-grounded LaTeX fragment from a writing plan, outline, citation plan, and optional figure/table context.

TikTok hashtag video scraper: input a hashtag name → output paginated video list with full metadata (author profile, engagement stats, music, video meta, hashtag list). Use when user mentions TikTok…

Complete SEO content creation system for AI agents. Research keywords, analyze competitors, write optimized articles, and track rankings — all through natural conversation. No APIs required.

The evidence, judgement, intake and market-data rules every research deliverable follows. Read before the first deliverable of a research task; when a number has no source; when two sources disagree;…

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.