Research AI Skills

Cross-model adversarial critique: use a different AI model to review anything your primary AI produced — posts, specs, code, research, decisions. Same-model self-review falls into local minima; a…

Opens a talk, module, paper, chapter, or referee report as a multi-session deliverable. Interviews the author, then scaffolds deliverable.yml, HANDOFF.md, the planning/ wiki, inbox/, and checks/. Use…

Draft and edit concise, reviewer-specific author responses in clear academic English. Use for paper rebuttals, response letters, revise-and-resubmit memos, reviewer-response matrices, evidence triage,…

Use when writing recommendation letters, reference letters, or award nominations for students, postdocs, or colleagues. Invoke when user mentions recommendation letter, reference, nomination, letter…

Develop evidence-backed points of view, white papers, case studies, industry briefs, and research reports for a consulting audience. Use to turn research or permitted engagement experience into a…

Competitive intelligence teardown — 5-layer analysis (signals, product, marketing, positioning, strategy) plus sales battlecard. Use when "competitor analysis", "competitive teardown", "who are our…

Goal-driven conductor for the whole idea-to-published-paper lifecycle. Takes a research idea plus experiments and a target ("submit to NeurIPS 2026", or "help me pick a venue") and runs a…

Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a…

Help users understand and respond to competition. Use when someone is positioning against competitors, evaluating market threats, running competitive war games, or deciding how much to focus on…

Manage HOT/WARM/COLD memory transitions, Wiki Phase 1/2/3 entity sedimentation, GDPR Art 17 purge. Triggered by hooks/stop_finalize.py + /forget-project command.

Use when onboarding an alternative data vendor, triaging legal rights, material non-public information exposure, scraping and computer-misuse risk, terms of service and personal data handling before…

Move skills, memories, context files, and agent rules between Memoire and peer agent ecosystems.

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces…

Create or improve a Chinese academic PPTX from a scientific paper or research reading notes, with source figures and speaker notes. Use for 论文做PPT、文献汇报、组会PPT and paper-based conference or defense…

Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page…

AI Berkshire skill: 管理层纵深研究：买股票就是买人. Source: skills/management-deep-dive.md.

Technical SEO audit with GEO-specific checks — crawlability, indexability, security, performance, SSR, and AI crawler access

Create a new academic paper or LaTeX manuscript through a citation-aware drafting and validation DAG; explicit full/PDF requests include artifact compilation. Do not use for repairing an existing…

Explore methodological approaches through structured analysis before planning implementation

对照高可信一手来源调研问题，并把发现保存为仓库中的 Markdown 文件。适用于用户想调研主题、收集文档或 API 事实，或把阅读工作委托给后台代理时。

Use when about to claim work is complete, a chapter is finished, or references are verified - requires running verification commands and confirming output before making any success claims

Semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)

Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data…

Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or…

Gate a pitch against one journalist at a time. Runs the pair through proven media-relations checks (last-10-bylines audit, 90-day topic sweep, beat-vs-angle-vs-one-off, the 5 forms of journalism,…

Maps every competitor and the gap they leave. Finds the direct competitors, indirect ones and the substitutes a buyer would use instead, from public sources only, and records what each sells, at what…

Independent web search from Brave's own index. Trigger phrases: brave, brave search, web search.

Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis

Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a…

Given an article DOI or PubMed ID, discover and download the genomics data files deposited by the authors (VCF, FASTA, H5AD, CSV, JSON, BAM, etc.) from public repositories such as GEO, ENA, Zenodo,…

Interactive skill verification — assess accuracy of parameters, citations, and methodology through structured expert review

Retrieve, verify, and synthesize scientific literature. Use for seminal-paper lookups, evidence summaries, method comparisons, and gap analyses. Every citation must come from a live lookup, never from…

Capture frames or clips from RTSP/ONVIF cameras.

LinkedIn-native long-form article and newsletter writing workflow for LinkedIn and Google-to-LinkedIn topic discovery, business-depth research, professional thought leadership, evidence-led drafting,…

资深产品经理助手，提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级，以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc：先读仓库证据，每轮只问一个决策，给推荐答案与理由，记录决策和未决项，支持 resume，产出结构化…

Audit, plan, scaffold, and safely migrate research project structures across greenfield, existing Git/non-Git repositories, and monorepo subroots. Use for project folders, repository cleanup, source…

Build and confirm the complete paper, review, constraint, concern, and reviewer-card baseline before rebuttal generation.

Use when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or…

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

Analyze an ordered temporal trajectory, including persistence/narrowing/widening tests, regime changes, inflection points, and optional extrapolation with uncertainty. Entity type, window, and…

Use when user asks about 中观, 空性, 缘起性空, 八不中道, 二谛, 世俗谛, 第一义谛, 戏论, 毕竟空, 不可得, 如幻, 离四句, 破自性, 难行道易行道, 龙树, or wants teaching in 龙树菩萨 Nāgārjuna's voice. Triggers include phrases like…

Turn a chosen segment + Core Jobs into a build-ready PRD (full functionality + edge cases) using Ivan Zamesin's AJTBD / Next Move Theory methodology. Consumes upstream work — segments from…

Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured…

Check a mathematical-modeling paper's in-text citations, bibliography, appendix length and content, code, supporting files, reproducibility, consistency, and anonymity. Use when the user provides a…

盒子原创行业研究 Skill 组合中的趋势分析专项。判断行业、技术、需求或商业化变化所处阶段、驱动机制、核心变量、时间关系、经营后果与证伪条件。用于“分析行业趋势或未来走向”“判断技术扩散阶段”“研究供需、需求演变或景气变化”等问题。 由 `hehe-industry-researcher`…

Web data extraction and discovery using the Bright Data Python SDK. Use when user asks to "scrape", "get data from", "extract", "search for", or "find" information from websites. Also use when user…

Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract,…

Claim-level verification of any report or data set — extract every figure and factual claim, check each against a primary source (SEC filing, company IR, FRED, exchange data, or the user's own…

Generate beautiful, high-resolution mindmaps from Markdown unordered lists. Outputs interactive HTML, HD PNG, and PDF with colorful branch themes.

View and manage agent loop reflections and episodic memory

Look it up before answering or building — this project's documents of record first, then external prior art. Use when the user says research, look it up, sleuth GitHub, "what do other people do", "is…