Research AI Skills

Tracks the latest preprints and emerging research topics related to your topic across bioRxiv, medRxiv, and arXiv. Use when a user wants to discover what is being published right now before it reaches…

Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a fresh context (never a conversation fork) so it never sees the draft — then…

Campaign planner: turns a product, offer, goal, budget and date into a plan the marketer can approve and a designer can start from today, with every channel kept or dropped for a reason. Zero paid is…

Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

Research a US employment law topic across federal, state, and city jurisdictions and produce structured research notes with proper source attribution. Use this skill any time the user asks about US…

Script a teacher think-aloud demonstrating expert reasoning processes for a specific task. Use when modelling problem-solving, writing, reading comprehension, or analytical processes.

Set up and run a dollar cost averaging bot from paper test to live.

Convert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections.

Source-cited draft: company formation & entity choice for Angola (tax year 2025) — rates, thresholds and rules with primary-source citations. Unverified; pending local-accountant review.

Use when finding papers or building a reference list. Searches PubMed, Semantic Scholar and bioRxiv/medRxiv, includes only references verified through an API, and generates BibTeX. Auditing an…

Converts research papers into executable skill packages via document conversion, critical analysis, and co-evolutionary refinement. Triggers on: "convert this paper to a skill", "paper-to-skill",…

Deep research on any topic — broad parallel web searches, multi-source validation, confidence tracking, and a cited Markdown report. Use whenever the deliverable is a thorough sourced report rather…

当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成（RAG）、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出（如故事、诗歌），不适用于无需溯源的常识问答，也不适用于注入防御（虽然两者都涉及内容可信度）。

evidence-based-replies — Compare a person's claim to a cited paper or source, isolate what the evidence actually supports, and draft concise replies that correct overreach without sounding evasive.

Knowledge base from NASA NPR 7150.2D — NASA Software Engineering Requirements. Use for NASA's Agency-wide software-engineering requirements: the software classification scheme (Classes A–F), the…

Produce bounded, source-backed research packets for product, ecosystem, and operator decisions.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Hand-drawn editorial illustration set in a cozy cluttered personal-studio scene. Loose scratchy black ink outlines that wobble, textured gouache fills with visible brush marks, warm cream paper…

Turns raw captures (dictated braindumps in a deliverable's inbox/, or recent macwhspr dictation-log entries) into proposed planning-wiki changes, shown as one unified diff. Classifies each statement…

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms,…

Investigate an open question properly — frame it as a decision, work from primary sources, sweep from several angles including the disconfirming one, and stop on a rule rather than on fatigue. Use…

Identify 5-framework content gaps (SEO gap / AI gap / FAQ gap / Format gap / Authority gap) from research.json. Returns prioritized opportunity list for outline-architect.

Turn source material into a restrained Quarto RevealJS talk using the quarto-talks format. Use for papers, manuscripts, documents, figures, code, bibliographies, or existing slide decks when the…

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

Let an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.

PDF content extraction and analysis specialist

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for…

Research competitor paid-ad presence, messaging, creative, formats, landing pages, keyword and auction signals, transparent ad libraries, and strategic gaps across supported platforms. Use for…

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon…

Apply the ScholarEval framework to systematically evaluate scholarly work across quality dimensions (novelty, rigor, significance, and clarity). Use to critique academic papers, research proposals,…

Apply Miller's Law — chunk information into groups of about four to fit working memory. Use when grouping fields, menu items, or steps. For reducing the number of choices offered, use `hicks-law`.

[omh] Hermes adaptation for bounded official/upstream best-practice research. Use when the user says: best-practice-research, best practice, official docs, upstream guidance, what do the docs say,…

Assesses whether study results are trustworthy by auditing design integrity, sample structure, statistical handling, bias control, validation chain, and claim discipline. It identifies where results…

Use when evaluating Jim Simons / Renaissance-style quantitative strategies: many weak signals, statistical validation, signal decay, portfolio construction, execution cost, and model risk.

Build, repair, or package Agentlas agents and teams with Hephaestus.

Help users navigate complex transitions, from scaling new business units to managing crises and driving AI adoption across large organizations.

Step of the research-audience playbook: finds candidate accounts matching the fit definition, confirms gates, applies exclusions and dedupes. Run research-audience instead; not for direct use.

Surface the one AI / ML paper to read today from Hugging Face Papers, with the central claim, why it's worth an hour, where it might be wrong, and a time-budgeted read order. Filters out pure…

Use when a quest needs a polished milestone chart, paper-facing figure, appendix figure, or a mandatory render-inspect-revise pass before treating a figure as final.

Transform, clean, reshape, and preprocess data using pandas and numpy. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

When you want multi-source, multi-step research on a topic — competitor research before a sales call, market research for a new business idea, positioning angles, due diligence on a partnership or…

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

Planner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.

Use when checking your own manuscript before submission from a reviewer's perspective. Returns anticipated Major/Minor comments with fixes, including numerical, citation and leakage checks, with an…

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table…

Implement PageRank algorithm to compute web page importance scores using the random surfer model. Use this skill when the user needs to rank pages by link authority, build a simplified search ranking…

Query ChEMBL via the chembl_webresource_client Python client for curated bioactive molecules and drug-like compound libraries at scale — search compounds by structure or physicochemical properties,…

Answer questions about rates, fees and terms from the current document, with the version cited.

Product discovery workflow — chain market analysis, competitor research, demand validation, and prioritization Use when: Exploring a new product idea, entering a new market, or validating an…

Reads, writes, and manipulates DICOM (Digital Imaging and Communications in Medicine) medical imaging files with the pydicom Python library. Use when reading/writing/modifying DICOM data, extracting…

Detect and process dangling paper titles in PPTX presentations. Reformats text boxes with paper titles (font, size, color), repositions them to bottom center, and creates a reference slide with…