Research & Search

metagalaxy-crystal Bundle

沁言学术文献引用 - 先通过沁言学术OpenAPI检索文献，然后按照GB/T 7714、IEEE、APA、MLA、Chicago、Harvard等标准格式输出引用参考文献。严格遵循学术规范，未获取的信息保留省略号。触发词：文献引用、参考文献、引用格式、citation、reference format、生成引用、引用管理、参考文献格式

metagalaxy-crystal Bundle

沁言学术文献检索 - 支持从 Google Scholar、万方(Wanfang)、PubMed、ArXiv 四大学术数据库检索文献。智能选择检索策略：中文优先万方、英文优先Google Scholar、医学类优先PubMed、理工计算机类优先ArXiv。使用沁言学术OpenAPI。触发词：文献检索、论文搜索、搜索论文、查找文献、paper search、find papers、search literature

metagalaxy-crystal Bundle

沁言学术研究空白发现 - 通过沁言学术OpenAPI系统检索大量文献，结合Python分析，自动识别特定领域中的研究空白和薄弱环节，为科研选题和基金申请提供创新方向建议。触发词：研究空白、research gap、研究不足、创新点发现、gap analysis、研究机会、find gap、领域空白

metagalaxy-crystal Bundle

沁言学术研究趋势分析 - 通过沁言学术OpenAPI大量检索文献，结合Python数据分析，生成某领域的研究热点演变、发文量趋势、核心作者/机构分布等量化分析报告。触发词：研究趋势、趋势分析、热点分析、research trend、热点追踪、领域分析、学术热点、bibliometric

metagalaxy-crystal Bundle

沁言学术文献综述生成 - 基于沁言学术OpenAPI大量检索文献，自动生成结构化的文献综述报告，包括研究背景、研究现状分类梳理、研究趋势、研究不足与展望。支持中英文输出，可生成完整综述初稿。触发词：文献综述、综述生成、literature review、写综述、生成综述、研究综述、综述报告

samhvw8 Bundle

Deep internet gathering — the search-fetch loop, query templates, multi-source/GitHub patterns, and retrieval tools. ONE job: collect raw sources and data from the internet on an assigned topic/language. Run standalone to deep-gather a topic, or as the GATHER-DATA step of lead-researcher's research loop. Does NOT reason, steer, or synthesize — that is lead-researcher's brain. Triggers: 'deep gather', 'gather sources/data on X', 'collect everything about Y'.

jahidulislamseo Bundle

Use when the user asks to "optimize entity presence"; builds Knowledge Graph, Wikidata, sameAs, and AI recognition signals for a canonical entity identity. Not for page-level AI-citation readiness — use geo-content-optimizer. 实体优化/知识图谱

6uclz1 Bundle

Research X/Twitter through the user's logged-in Chrome session. Use when Codex needs keyword or hashtag search, Top/Latest result scanning, direct tweet/thread URL extraction, or linked article explanation from X/Twitter without posting or changing account state.

6uclz1 Bundle

Create Japanese equity-centered stock market news digests from current news, timely disclosures, company IR, market data, US market spillover context, and crowd trends. Use when Codex should summarize Japan stock market news, individual Japanese stock catalysts, earnings or TDnet disclosures, market themes, Nikkei/TOPIX context, S&P 500/Nasdaq/Dow or major US equity spillovers, or X/Twitter-driven crowd reaction while avoiding investment recommendations.

abed-zahed Bundle

Semantic web search via Exa and JS-heavy page scraping via Firecrawl. Use proactively whenever research, current information, or URL content is needed.

abed-zahed Bundle

Advisory board skill. Two modes — recommend (research and suggest 2 expert advisors for any context) or consult (get each advisor's honest take on a decision in their own voice). Works for engineering, business, career, and personal decisions.

aliakseit Bundle

Run a PRISMA 2020 systematic literature review for an HTA/HEOR dossier: extract a PICO from the dossier and its documents, generate tiered PubMed and ClinicalTrials.gov search queries, execute the literature search, screen abstracts against PICO criteria (include/exclude/maybe with reasons), build the PRISMA 2020 flow diagram, and write a cited narrative synthesis chapter. Use for: systematic review, literature review, literature search, PRISMA, PICO, evidence synthesis, abstract screening, PubMed search, ClinicalTrials.gov search, study selection.

catchintent Skill

Deep research on a single LinkedIn person-lead — public web sources first, paid enrichment only if needed. Builds a sharp 60-second profile and the angle to lead with. Use when the user says "research X", "what do I need to know about this lead", or before acting on a high-stakes lead.

ino-xious Skill

Work through one IDX symbol properly — trend, patterns, timeframe alignment, fundamentals and broker flow — and present a lean with its evidence. Use when the user asks what you think of a stock, or to look at, research or analyse one.

iggmasterdev Skill

On request, states the established best-practice principle behind any RCA step (5 Whys, blameless framing, contributing factors, prevention design, the feedback loop), and always separates the PRINCIPLE (why the step is sound) from the APPLICATION (how it maps to your team's context). Use when a facilitator or team asks "why do we do this step", "what's the reasoning", "is this best practice", or wants the rationale behind a recommendation. Grounds only in principles it can stand behind — it never invents a source or a citation. Called by rca-session-facilitator; usable standalone.

hsnuhow Bundle

Pull real Taiwan economic and market data for business-case research — the NDC business-cycle light (景氣對策信號/景氣燈號) and its driving components, leading/coincident indicators, and household income, spending and consumption mix by county and income quintile. Use this to answer "how is Taiwan's economy doing right now", "is the cycle turning", "how big is category X in Taiwan" (at the household survey's 10-category grain — no finer), "what do households in 新竹 spend", "size this market bottom-up", or whenever a Taiwan market-entry, competitor, investment or trend question needs numbers behind it rather than assertions. Coverage is strongest for consumer, manufacturing and export questions; pure services industries (media, education) are invisible to the fast monthly series. Also use it when someone asks where Taiwanese economic data comes from or whether a source is usable — this skill knows which endpoints are alive, which are traps, and why.

hsnuhow Skill

Pick the right strategy framework for a Taiwan business question — and know when a framework is the wrong move. Routes a question ("should we enter this market", "how big is this", "why are we losing share", "is now the time") to the one framework that answers it, binds each framework to the tw-data command that feeds it with real numbers, and says which frameworks are undeliverable in Taiwan because the data does not exist. Use this before analysing a market-entry, sizing, competitor, investment or timing question, whenever someone proposes running a SWOT/Porter/BCG, or when an analysis has collected data but has no shape yet.

tractorjuice Bundle

This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic files', 'memory best practices', or wants to establish a persistent knowledge base across Claude Code sessions. Triggers on: memory setup, MEMORY.md, topic files, cross-session knowledge, persistent notes, memory maintenance, memory pruning.

hyperlink-academy Skill

Draft design documents and specs with research-informed questioning

poco-ai Bundle

Prepare and optionally update Agentero GitHub Release notes from merged pull requests and uncovered first-parent commits. Use when the user asks to prepare, dry-run, review, or update a release; summarize changes between versions or tags; or fill a Draft GitHub Release after the v* release workflow. Produce mirrored Chinese and English notes (Chinese first) and require explicit approval before changing GitHub state.

poco-ai Bundle

Use the Agentero CLI (bin `agentero`) to create, discover, and inspect a local research vault and catalog—list/get papers, import by id/URL, layout regions, reading marks, download assets, parse PAPER.md, export bib—without BYOA. Prefer --json. Discover unknown flags via `agentero describe`. Use when managing a vault headless, scripting Motif/Agentero, or exploring papers via machine APIs ($agentero-cli / /agentero-cli).

poco-ai Skill

Normalize an existing research directory into an Agentero vault layout. Use when reorganizing files, papers, notes, PDFs, TeX sources, marks, assets, attachments, or legacy Zotero/Obsidian-style folders to match Agentero directory and catalog conventions.

stempeck Bundle

Generate or refresh `/docs/architecture/` — the current-state source of architectural truth for this codebase, grounded in code and git history (NOT in .designs/). Produces an anchor-dense corpus (`invariants.md`, `idioms.md`, `trust-boundaries.md`, `seams.md`, `subsystems/*.md`, `history.md`, `gaps.md`) plus a high-level overview layer (C4 L1/L2 diagrams, sequence flows, Nygard ADRs). Every claim is anchored to a file:line or commit SHA, or labelled literally `"unknown — needs review"`. A bundled `validate.sh` mechanically enforces citation density and phase-completion gates. Used to ground future design reviews so they cannot silently drift away from established idioms.

mattbaconz Bundle

Manually triggers a checkpoint compression of the current session state. Collapses conversation history into a compact state atom (≤50 tokens). Use when user types /signal-ckpt, "checkpoint", "compress context", "summarize session", "save state", or when the context window is getting large. In SIGNAL-3 mode this fires automatically every 5 turns.

the-vibe-company Bundle

Summarize an incident timeline from logs into a concise postmortem draft.

45ck Skill

Create a pricing and packaging hypothesis, research plan, and low-risk validation path tied to customer value and unit economics.

birdsigh Skill

Produce a structured closing summary for work-focused sessions — coding tasks, feature builds, bug fixes, design work, content production, or any session with a defined goal or deliverable. Trigger whenever the user types /wrap-up, or says something like "let's wrap up", "we're done with this task", "summarise what we built", or "what did we get done". Also trigger when a task reaches a natural completion point and the user signals they want to review what was accomplished. Do NOT use for informal chats or exploratory discussions — use /wind-down for those instead.

birdsigh Skill

Produce a structured closing summary for informal or exploratory conversations — discussions, brainstorms, research dives, or any chat that isn't primarily a work task. Trigger whenever the user types /wind-down, or says something like "let's wind down", "wrap this up", "summarise what we discussed", or "close out this conversation". Also trigger at the natural end of a long informal chat when the user signals they're done. Do NOT use for task/work completion — use /wrap-up for that instead.

birdsigh Skill

Score user-research responses on sentiment, pain, and excitement with quote-backed evidence. Use this whenever the user wants to analyse interview answers, survey responses, support tickets, sales-call transcripts, customer feedback, or any qualitative response on the three dimensions of sentiment, pain level, and excitement about a solution. Trigger on phrases like "analyse this response", "score this interview", "how does this customer feel", "rate the pain level", "extract sentiment", or when the user pastes a transcript and asks for structured emotional/attitudinal analysis. Use even if only one of the three dimensions is mentioned by name.

stevenflanagan1 Bundle

Writes on-brand social media captions for SMBs. Takes post concepts or a content calendar and produces ready-to-post captions with hooks, body copy, CTAs, and hashtags. Reads brand-style.md for voice and tone. Supports Instagram, LinkedIn, Facebook, TikTok, and X. Batch and single-post modes. Optional trend and competitor research via Firecrawl and SerpApi.

team-attention Bundle

This skill should be used when the user asks about "MVP", "유저 인터뷰", "talk to users", "사용자 대화", "제품 개발", "프로토타입", "MVP 만들기", "/yc-4", "product development", "user research", "사용자 인터뷰", or any questions about user research, building an MVP, or product-market fit iteration. YC Startup School Module 4: Planning an MVP — Gustaf Alströmer on talking to users, Michael Seibel on building MVP, and Diana Hu on technical founder principles.

lion-1209 Skill

Answer questions using the Obsidian wiki vault. Reads hot cache first, then index, then relevant pages. Synthesizes answers with citations. Files good answers back as wiki pages. Supports quick, standard, and deep modes. Triggers on: what do you know about, query:, what is, explain, summarize, find in wiki, search the wiki, based on the wiki, wiki query quick, wiki query deep.

misaka16384 Skill

Entry point for a MAGI research project: run magi next, do what it says, and call the skill it names.

misaka16384 Skill

Take a folder that already holds research — papers, notes, code, half-written drafts — into MAGI, without breaking what is already there.

misaka16384 Skill

Investigate a question across the project from several angles at once, verify what comes back, and land it as propositions plus at most one synthesis.

misaka16384 Skill

Triage a literature-radar digest: judge each candidate against what this project is actually doing, and queue only what earns it.