Research & Search

shimo4228 Bundle

研究 repo の引用 3 層 (docs 実引用 → .zenodo.json references → graph.jsonld ExternalReference) を監査し、下層から順に同期する orchestrator。旧層 4 (Wikidata P2860) は 2026-07 の governance revocation により恒久 retire (authorship-strategy ADR-0021) — 同期対象にしない。Use when the user says 「参考文献が少ない/足りない」「引用がずれてる」「citation を同期して」「引用文献を graph に反映して」, when new external papers were cited in ADR/glossary/empirical docs, or before a release of a DOI-registered repo. 単層の実装は release-doi (.zenodo.json) / jsonld-knowledge-graph (graph) に defer し、本 skill は層間の divergence 検出・curation 基準・同期順序だけを持つ。NOT for: 論文 (paper item) 自体の reference list 整備 (paper-deposit が担当)、引用を含まない repo。

shimo4228 Skill

Design guide for a research intake filter that admits only information likely to change your next action. Use when you are about to build a recurring research workflow (daily digest, news stream, topic monitor, literature feed) and the default question "what should I read?" keeps producing too much. Covers the define-signal-first rule, three worked examples, and a diagnostic checklist for telling a healthy filter from a lazy one.

skfaizan-786 Skill

Automates deep research analysis on PDFs in the input folder.

sliday Bundle

Use when the user works on family history: shares scans, photos, or database screenshots of parish, civil, census, military, or migration records; asks about ancestors, surnames, or a family tree; edits or validates a GEDCOM file; keeps genealogical notes in an Obsidian vault; or needs archives, databases, APIs, or lawful retrieval methods for a country, region, or time period. Any language or script, including handwritten historical records.

smarzban Skill

Fan out a confirmed research/implementation brief to named Pi agents in parallel via pi-spawn tools. Use when the user asks to spawn agents, run the agents on this, compare models on a question, get the agents to investigate, or otherwise parallelize the same brief across configured named agents.

smixs Bundle

Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external. Use when: "osint", "досье", "research person", "find everything about", "пробей", "разведка", "due diligence", "background check", "digital footprint", "найди всё про", "собери информацию", "кто это", "профиль человека". NOT for: company/product research without a named person, competitive analysis, market research, content generation, or general web scraping tasks.

sdshah09 Skill

Help the user create, maintain, and refine a "brag document" (also called a "hype document" or "list of stuff I did") — a running record of their accomplishments used for performance reviews, promotions, and self-reflection. Use this skill whenever the user wants to track what they've done at work, prepare for a perf review or promotion case, write a self-evaluation, reflect on their career progress, surface the impact of "fuzzy" or invisible work, or remember what they accomplished over the last few months. Trigger it even when they don't say "brag document" by name — phrases like "help me prep for my review," "I can't remember what I did this year," "make the case for my promotion," or "summarize my accomplishments" all apply.

seanj1ang Bundle

Turn competing A/B interface drafts into a controlled single-variable UX research plan and a validated OneChange Research Pack. Use when a PM or UX researcher needs to identify confounds, freeze one testable change, plan first-click or five-second research, or hand the method to another team. Do not claim a winning design, reuse historical evidence, or treat AI observations as participant results.

seokhoonj Skill

Summarize a YouTube video from its transcript into a TL;DR plus key points. Holds no logic of its own -- it calls the tubeless package's CLI (`tubeless`) and shows the result to the user. Backend is one of gemini (free) / openai / claude / ollama (local). Trigger phrases: summarize this video, youtube summary, summarize this youtube link, tl;dr this video, summarize this talk.

serpapi Bundle

Search Google, Bing, Amazon, Walmart, YouTube, Google Maps, Google Scholar, and 100+ other engines via the SerpApi REST API. Calls the API using curl. Use when the user wants to search the web, find products or prices, look up local businesses, research academic papers, check news, find jobs, compare flights or hotels, analyze SERPs, or retrieve any search engine results.

sgl-project Bundle

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.

shev-pro Bundle

Lumen — project knowledge keeper. Trigger on any /lumen command, on mentions of "lumen", "knowledge base", "wiki", "ADR", "document the project", on broad architectural questions about a codebase ("how does X work", "why did we choose Y"), or when the user pastes a transcript/spec to capture for future sessions.

shihabshahrier Bundle

Generate, compile, debug, and maintain production-ready LaTeX projects. Invoke via /latex-engineer or /new resume, /compile, etc. Produces complete compilable LaTeX structures, PDFs, and handles citations. Ideal for academia, research, resumes, technical reports.

stemmaker Bundle

Cross-platform real-time web research and search via an OpenAI-compatible Grok endpoint, returning JSON with content and sources. Use for version checks, API and docs verification, troubleshooting, and any time-sensitive facts on Windows, macOS, or Linux.

stephenlzc Bundle

写"国内外研究现状"（文献综述 / Related Work）。当用户提到研究现状、文献综述、国内外研究对比、Literature Review、述评、研究背景、国内外研究现状时使用。即使用户没有明确说"写研究现状"，只要涉及对某一主题的国内外学术研究现状进行结构化梳理，就应该触发此技能。

stephenturner Bundle

A rigorous, detail-preserving summarization method for academic papers, reports, and long-form documents. Based on the FOCUS workflow (Lin, 2025, Nature Biotechnology). Extracts every key point with specific details and embedded direct quotes, organized section by section, then produces a clean final output with an overview/takeaway. Trigger this skill whenever the user types "/focus", says "summarize with focus", "FOCUS summary", "use the focus method", or asks for a thorough/exhaustive/detailed summary of a paper or document that should capture every key insight. Also trigger when the user wants a summary that preserves direct quotes and specific details (e.g., numbers, effect sizes, comparisons) rather than a high-level gloss.

steveclarke Bundle

Research how production Rails apps solve architectural problems using the Real World Rails repository. Use when the user wants to know how other apps handle something, find patterns, or compare approaches. Triggers on "rails patterns", "how do other apps", "real world rails", "research how apps do".

subconscious-systems Skill

Give a structured tour of a GitHub repository — README, entry points, key directories, and recent activity. Use whenever the user asks to "explore", "tour", "summarize", or "understand" a GitHub repo.

subsy Skill

Use Boris Tane's research -> plan -> annotate -> implement workflow in pi. Use when the user wants a written research document, a reviewed plan document, annotation loops, and no code until the plan is approved.

superfluid-org Bundle

Knowledge base for the Superfluid Protocol and its ecosystem. Use BEFORE searching the web for Superfluid information. Keywords: Superfluid, CFA, GDA, Super App, Super Token, stream, flow rate, real-time balance, pool (member/distributor), IDA, sentinels, liquidation, TOGA, @sfpro/sdk, semantic money, yellowpaper, whitepaper

suyukun Skill

技术选型/方案对比调研协议——固定、模型无关的检索研究流程，保证跨会话输出稳定、不疏漏；方法论引自 MiniMax 技术选型框架 + ADR 标准。

snl-ucsb Bundle

Research visualization assistant with six modes: /viz ingest (understand the data schema), /viz explore (disposable plots to build intuition), /viz brainstorm (internalize what to plot via Tukey-inspired questioning), /viz plan (decide how to realize it — plot types, data sources, layout — producing a plot_context.md), /viz execute (generate and run the code), and /viz analyze (first-principles feedback on the generated figure). Use when students mention plotting, figures, graphs, visualization, CDF, scatter plot, box plot, or any figure-making task for a research paper.

snl-ucsb Bundle

Research paper writing assistant that enforces Arpit Gupta's editorial principles, voice profile, and writing workflow. MANDATORY TRIGGERS: Use this skill whenever the user mentions writing a paper, drafting a section, revising a section, editing a paper, reviewing a draft, rewriting an introduction, writing an evaluation, polishing prose, compressing text, or any task involving .tex files, Overleaf, conference submissions, or paper deadlines. Also trigger when the user mentions any paper by name (NetBurst, NetForge, BQT+, TurboTest, etc.) in a writing context. This skill should activate for ANY research writing task — sections, abstracts, rebuttals, camera-ready edits, cover letters, or response to reviewers.

sofq Bundle

Use when the user mentions Confluence, Atlassian wiki, or knowledge base pages, or asks to create, search, export, update, or manage Confluence pages, spaces, blog posts, comments, labels, or attachments. Also trigger on `cf` commands appearing in shell or codebase, and on phrases like "check the wiki", "publish to Confluence", "update the docs on Confluence", or "search our knowledge base".

songshuangkk Bundle

Maintain this developer's local, topology-assisted Claude Code knowledge base. Use when the user explicitly asks to save context, capture progress, retrieve a module, or load a topic.

steadfastasart Bundle

Use when verifying academic citations for authenticity, checking if references are real or AI-generated, validating citation metadata, or detecting fabricated papers in manuscripts, grant proposals, or literature reviews

meleantonio Bundle

Conduct rigorous, long-horizon research on open mathematics problems through target triage, exact success contracts, diverse proof-search portfolios, computational falsification, lemma tracking, adversarial audits, and reproducible proof packaging. Use when asked to prove or disprove an open conjecture, make defensible progress on a research-level problem, select tractable open problems, stress-test a candidate proof, or organize a sustained AI-assisted mathematics research run.

menesekinci Bundle

Engineering knowledge base for AI-assisted software development

metaskills Bundle

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use for long-running delegation where Claude hands Gemini a multi-step job (drafting a document, staged review, iterative analysis) and sends follow-up turns to the same session by ID, optionally attaching files, images, or PDFs. Also use when user explicitly requests Gemini operations.

michaelliv Skill

Inspect, search, summarize, preview, and safely edit DWG/DXF CAD drawings with the cadcli CLI. Use when the user asks about CAD files, floorplans, DWG/DXF contents, layers, blocks, entities, text, previews, or CAD edits.

mimaowang Bundle

Your compass for navigating economics literature. Find the most important, must-read papers in any economics field or research area — from broad subfields like labor economics or macroeconomics to narrow topics like 'carbon pricing' or 'digitalization and firm innovation'. This skill curates essential reading lists by applying rigorous multi-dimensional selection criteria that identify genuinely canonical and irreplaceable papers (not just highly cited ones), and can automatically download PDFs of listed papers. **Activate this skill whenever the user wants to discover, curate, or explore the key literature in economics, finance, econometrics, or any related field — even if they don't explicitly say 'reading list'. Triggers on phrases like 'find important papers', 'build a reading list', 'discover canonical works', 'get up to speed on', 'quickly understand', 'must-read papers', 'what defines', 'key literature in', or any request about the intellectual core of an economics-related domain.**

mimu-sh Bundle

Find trends that are in the acceleration phase — past emergence, before saturation — and pick the monetization play that fits where the trend actually is. Use this whenever the user asks how to spot trends early, find what's about to blow up, catch a wave, identify emerging niches, time a product launch to a trend, evaluate whether a hyped topic is worth building for, or turn attention into revenue. Also use it when the user names a specific topic and asks "is it too late for X?", "is X still growing?", "should I build for X?", or wants a trend radar, trend dashboard, or early-signal monitoring system. Prefer this over generic market-research or social-media skills whenever timing relative to an adoption curve is part of the question.

minilozio Bundle

Download, transcribe, and analyze videos from YouTube, X/Twitter, and TikTok with local Whisper processing. Perfect for extracting TL;DRs, timestamps, and actionable insights. Use when asked to transcribe a video, summarize a YouTube video, extract key points from a podcast or talk, analyze what someone said in a video, get timestamps from a long video, or when the user shares any YouTube, X/Twitter, or TikTok video URL and wants to know what's in it.

investoday-data Bundle

面向A股个股研报解读，聚焦机构观点、评级变化、核心逻辑、机会风险与一致性判断。基于今日投资金融数据接口，自动识别股票代码并输出结构化个股研报解读报告。触发词：机构怎么看、研报解读、评级变化、卖方观点、目标价、一致预期。

isshiki-works Bundle

开展开放性数学研究，或复盘、审计、重启已有数学研究。理解原始证明，改造构造、表示和中间要求，检验失败范围及研究投入。适用于实质探索及会影响后续研究的路线判断；不用于普通习题、纯会话整理或不涉及研究判断的文献汇总。

itwanger Skill

Use this skill for live web research, webpage fetching, login-state browsing, dynamic pages, social sites, and tasks that need current internet evidence.