Research & Search

mrzhangguoguo Skill

Bounded best-practice research using official/upstream evidence first; produces a cited, reusable recommendation and a handoff to planning/execution

qa-aman Skill

Write a concise feature spec (one-pager) for engineering handoff. Use when user says "write a spec", "one-pager", "feature spec", "spec this out", "spec for [feature name]", or wants a structured feature brief grounded in product context and user research.

qa-aman Bundle

Fetch transcripts from YouTube videos. Use when user says "get transcript", "fetch transcript", "YouTube transcript", "pull captions", "what does this video say", or pastes a YouTube URL and wants the text content extracted. Also use when user wants to research or summarize a YouTube video.

tylerprogramming Bundle

Search and read Gmail for research or information retrieval.

tylerprogramming Bundle

Research TikTok trends for the given hashtags.

tylerprogramming Bundle

Research a topic across YouTube, Instagram, X and TikTok with Apify, read the top YouTube videos' transcripts and comments, and return a brief of what is working, where the gaps are, and what to make next. Every number is pulled or computed from real data, never invented. Triggers on - social me, research this topic across platforms, what is working on social, cross-platform research, find the content gaps, topic brief, scout a niche, what should I make about.

tylerprogramming Skill

Generate a weekly short-form content package from yt-search research at $ARGUMENTS.

mearman Skill

Create bibliography citations from web page URLs with automatic Wayback Machine archival and metadata extraction. Use when the user asks to cite a website, create a citation for a URL, archive and cite a web page, or generate a bibliography entry from a web address.

dartsim Skill

DART References: manage the experimental simulation research catalog (papers, textbooks, engines) with status, priority, and verdict

tanstack Skill

Pluggable, category-toggleable debug logging for TanStack AI activities. Toggle with `debug: true | false | DebugConfig` on chat(), summarize(), generateImage(), generateSpeech(), generateTranscription(), generateVideo(). Categories: request, provider, output, middleware, tools, agentLoop, config, errors. Pipe into pino/winston/etc via `debug: { logger }`. Errors log by default even when `debug` is omitted; silence with `debug: false`.

intertwine Bundle

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

intertwine Bundle

Free web search via DuckDuckGo when Firecrawl is unavailable. No API key needed. Use ddgs CLI or Python library to find URLs, then web_extract for content.

huzengyun3268 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.

huzengyun3268 Bundle

Analyze stocks and companies using financial market data. Get company profiles, technical insights, price charts, insider holdings, and SEC filings for comprehensive stock research.

huzengyun3268 Bundle

description: A 鑲＄洏鍓嶇畝鎶ユ妧鑳斤紝浜ゆ槗鏃ュ紑鐩樺墠鍒嗘瀽甯傚満鏂伴椈銆佸畯瑙備簨浠讹紝鐢熸垚鎶曡祫鍙傝€冩姤鍛娿€傛暣鍚?multi-search-engine 鍜?summarize锛屾棤闇€ API Key銆?---

microck Skill

Structure complex questions into testable hypotheses. Use when validating product ideas, debugging problems, planning experiments, or breaking down ambiguous challenges into actionable research.

microck Skill

Understand customer motivations through job theory. Use when defining product strategy, conducting user research, identifying competitors, writing user stories, or reframing features around customer progress.

quick-brown-foxxx Skill

ALWAYS LOAD THIS SKILL WHEN RESEARCHING AN UPSTREAM PACKAGE OR HOSTED REPOSITORY SUCH AS GITHUB OR GITLAB FOR SOURCE CODE, ISSUES, REFS, RELEASES, OR COMMIT HISTORY. Do not assume web-only research is enough before reading this skill.

quick-brown-foxxx Skill

Use when deciding whether multiple agents can work in parallel on independent tasks, failures, research threads, verification checks, or implementation slices. Guides independence checks, how to properly dispatch parallel work, write focused prompts, integrate agents, and when not to parallelize.

buildingwithai Bundle

Synthesize raw voice-of-customer data — calls, interviews, surveys, reviews, CRM notes, support tickets, win-loss — into buyer language, themes, contradictions, and evidence chains. Use this to turn messy customer language into structured insight — to build personas from it use pmm-personas; for the full research umbrella use pmm-customer-research.

buildingwithai Bundle

PMM Research Brief — the research front door

buildingwithai Bundle

PMM Customer Research

fortunto2 Skill

Use when "swarm research", "parallel research", "investigate fast", "3 agents", "team research", or want faster multi-angle alternative to /research. Do NOT use for solo research (/research) or idea scoring (/validate).

blakehastings Bundle

Create, lint, and search notes in Blake's Obsidian vault (second brain, knowledge base). Use when the user wants to create an atomic note, daily note, index note, project note, feature note, reference note, person note, recipe note, repository note, or any other Obsidian note; lint existing notes against vault standards; search the vault; explore a note's related notes (backlinks/incoming links, outgoing links, neighbors); rename, move, or delete notes (via the official Obsidian CLI, so backlinks stay intact); or propagate template/standards version updates. Operates on the vault at C:\Users\Blake\Documents\Obsidian\main.

blakehastings Bundle

Deeply research subjects using iterative refinement and context space traversal. Use when conducting comprehensive investigations, systematically exploring related concepts across multiple sources (vault, web, codebase), or arriving at well-reasoned answers through multi-step reasoning with feedback loops and self-critique. Supports deep-explore, trace-connections, refine-answer, and map-context operations.

matematicsolutions Skill

Buduje jawny sylogizm prawniczy (subsumcję) dla zagadnienia - rozkłada rozumowanie na przesłankę większą (norma + wykładnia), przesłankę mniejszą (istotne fakty), podciągnięcie faktów pod normę i wniosek, a potem wskazuje słabe ogniwa: ukryte założenia, sporne fakty, wątpliwą wykładnię. Wymusza, by każdy krok był wypowiedziany i sprawdzalny, zamiast skoku od stanu faktycznego do tezy. Pairuje z adversarial-legal-review-pl (atak na sylogizm), citation-grounding-pl (weryfikacja powołanej normy) i struktura-wyroku-pl. Uzywaj gdy: "zbuduj subsumpcję", "sylogizm prawniczy", "podciągnij fakty pod normę", "rozpisz rozumowanie", "gdzie jest luka w argumentacji", "przesłanka większa i mniejsza", "uzasadnij krok po kroku", przy pisaniu opinii / uzasadnienia / pisma procesowego.

matematicsolutions Skill

Rozkłada polskie orzeczenie na role retoryczne i robi streszczenie EKSTRAKTYWNE (cytuje zdania źródłowe, nie parafrazuje) - segmentuje wyrok/postanowienie na komparycję, stan faktyczny, przebieg postępowania, zarzuty/wnioski, podstawę prawną, rozważania sądu, sentencję i tezę (ratio decidendi), wskazuje rozstrzygnięcie i powołane przepisy. Mechaniczna segmentacja + ekstrakcja kluczowych zdań, bez zmyślania. Pairuje z saos-orzecznictwo (znajdź), ekstraktor-cytatow-pl (cytaty) i citation-grounding-pl (weryfikacja). Uzywaj gdy: "streść ten wyrok", "co sąd orzekł i dlaczego", "wyciągnij tezę z orzeczenia", "struktura uzasadnienia", "ratio decidendi", "rozłóż wyrok na części", "podsumuj orzeczenie", przy czytaniu długiego uzasadnienia / analizie linii orzeczniczej / przygotowaniu glosy.

nielsmadan Bundle

Generate ideas with structure when you're stumped — on what to build next, what the real problem is, or how to solve it. Pulls in research for context, diverges wide using matched frameworks, then converges on a prioritized few. Use when the user says "I'm stuck", "I'm stumped", "ideate", "brainstorm ideas", "help me think of", "what could I add", "what should I build", "I don't know what the problem is", "how could I solve", or wants idea generation on any topic (product, technical, business, writing, personal). For auditing an existing product against its users, use review-product instead.

nielsmadan Bundle

Structured evaluation before adopting a library, tool, or hosted service — enumerate candidates wide, then score every one against an identical rubric where maintenance health is a mandatory gate, not an afterthought. Use when the user asks "which library/package should I use", "what should we use for X", "which service/vendor should we pick", "is this package still maintained", "alternatives to X", "should we add this dependency", "should we switch to X", "pick a tool/service for", "evaluate this dependency/tool/service", or is choosing between named options to adopt. Covers code dependencies (npm, pip, pub, cargo, go), CLI/dev tools and dev software, and SaaS/API/hosted services. For learning how to USE something already chosen, or for open-ended technical research, use research-tech instead.

nielsmadan Bundle

Research a non-technical topic online (science, history, news, policy, regional/regulatory, consumer purchases, personal decisions, fact-check). The default for research in non-code repos (e.g. a notes vault). For technical/developer topics — libraries, errors, tooling, and even choosing/evaluating dev tools or products — use `research-tech`.

benjaminshoemaker Skill

Capture links, thoughts, and a thesis for a blog post, then research and structure them into a writing brief. Use when starting a new blog post.

benjaminshoemaker Skill

Exploratory conversation before /product-spec. Asks one question at a time, runs background research for open-source/off-the-shelf alternatives, and writes DISCOVERY_NOTES.md. Use when the user has an idea but hasn't scoped it yet.

orkas-ai Bundle

Research e-commerce merchandise opportunities, category viability, price bands, competitors, profit assumptions, sourcing risks, and evidence gaps across Amazon and Chinese commerce platforms.

orkas-ai Bundle

paper-research

chanw-research Bundle

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 reporting-guideline support.

chanw-research Bundle

Use when checking manuscript citations, bibliography hygiene, DOI or PMID completeness, placeholder references, or BibTeX consistency before submission or revision.