Research & Search

indigokarasu Bundle

Travel planning, itinerary construction, reservation management, lodging search, and flight search. Parallel lodging search across Expedia, Marriott Bonvoy, Marriott AI, Google Hotels, 1Stay, and HotelsByDay (day-use rooms). Flight search via Google Flights. Uses Sift for destination research and optionally GoPlaces for location enrichment. HotelOracle (Google Hotels) used for price trends, area guides, and price comparison research. NOT for generic travel inspiration, visa advice, or points-only optimization.

indigokarasu Bundle

Private provenance-backed social graph. Maintains queryable records of people, relationships, preferences, and shared experiences for recall, gifting, hosting, introductions, and serendipity. Use for storing or retrieving facts about a person, recording a relationship, or discovering connections between people. Not for sending messages (use Dispatch), calendar management (use Sands), OSINT research (use Scout), or web research without a social graph need (use Sift).

bayramannakov Skill

Find and rank outbound leads matching your ICP using LinkedIn and web research. Supports direct ICP, inverse ICP (find leads FOR someone), product-based search, and "find similar" patterns. Returns scored results with personalized outreach angles.

bayramannakov Bundle

Automate NotebookLM notebook creation from YouTube videos. Given a YouTube video URL, extract information about people featured in the video, research them online, create a new NotebookLM notebook with the video and research as sources, and generate an audio overview. Uses screenshot-first automation to reliably target UI elements.

bchaoss Bundle

Transforms raw interview or podcast transcripts into structured Q/A digests, with optional commentary layer. Use this skill whenever the user provides a transcript (interview, podcast, earnings call, press conference) and wants it cleaned, organized, or analyzed. Trigger words include: "organize this transcript", "clean up this interview", "Q/A format", "digest", "summarize this interview", "what did X say about Y". Also trigger when the user uploads a long conversation text and wants to extract key points or prepare it for sharing. Handles any output language. Always use this skill for transcripts longer than ~15 minutes of content.

benedikt-e Bundle

Verify academic references and bibliographies for citation errors and AI hallucinations using live database APIs (OpenAlex, OpenAIRE, K10plus, lobid, DNB, Crossref, Semantic Scholar, ZBW EconBiz, Open Library, arXiv, Library of Congress, GESIS). Trigger whenever a user wants to check, verify, or validate ANY bibliography, reference list, or Literaturverzeichnis — their own or someone else's (a student's thesis, a colleague's paper, an AI-generated draft). Trigger on phrasings like "prüfe mein/dieses/das Literaturverzeichnis", "kannst du dieses Quellenverzeichnis checken", "check this/these references", "verify this bibliography", "sind diese Quellen echt / halluziniert", or whenever they paste or upload a list of references for checking. Also trigger when the user suspects fabricated sources, or asks whether a specific book, paper, or article actually exists. Use for any literature verification task, even a single source.

bgunebakan Bundle

Complete App Store Optimization (ASO) toolkit for mobile app performance on Apple App Store and Google Play Store. Use to research keywords, optimize metadata, analyze competitors, and calculate ASO health scores.

binqi20 Bundle

Search and download academic PDFs from the Management Research Library through a validated SQLite catalog, authoritative quotas, and hash-verified no-clobber installation.

jalaalrd Skill

Converts video tutorials into production-quality SKILL.md files where Claude executes the work, not teaches it. Accepts a YouTube URL, local video file, or pasted transcript. Extracts content, assesses quality and executability, fills gaps with verified research, verifies available tool actions, and outputs a valid execution-mode SKILL.md. Use when the user says 'learn from this video,' 'turn this tutorial into a skill,' 'convert this video,' or provides a YouTube URL or transcript with intent to create reusable instructions.

jarodise Bundle

Use when user wants to analyze China stock reports (A-share or Hong Kong), upload annual/quarterly reports to NotebookLM, or research a Chinese listed company's financials

jaygptpro Bundle

Give your Claude Code employee a real personality. character, tone of voice, humor, and values. Runs a short research-backed interview, then writes a dedicated character file (.claude/character.md) plus a pointer in CLAUDE.md, so the personality loads automatically in every conversation in that folder. Use when someone wants to give their AI a personality, a character, a voice, or a vibe; make their assistant sound a certain way (nice, direct, bossy, funny); name their employee; or turn a blank folder into a character. Triggers on: "/character", "give my AI a personality", "create a character", "give my employee a personality", "make it sound more direct/funny/bossy", "give it a vibe", "make my assistant feel like a real person".

jessedc Bundle

Extract and process transcripts from Apple Voice Memos synced via iCloud. Use when the user wants to access, read, or summarize voice memos.

htlin222 Bundle

End-to-end clinical diagnostic reasoning skill. Takes a patient case (SCENARIO.md), runs multi-persona Bayesian reasoning rounds with textbook evidence and literature search, outputs structured DDx with likelihood ratios. Use when solving clinical cases, generating differential diagnoses, discussing clinical scenarios, or running diagnostic rounds.

huggingface Skill

Scaffold a PhysicsIntern research workspace in the current folder.

hughyau Bundle

Transform dense technical, scientific, cybersecurity, computing, network, or life-science research questions into clear source-domain-neutral fables for non-specialists. Use when the user asks to allegorize, fable-ize, turn complex research into a metaphorical story, explain without jargon, produce both plain and more imaginative fable versions, or reduce listener association with the original field while preserving the reasoning structure.

hughyau Bundle

Use when preparing research progress updates, advisor emails, lab meeting notes, or collaborator syncs from scattered evidence such as git history, notebooks, figures, and notes, especially when the output must adapt to audience, tone, and Chinese/English workflow.

huiyuli-2000 Bundle

Find and insert citation support for academic claims. Identifies statements requiring literature backing, searches scholarly databases (OpenAlex, Crossref, Zotero, Exa, Google Scholar), ranks results by recency (40%), journal tier (30%), and support degree (30%), and inserts citations into the original text. Use when the user asks to find citations, add references, support claims with literature, locate papers for specific statements, or any task involving citation, reference, literature support, 文献支撑, 引用, 找文献, cite, or adding academic backing to text.

huiyuli-2000 Bundle

Reconstruct publication-quality LaTeX pseudocode (algorithm2e) from academic papers, source code repositories, and research projects. Use when the user asks to generate pseudocode, write algorithm LaTeX, convert code to algorithm, reconstruct algorithm from paper, or any task involving scientific algorithm representation for SCI journals or AI/ML conferences (NeurIPS, ICML, ICLR, AAAI, KDD, TPAMI, TKDE, etc.). Triggers include "pseudocode", "algorithm", "algo2e", "algorithm2e", "write algorithm", "generate algorithm", "reconstruct algorithm", "论文算法", "伪代码".

iblinkq Bundle

Standardize how an AI-collaboration project turns work into reusable knowledge. Use when initializing or retrofitting Project Cairn in a project, recording progress after meaningful work, maintaining AGENTS/CLAUDE/cairn docs, auditing project knowledge for drift or missing records, pulling and citing external knowledge, or graduating validated project experience into a reusable knowledge base.

iannwu Bundle

Dispatch a bounded implementation, review, or research assignment from a Codex task to a dedicated ChatGPT Pro conversation in the official combined desktop app, recover the result without resending, and return to the parent Codex task. Use when the user asks Codex to delegate work to ChatGPT Pro; do not use for ordinary local coding.

gryszzz Bundle

Source-grounded Kaspa protocol and Toccata engineering for Rusty Kaspa, KIPs, wallets, Kasware/Kaspium, indexers, WASM/TypeScript, covenants, ZK, vProgs, mining, infrastructure, repository audits, and current network or release status. Use when Codex must research, explain, design, implement, review, or verify Kaspa systems with UTXO-first architecture, DAG-aware correctness, explicit monetary flows, current primary sources, and reproducible validation.

guhcostan Skill

Use when conducting research on any real-world topic — products, services, finance, health, travel, or life decisions. Ensures sources are fetched, cross-referenced, and not fabricated.

haiyichen001 Bundle

Citation Check

hanzoskill Bundle

Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), and Exa (Neural) with confidence scoring.

hartreeworks Bundle

Summarise Granola calls and meeting transcripts.

edlsh Bundle

You MUST use this before high-stakes architectural decisions, irreversible changes, or when requirements are ambiguous. Runs a decision handshake with the ask_user tool: summarize context, present structured options, collect explicit user choice, then proceed.

ehzawad Bundle

Adaptive, context-driven Claude Code council for project implementation, computer science, software/ML engineering, DevSecOps, research, and other complex work: Codex orchestrates role-framed persistent Claude Code agents to collaborate and reconcile toward one shared goal. Use for direct invocation $claude-coterie or when the user invokes "claude council," "claude coterie," or "claude team." On invocation, reconstruct what the user is actually doing, compose task-specific roles with no built-in catalog, share the decision-complete context, announce the panel, and launch without a manual approval gate. A one-role panel uses the same council workflow.

elb-pr Bundle

Use when conducting structured investigative research, OSINT analysis, due diligence, or intelligence-grade inquiry. Activate for tracing beneficial ownership, mapping entity networks, authenticating digital evidence, sanctions screening, resolving fragmented identity records, constructing chronological timelines, or producing ICD 203-compliant analytical briefings. Also activate when the user references case decision logs, investigation strategy, source grading, entity registers, evidence preservation, network analysis, content verification, genealogical research, cultural context assessments, or analytical briefings.

emaynard Bundle

Scaffold a new genealogical research project inside an Obsidian vault that uses Charted Roots (CR). Creates a Research Project index note plus a seeded Individual Research Note, both flat in the vault's shared Research folder (no per-project subfolder), using CR's cr_type frontmatter so the project shows up in existing Bases views immediately. Use this whenever the user wants to "start a new research project," "research a new ancestor," "open a case file on" someone, or names a specific ancestor plus an open question (parentage, origin, identity, a conflicting record, immigration, etc.) with no existing project for them yet. Also use it for "help me dig into who X's parents were" when no project for X exists. Do not use for editing an existing project, creating a plain Person/Source/Event note (those have their own CR templates), or vaults that don't use Charted Roots.

erongcao Skill

历史学文献检索工具。支持 OpenAlex、Crossref、Google Scholar 等多数据库检索，用于检索历史学领域的研究进展。

erongcao Bundle

医学文献检索、批判性评价与综合分析。支持PubMed/Embase/Cochrane多数据库检索、PMC全文获取、AI辅助分析、研究质量评价、系统综述写作。使用场景：(1)检索多数据库医学文献，(2)自动获取PMC开放获取全文，(3)基于全文的深度批判性评价，(4)AI辅助PICO提取与质量评价，(5)辅助系统综述和Meta分析。

eshaham Bundle

Give a fast, reviewer-facing verdict on whether a PR or diff in this repo is safe to merge — SAFE, RISKY, or BREAKING — instead of a long research writeup. Checks for (1) unnecessary/stale comments, (2) whether existing working code paths still behave identically (backward compatibility), and (3) whether any new feature added alongside the core scraping logic degrades gracefully instead of risking the whole scrape on failure. Use this whenever the user asks to review a PR, look at a diff, check a pull request for breaking changes, asks "is this safe to merge/approve", pastes a GitHub PR URL/number and asks what to watch out for, or says they don't have time to dig into a PR themselves and just want the important part. Trigger even if they only give a PR number or link with no other instructions — that alone means they want this fast verdict, not an essay.

esm7 Skill

Look up and record geolocations in Obsidian notes using the Map View plugin. Use as part of helping the user to plan a trip, research places to visit, record a location in a note, or whenever the content being added to a note includes named real-world places. Every time the user asks you add to a note something that is a location, consider using this skill so it will be logged as a geolocation. Also use when the user refers to a known place ("my home", "my office", "my hotel") — query their vault to find its coordinates, then use with other commands. Another usage is to measure distances, either aerial or by routing (foot/driving/cycling etc), e.g. for researching for places that are nearby a location, within a walking distance from it, within a driving distance, etc. Or to query for places around a point with the distancefrom operator.

joshuaroll Bundle

Comprehensive Wikipedia research skill for extracting verifiable, citation-backed information in structured JSON format optimized for AI consumption and verification pipelines. MANDATORY TRIGGERS: Wikipedia research, Wikipedia citations, verify Wikipedia claims, extract Wikipedia references, fact-check with sources, research topic with citations, gather verifiable information, Wikipedia API, collect research data, build knowledge graph, entity extraction, research timeline Use when: (1) Researching topics that need source verification, (2) Extracting Wikipedia content WITH its underlying citations, (3) Building research datasets for AI verification, (4) Collecting structured bibliographic data, (5) Tracing claims to original sources, (6) Building knowledge graphs of entities and relationships, (7) Constructing timelines from biographical/historical data, (8) Cross-validating facts across multiple sources

juneyaooo Bundle

Use this skill when the user asks about 周易研究, 易经学习, 六十四卦, 起卦解卦, 动爻变卦, 经传结构, 筮占方法史, 乾坤卦解, 王弼/朱熹/孔颖达/李鼎祚注疏, 林义正《易经》解读, or needs source-grounded Zhouyi lookup with original text, commentary, course notes, and image evidence.

existential-birds Skill

Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose improvements plus OSS candidates.