Research & Search

duckduckgo Skill

Use this skill when the user asks to review a DuckDuckGo Android public API proposal. If given an Asana task URL, first fetch the task and confirm it is an API proposal before invoking — do not invoke just because a URL was paired with "review". Confirmed signals: the task title contains "API Proposal"; the task belongs to project 1212149061863360 (API Proposals); or the description proposes changes to a -api module. Also invoke for any request to review, evaluate, or give feedback on a proposal pasted inline or provided as a file. Covers phrases like "review my API proposal", "is this API design good?", "check my public interface", "I'm about to submit an API proposal". When the user shares Kotlin code, only invoke if the code is explicitly from or intended for a -api module — do not invoke for impl-only changes or general Kotlin questions. IMPORTANT: Always apply these instructions directly — never delegate or summarise.

dyoshikawa Skill

Summarize the project context and key constraints

jibaxzzz Skill

Perform a focused web search and summarize authoritative sources.

eduard256 Skill

Add a new protocol support to Strix -- full flow from research to implementation. Covers stream handler registration, URL builder updates, database issues, and go2rtc integration.

eruo005-dev Skill

Uzun Türkçe metinleri madde madde, yönetici özeti veya TL;DR olarak özetler; Türkçe akıcılığı ve anlam bütünlüğünü korur. Use when the user wants to summarize long Turkish text (articles, reports, transcripts, meeting notes) into bullet points, an executive summary, or a short TL;DR.

kju4q Bundle

Use this skill when the user wants an idea, plan, or position pressure tested before committing to it. Activate when the user is about to spend significant time or money on something, wants the strongest case for or against a position, or suspects they are too attached to an outcome to judge it honestly.

kweaver-ai Bundle

Draft or update release notes and changelog entries from repository evidence. Use when the user asks to add a new version to CHANGELOG files, summarize what changed in a branch or release, explain how changelog content was derived, or keep multilingual changelogs consistent.

kyungseo Bundle

Writing Quality Editor (WQE) composes, assesses, revises, and adapts user-facing writing so it reads naturally while preserving meaning, claims, intent, voice, conditions, numbers, identifiers, exceptions, and risks. Use when a user asks to write, review, polish, fix, improve, supplement, clarify, translate, localize, or make a document sound natural; no skill or mode name is required. Covers README, onboarding, release notes, manuals, UI, errors, gallery copy, research-backed briefs, technical comparisons, and natural English↔Korean adaptation. If a host repository workflow owns document classification, path, indexing, lifecycle, or approval, keep it primary and use this skill only as an optional authoring layer. Locale-neutral design; EN↔KO (`ko-KR`) is the initial profile under validation. Do not game detectors, conceal provenance, invent claims, replace evidence review, or bypass host workflows.

learnprompt Bundle

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

lgldlk Bundle

Fetch and summarize the latest AI news from reputable sources (via RSS/Atom feeds) and produce a dated digest with links. Use when the user asks for “latest AI news”, “AI 新闻汇总/简报”, “本周/今日 AI 动态”, or when you need to gather up-to-date AI announcements, research highlights, and industry coverage from known sites.

liblaf Bundle

Generate exactly one high-quality Conventional Commit message from the current Git diff. Use when Codex needs to inspect staged changes, summarize the dominant intent, and return only the final commit message with no analysis or extra text.

liorhai5 Skill

Investigate a codebase with system awareness — read boundaries, ownership, control flows, data flows, contracts, and blast radius BEFORE recommending action. Produces a structured understanding artifact with every claim cited file:line. Use when the user asks to "understand this codebase", "deep-dive this feature", "trace this flow", "why is this slow/flaky/coupled", "is this PR safe", "what breaks if I change Y", "prepare to refactor Z", "investigate this bug at the system level". For research from external sources (URLs, docs, Slack), use a research command in mtg or similar. For greenfield architecture design, this is not the right tool.

lnilya Skill

Plan and scaffold an academic introduction section from source papers, context, or rough notes. Use this skill whenever Ilya wants to structure an intro, outline a paper's opening, map the literature into a writing plan, figure out what paragraphs an introduction needs, or asks "what should my intro cover?", "help me plan my introduction", "outline an intro from these papers", "what topics should I introduce?", "scaffold my intro section", "turn these papers into an intro plan", or "structure my background section". Also trigger when the user uploads or pastes papers/abstracts and wants to know what to write about — even if they don't say "introduction" explicitly. This skill does NOT write the prose; it produces a clear paragraph-by-paragraph blueprint that guides writing. For the actual prose, hand off to ea-academic-writer.

microck Skill

Search the web, extract or summarize a page, translate it, or check the news with the kagi CLI instead of WebSearch or WebFetch. Load this first for any Kagi task: it covers search and page content, and routes Assistant, automation, and account work to the right skill.

migaceta Skill

Búsqueda y análisis de criterios del Instituto Nacional del Derecho de Autor (INDAUTOR) sobre obras IA-generadas, derechos sobre output IA y propiedad intelectual mexicana en contexto de IA generativa. Cubre el vacío regulatorio mexicano frente al precedente USA (Thaler v. Perlmutter, Zarya of the Dawn). Genera cláusulas contractuales sugeridas sobre titularidad de derechos de autor sobre material generado con IA, para negociar en engagement letters. Usar cuando el abogado mexicano debe asesorar a cliente sobre IP del output IA, registrar obra con componente IA, o estructurar cláusula contractual sobre titularidad.

miles990 Skill

Creative project memory management system — Three-tier memory architecture / Knowledge base maintenance / Summary generation

monarchjuno Bundle

Install, list, inspect, update, remove, create, check, or share a GitHub-backed Wiki, Lens, or Method Pack. Use only for an explicit Pack lifecycle or publishing request; Guru Mode Auto and an ordinary natural-language investment request never invoke Pack work implicitly. Do not use for research, local memory curation, Decisions, or lesson extraction.

monarchjuno Bundle

Recall or maintain project-owned Wiki, Lens, Evidence, and Method memory, initialize a workspace, or inspect and explicitly change Guru Mode. Use automatically in an initialized Guru Maker project when a natural-language investment request can materially benefit from existing local memory or produces eligible stable knowledge, even if the user does not mention Guru Maker, a Skill, or saving. Use also for a short follow-up that clearly refers to saved investment memory but omits its subject, so the missing referent is requested before searching. Use when no external refresh, analysis of supplied point-in-time external evidence or data, or point-in-time judgment is requested; an explicit request to retain a supplied source is still memory work. Do not use for research, Decisions or outcomes, deliberate lesson extraction, or Guru Pack lifecycle work.

monarchjuno Bundle

Synthesize a requested point-in-time investment judgment, record a Decision and explicit relationships, review an outcome, or render the Decision Graph. Use automatically for natural-language requests asking what investment alternative to choose, buy, sell, hold, allocate, or size, or explicitly revisiting a prior Decision, even when the user does not mention Guru Maker or a Skill; in Guru Mode Auto, a material judgment may be recorded without a separate save request. Use also for an Execution Brief after explicit action intent. Do not use for a research-only thesis update without an investment choice, general research, memory curation, explicit lesson extraction, or Guru Pack lifecycle work.

monarchjuno Bundle

Apply Guru Maker's project-memory retrieval and retention contract to material natural-language investment or financial research in an initialized Guru Maker project, even when the user does not mention Guru Maker or saving and another research capability supplies the domain procedure. Host agents and specialized capabilities own research strategy, tool selection, and synthesis. Use explicitly outside an initialized project only when the user names Guru Research. Do not use for memory-only recall, supplied-source capture without refresh or analysis, a requested point-in-time Decision or outcome, deliberate lesson extraction, or Guru Pack lifecycle work.

n1ddeh Skill

Summarize uncommitted changes or recent commits for PR preparation. Use when asked to summarize changes, prepare a PR description, review what changed, or generate a summary of work done.

mb3rgel-ui Skill

Research topics using Grok's web search and X/Twitter search via the xAI Responses API. Use for finding media appearances, news, people, companies, or any task requiring real-time web data.

mehdiforoozandeh Bundle

An agentic research companion — a scientific-method lab notebook for a research program. Organize work as a tree of Questions (what we don't know) and falsifiable Hypotheses (testable leaves), each with pre-registered verifiables and findings; a deterministic engine derives verdicts, rolls them up, and trips a human review gate. Use when the user wants to run a research program rigorously: open/track research questions, design experiments as problem-statement → hypothesis → verifiables → findings, synthesize results, and update the open questions. Triggers: crux, "open a research question", "lab notebook", "hypothesis/experiment tracking", "design an experiment", "what should we try next", "research notebook", scientific method, meta-questions, research vault.

romiluz13 Bundle

Compare finished code against requirements and applicable official docs, research unexplained discrepancies, correct authorized changes, and run affected checks. Use for verification or review of an implementation.

rudironsoni Skill

Draft outbound announcements from ontology-brain facts. Use when asked to announce, summarize for others, write an update, or turn brain facts into a reviewable message.

runkids Skill

Record external observations, ecosystem trends, and creative inspiration into .feature-radar/references/. MUST use this skill when the user mentions something interesting from outside their project — other tools, articles, approaches, or trends. Even casual mentions like "I saw a cool thing in X" should trigger this skill. Use when the user: - Says "I saw this cool thing in X's API", "check out how X handles this" - Shares a URL, article, talk, or research finding with relevant insights - Notes an ecosystem trend: new tools, standards, community patterns - Mentions a related project shipping a notable feature - Wants to bookmark external inspiration: "interesting approach", "save this" - Says "add reference", "log observation", "track this project" Do NOT use for internal learnings/patterns — that's feature-radar-learn's job. Do NOT use for prioritizing features — that's feature-radar's job.

sarbak Skill

Run deep research on specific questions to validate assumptions, check facts, and discover recent developments. Pairs with opportunity-analysis and storyline-synthesis for full strategy workflows. Use when the user wants to research specific questions, validate business assumptions, fact-check claims, or investigate a market. Also trigger when someone says "research this", "is this actually true?", "validate these assumptions", or "what's the current state of [topic]?"

sarbak Skill

Write a clean, McKinsey-style synthesis document from analysis work. Pairs with opportunity-analysis and deep-research for full strategy workflows. Use when the user asks to synthesize findings, write up results, create a strategy summary, or produce a recommendation document. Also trigger when someone says "write this up", "synthesize", "create the storyline", "write the synthesis", or "turn this research into a document."

scottwater Skill

Transform feature ideas/bugs into comprehensive implementation plans in docs/plans with research, flow analysis, and actionable phases.

scottwater Skill

Conduct comprehensive codebase research, then synthesize into a dated research document with metadata.

cabaynes Bundle

Structured interrogation skill for stress-testing plans, designs, and ideas. Use when the user says "grill me", "grill me about", "stress test my plan", or "poke holes in this", or asks to resume an earlier grill session. Produces dialogue and a persistent session file — not code or files. Works across domains: product design, software architecture, business strategy, creative writing, research proposals. Do NOT use for code review, debugging, refactoring, implementation tasks, or general feedback on existing code.

carlvellotti Skill

Turn raw interview notes into structured insights with patterns and quotes

chekusu Skill

Methodology for market research and data collection, ensuring data quality and source traceability

chianglianglin Skill

Research any world-building, historical, or thematic topic using live web search and ingest findings into the story wiki.

context-is-everything Bundle

Search paywalled and protected sites (LinkedIn, WSJ, news sites) using stealth browser techniques when WebFetch fails. Use when (1) WebFetch blocks or cannot access a site, (2) Searching LinkedIn profiles or professional networks, (3) Searching paywalled news sites (WSJ, NYT, FT), (4) Need to avoid bot detection for legitimate research, (5) Extracting metadata from search results when full content is behind authentication. Provides DuckDuckGo and stealth Google search with Chromium browser automation.

cookjohn Skill

Search PubMed for biomedical literature by keywords. Returns structured results with PMID, title, authors, journal, date, DOI. Use when the user wants to find papers on a topic.