Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Web search using curl + multiple search engines (Baidu, Google, Bing, DuckDuckGo). Activates when user asks to search, look up, or query something online. Includes security enhancements: input sanitization, command injection protection, and URL encoding.
Run a disciplined, multi-source research investigation for a high-stakes question or decision — fan-out web search across many channels, parallel sub-agents, source triangulation (each claim backed by ≥3 independent sources), an adversarial review pass, and every source saved to its own file with verbatim quotes for reuse. Use when a low-quality answer is expensive: strategy work, comparing N products/methods/markets, validating a hypothesis with external data, or mapping how a field works. NOT for quick fact-checks (answer directly), structured 12-dimension competitor scoring (use competitive-teardown), or fast topic overviews where the decision risk is low (use the research router instead).
Take full-page screenshots of web pages in the browser, producing one long PNG that contains all page content. Trigger scenarios: the user asks for a long screenshot, full-page screenshot, complete screenshot, long screenshot, or full page capture of a web page, or wants a web page/article/report captured as one complete image. Supports the user's already open tab or a specified URL. Automatically handles SPA internal scroll containers, lazy-loaded images, and stitching very long pages from tiles. No external dependencies; connects directly to the Chrome DevTools Protocol for all operations.
Provides practical frameworks for fast decision-making through mental shortcuts (heuristics) and systematic error prevention through structured checklists. Guides through designing effective heuristics, creating checklists for complex procedures, and recognizing when shortcuts lead to biases. Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions heuristics, rules of thumb, mental models, checklists, error prevention, cognitive biases, satisficing, or standard operating procedures.
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, Wallstreetcn, V2EX, and Weibo Hot Search. Useful for 'daily scan', 'tech news briefing', 'finance updates', and 'deep dives' on trending topics.
Open Orbit briefing skill — selected by the Orbit pipeline when Linear is the user's only connected connector, or when the user explicitly scopes their daily digest to Linear. Pulls the past 24 hours of issue movement, status changes, assignments, and cycle progress from the user's authenticated Linear connection and renders the digest in Linear's native Inbox + cycle-progress visual language. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Linear data.
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and renders the digest as a native Notion page (callout / toggle / database table primitives). This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Notion data.
Pachca — interactive forms and modal windows for bots. Creating forms, modal windows, polls, questionnaires and requests with input fields, dropdowns, checkboxes, date/time selection, file uploads. Use when the user wants to show a form, open a modal window, create a poll or questionnaire, handle form submission (view_submission), or validate fields. Also for trigger_id and dropdown/select. Requires a bot token. NOT for inline buttons in messages or configuring webhooks. Use when: показать форму, открыть форму, собрать форму, модальное окно, модалка, отправка формы, обработать форму, валидация формы, валидация поля, view_submission, опрос, анкета, заявка, форма заявки, form, modal, interactive form. NOT for: кнопки в сообщении, настроить бота, вебхук, → pachca-messages, → pachca-bots.
Pachca — MY profile, MY status, custom fields. Always only about yourself — no parameters, data is determined by the token. Use when the user wants to get their profile, find out who they are, set or remove their status, view their email/department, or learn which custom/additional fields exist (custom_properties). Also for requests like “who am I”, “my account”, “my email”. NOT for managing other employees, NOT for changing another employee's status, NOT for information about the token and its scopes (use pachca-oauth). Use when: мой профиль, покажи профиль, мой статус, установить статус, убрать статус, кто я, мой email, мои данные, дополнительные поля, кастомные поля. NOT for: сотрудники, список сотрудников, создать сотрудника, статус сотрудника, → pachca-users, → pachca-oauth.
Write OKRs, KPIs, or a North Star Metric derived from product strategy — or review an existing goal set. Enforces outcome-based key results with baselines and targets, one focus objective per team per cycle, leading+lagging balance, and guardrails against gameable targets. Trigger when asked to write OKRs, set quarterly goals, define KPIs or success metrics, choose a North Star Metric, or run goal-setting/planning for a team or product.
[Hyper] Produce a multi-source, source-backed markdown research report for fact-finding, comparisons, market/trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources. Use when synthesis and citations are needed, not for one-source lookups.
Generate the user's daily standup update from real activity: GitHub PRs and commits, unpushed local work across worktrees, and Claude/Codex/OpenCode session history. Use when the user says /standup, give me my standup, what did I do yesterday, or wants a status summary.
Publish, review, organize, and share work with Artifact Server, or operate an installation when the user explicitly requests administrator work. Use for Artifact Server links, files or sites to upload, project, artifact, version, tag, sharing, or comment work, connection help, and explicit install, deploy, upgrade, backup, restore, or repair requests. Do not use for unrelated package publishing or for building software that the user did not ask to store in Artifact Server.
Transcribe or post-process audio with AssemblyAI when explicitly requested or already selected by the project. Choose models, languages, diarisation, and region; retain resumable job IDs and produce speaker-aware local exports. Do not activate merely because a task involves generic transcription.
Academic paper writing, paper analysis, and research-side workflow kit for bilingual Chinese-English research work. Use when Codex needs to draft, translate, polish, shorten, expand, humanize, logic-check, explain long English sentences, read or analyze papers, produce reviewer-style reports, suggest model-improvement ideas from code or papers, generate paper-figure or UML prompts, or handle evidence-based research queries from notes, LaTeX, Markdown, PDFs, code, or full manuscripts. Especially useful when the user wants direct academic output rather than only a generic prompt template.
Applies Apple's Project Purple design philosophy for radical innovation. This skill should be used when the user wants to challenge industry conventions, approach open-ended problems requiring disruptive thinking, or when standard brainstorming needs a breakthrough approach.
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host, or to continue, resume, or recall recent Cua activity.
Turn AI coding conversations and project delivery materials into a verifiable nine-part evidence chain, distinguishing problems, decisions, individual actions, delivery stages, outcome evidence and responsibility boundaries. Use when the user runs /evidence-recap, $evidence-recap, or explicitly asks to review an AI coding process, delivery records, rollout status and evidence gaps; not for resume rewriting, source-code walkthroughs or mock interviews.
Extract architecture, method and result figures from an arXiv ID/link, a public direct PDF URL, or a local paper PDF, save them to an Obsidian images directory, and generate an index. Use when the user asks to extract figures or another research skill needs embeddable images.
Use when the user explicitly asks to "update the project guide", "sync the guide", or "capture insights into the guide". Capture reusable writing insights newly produced in the conversation into the project guide file in real time, keeping terminology consistent, the structure stable, and the content verifiable and reproducible. The guide file path must be specified when invoking.
Applies "what if" thinking to explore alternative scenarios, test assumptions, understand causal relationships, and prepare for uncertainty. Guides through counterfactual reasoning, scenario exploration, pre-mortem analysis, and stress testing decisions against alternative futures. Use when exploring alternative scenarios, testing assumptions through "what if" questions, understanding causal relationships, conducting pre-mortem analysis, stress testing decisions, or when user mentions counterfactuals, hypothetical scenarios, thought experiments, alternative futures, what-if analysis, or needs to challenge assumptions.
ONLY when the user explicitly wants a thorough, exhaustive, or comprehensive multi-source investigation or report that can run for minutes — due diligence, market landscapes, "compare X across many entities", verified fact-finding. ALSO read this when writing code that integrates the /v1/research endpoint (modes, reasoning depths, async polling). Slower and more expensive than linkup-search. For normal lookups and research use linkup-search instead; for bulk records from a page use linkup-extract. Uses Linkup's async /v1/research REST endpoint. Requires LINKUP_API_KEY.
Load when user says "mental model", "think through this", "structured thinking", "help me decide", "analyze this problem", "first principles", "pre-mortem", "stakeholder mapping", "what framework should I use", or any specific model name. Provides 59 thinking frameworks for decision-making, problem decomposition, and strategic analysis.
Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them in a layout that mirrors GitHub's native Notifications + PR-diff visual language. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live GitHub data.
Transforms an academic paper into deep, multi-layered understanding. Use when asked to explain a paper, break down a research paper, understand an arXiv paper, or build intuition for a technical concept from a paper. Generates explanations at multiple levels plus visual intuition diagrams.
Use when: the user explicitly requests demand research or pain-point validation, or an existing product needs to validate a specific requirement. Do NOT auto-select when: the user only wants to brainstorm new product directions (prefer pm-brainstorm) or is just having a brief discussion that doesn't need formal research. Direct /pm-demand requests may proceed with their own evidence checks; a full new-product chain can recommend brainstorm first.
Find and validate startup ideas by mining user complaints, crafting premises, and navigating the idea maze. Use when discovering product opportunities, validating ideas, shaping solutions, researching user pain points, or exploring what to build.
All online operations must be handled through this skill, including searching, web scraping, post-login actions, and online interactions. Use when the user asks to search for information, view web content, visit a site that requires login, interact with a web interface, scrape social media content (Xiaohongshu, Weibo, Twitter, etc.), read dynamically rendered pages, or perform any online task requiring a real browser environment.
Health-check the wiki: scan all pages for broken wikilinks, orphaned pages, stale index entries, missing connections, em-dash violations, orphaned assets, and schema errors. Produces a dated lint report. Always use this skill when the user says /wiki-lint, mentions broken links, dead wikilinks, orphaned pages, 'what's broken in my wiki', 'are my links working', 'which pages have no connections', or asks for a wiki health check. Also use when the user notices a link that doesn't resolve, suspects the index is out of date, or asks whether the wiki is in good shape - even if they don't say 'lint'. Never auto-fixes anything; reports only. When in doubt whether a wiki health check is being requested, use this skill. Requires filesystem read access and write access to archive/.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.