Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when the user mentions academic research, scholarly writing, papers, or scientific literature.
Use when the user wants prose rewritten, tightened, audited, simplified, polished, humanized, grammar-checked, or made plainer, clearer, shorter, easier to scan, or easier to act on without changing the intended meaning, audience, tone, or explicit constraints. Trigger on requests such as plain English, simple English, make this clearer, make this more direct, clean this up, edit this, review this writing, grammar check, too wordy, too formal, less fluffy, friendlier, shorter, audit then rewrite, keep the tone, mode=strict, STE, ASD-STE100, or ADHD-friendly. Also trigger for docs, prompts, emails, UI copy, support replies, release notes, status updates, incident notes, procedural text, and other LLM-written prose. Prefer this skill when the main job is improving English prose or preserving tone while increasing clarity, including audit-only requests and exact-text-preservation constraints, but not when the real task is fact-checking, policy setting, or substantive content design.
Create financial plans for Chinese wealth management clients covering retirement, education, estate, and cash-flow planning. Adapted from the original financial-plan skill for Chinese tax rules, social security, and local financial products. Triggers on "A股财务规划", "理财规划", "financial plan China", "retirement plan China", "财务规划客户", "退休规划", "教育金规划", or "comprehensive financial plan".
Comprehensive A-share sector and industry landscape reports — market size, competitive positioning, policy environment, key A-share players, trading multiples, and thematic trends. Adapted from the original sector-overview skill for Chinese market structure and terminology. Triggers on "A股行业分析", "行业研究", "板块分析", "sector overview China", "A-share sector deep dive", "白酒/半导体/新能源 行业分析", or "[industry] landscape China".
Audit your calendar with Cowork's calendar tools -- measure meeting load and fragmentation, identify which recurring meetings earn their slot, propose consolidations and focus blocks, and draft the diplomatic messages that reclaim your week.
Sweep your folders and downloads for tax documents and build a CPA-ready package -- checklist by form type, everything renamed and organized, a missing-document chase list, and flagged items worth asking your accountant about. Organization, not tax advice.
Drop a folder of vendor quotes, proposals, and SOWs on Cowork -- normalizes them into one comparison matrix, computes true total cost of ownership, surfaces the terms each vendor buried, and arms you with negotiation leverage points and reference-check questions.
Apply 25 professional mental models to solve complex problems. Use when: (1) facing multi-faceted challenges that require diverse perspectives, (2) stuck in single-minded approaches, (3) need innovative solutions, (4) making major decisions with multiple stakeholders, (5) understanding complex human behavior, or (6) seeking to break cognitive biases and adopt alternative viewpoints.
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals. Use when asked to set up the screen or the day, open and arrange a set of apps or repos, prepare or run a live demo before recording, test a desktop application that has no headless harness, launch or steer a Claude Code session in another window, or capture what is on screen as evidence. Triggers on "set up my screen", "get my demo ready", "drive the screen", "control my desktop", "open these repos and start", "test this desktop app", "run this on my machine and show me". Not for browser automation, which has its own headless tooling.
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
Use when searching public content on a Halo site with Halo CLI. This includes keyword search, site URL based search, result limits, or any search that does not require authenticated console access. Trigger this skill whenever the user wants to search a Halo site from the terminal, even if they do not explicitly mention 'search'.
When you paste raw human input — a call transcript (Grain, Zoom, Granola, Fathom), a text or email from a client/partner/friend, a voice-memo dump, or meeting notes — and want it converted into structured work. Extracts decisions, action items (yours vs theirs), bugs/feature requests, and facts worth keeping; files GitHub issues in the right repo, captures to the second-brain vault, and drafts (never sends) the reply. Triggers on "/ingest", "ingest this", "here's my call with X," "here's the transcript," "this is from [person]," "[person] asked me this," "from [person]:", a pasted transcript with speaker labels, or a forwarded client message that clearly expects processing. Person→project routing lives in a private config; unknown senders get asked about once, then remembered.
Structures thinking across multiple abstraction levels (30,000 ft strategic, 3,000 ft tactical, 300 ft operational) while maintaining consistency between layers. Guides through top-down decomposition, bottom-up aggregation, cross-layer translation, and constraint propagation. Use when reasoning across multiple abstraction levels, designing systems with hierarchical layers, explaining concepts at different depths, maintaining consistency between principles and implementation, or when users mention 30,000-foot view, layered thinking, abstraction levels, top-down design, or strategy-to-execution alignment.
Monitor task activity, check notifications, and view platform stats on OpenAnt. Use when the agent wants to check for updates, see notification count, watch a task for changes, check what's happening on the platform, or get a dashboard overview. Covers "check notifications", "any updates?", "platform stats", "what's new", "status update", "watch task". For personal task history and listing, use the my-tasks skill instead.
Builds a backwards submission timeline from a conference deadline - days remaining (AoE-aware), abstract-registration offsets, author-list freeze, OpenReview/CMT/EasyChair/HotCRP/PCS account lead times and per-system steps, supplementary-material and code size limits, reciprocal-reviewing duties, and a dual-submission audit. Use when the user wants to plan a submission, asks how long until a deadline, mentions abstract registration, submission checklist, deadline countdown, "what do I need before the NeurIPS/ICML/CHI deadline", or asks what happens after submitting (rebuttal window, notification, camera-ready). Phase-aware - produces pre-submission, under-review, and camera-ready plans from venues/ profiles and flags overdue steps.
Plan how to test the assumptions behind a product idea before building — decompose the idea into its load-bearing beliefs, prioritize the riskiest, phrase them as falsifiable hypotheses, and pick the cheapest method that answers the question. Or critique an existing validation plan. Trigger when asked to validate an idea, de-risk a feature, plan discovery/experiments, test assumptions or a hypothesis, design an MVP test, or decide "how do we know this will work?"
Run a structured rigor audit on prioritization decisions, scored backlogs, RICE/ICE/MoSCoW outputs, or roadmap orderings. Produces a severity-rated issue list with concrete fixes — catches invented scores with false precision, priorities unmoored from strategy, feature-factory ordering, everything-is-a-must-have inflation, and trade-offs left implicit. Use when reviewing a prioritized backlog, scoring exercise, roadmap order, or "what should we build first" decision, or as a validation step after any prioritization work.
Produce or critique a product vision and/or product strategy — an aspirational destination and the deliberate, trade-off-driven choices to reach it — not a buzzword poster or a feature list. Distinguishes the vision/strategy/roadmap/mission artifacts, ladders product vision up to company vision, forces a focused segment + differentiation + explicit "won't do", and sets the stability rule (stubborn on vision, flexible on strategy). Applies the always-true core and gates context-dependent decisions (which strategy framework, vision communication format, single vs. multi-product, B2B vs. B2C, new vs. existing, depth). Trigger when asked to write/define/critique a product vision, vision statement, product strategy, strategic themes, positioning/where-to-play/how-to-win, or to tell vision from strategy from roadmap.
Qinyan academic citation - first search literature via the Qinyan OpenAPI, then output citations in standard formats such as GB/T 7714, IEEE, APA, MLA, Chicago and Harvard. Strictly follow academic conventions and keep ellipses for information that was not retrieved. Triggers: 文献引用, 参考文献, 引用格式, citation, reference format, 生成引用, 引用管理, 参考文献格式
This skill should be used to search the local Obsidian vault / markdown knowledge base by meaning, not just keywords, using the on-device qmd engine (BM25 + vector + LLM rerank). Trigger when the user asks to "search my vault/notes", "find notes about X", "what do my notes say about Y", "do I have anything on Z", "semantic search my knowledge base", or wants concept/cross-lingual retrieval over markdown. Fully local — nothing leaves the machine.
Investiga uma pergunta contra fontes primárias de alta confiança e registra os achados como um arquivo Markdown no repo. Use quando o usuário quiser um tema pesquisado, fatos de docs ou de API reunidos, ou o trabalho braçal de leitura delegado a um background agent.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Due diligence checklists for A-share investments and M&A transactions. Adapted from the original dd-checklist skill for Chinese market due diligence requirements, regulatory filings, and business practices. Triggers on "A股尽调清单", "尽调清单", "due diligence China", "DD checklist A-share", "尽调checklist [company]", or "due diligence questions [company]".
This skill should be used for personal operating-system workflows: content creation, voice consistency, relationship lookup, meeting preparation, weekly review, goal tracking, personal brand management, and network management.
Discovers, retrieves, ranks, and summarizes real existing research papers on any topic. Searches arXiv, Google Scholar, PubMed, Semantic Scholar, and reputable open repositories; returns a curated reading list with verified DOIs, key findings, and citation-ready metadata. Activates on slash commands (`/get-research-paper`, `/find-paper`, `/fetch-paper`, `/papers-on`, `/scholar`) and natural-language requests like "get research paper on …", "find papers about …", "what are the top papers on …". Hands off cleanly to the `research-paper` skill for paper writing. Runtime-neutral — works with Claude Code, OpenCode, Cursor, Cline, Codex, Aider, Amp, and 50+ agents.
Expert in corporate communication, employee engagement, and change management. Use when drafting internal announcements, change communications, leadership messages, or employee updates. Triggers include "internal announcement", "employee communication", "change management", "company update", "leadership message", "town hall".
Operate Jira through the jira-axi CLI - work items, JQL search, transitions, assignments, comments, projects, boards, sprints, saved filters, dashboards, and custom fields. Use whenever a task touches Jira: viewing or editing a work item, moving a ticket through its workflow, assigning it, reading or adding comments, searching with JQL, or working with boards, sprints, and filters.
Discovers, enriches, and scores local businesses in any neighborhood using Nimble Web Search Agents (WSAs) and web data. Returns a structured, ranked list with confidence scores, reviews, social presence, and an interactive map. Use this skill when the user asks about local businesses, places, or neighborhood discovery. Common triggers: "find all coffee shops in", "map every bar in", "local businesses in", "discover gyms near", "what restaurants are in", "neighborhood guide for", "local places in", "find places near", "list all [business type] in [area]", "best [type] near [location]", "build a neighborhood guide", "local place search". Requires the Nimble CLI (nimble extract:templates run, nimble search, nimble extract) for live web data via WSAs and fallback search. Do NOT use for competitor analysis or monitoring (use competitor-intel), company research or deep dives (use company-deep-dive), general web search or extraction (use nimble-web-expert).
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the top of "我的设计". Each connector module picks its own UI form (list, avatar stack, status ring, heatmap, file grid, alert card, …) based on the data shape it returns, so the layout scales as Orbit's connector ecosystem grows. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against the user's live connector data.
Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection and renders the digest as the Orbit Daily Digest email opened inside Gmail's reading view. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Gmail data.
Triggered when an agent needs to retrieve auxiliary legal information beyond legal provisions, judicial interpretations and typical cases. This includes, but is not limited to: legislative background materials (draft explanations, deliberation reports, legislative body press conferences), regulatory cases and administrative penalty decisions, local guidance documents and meeting minutes, drafting explanations and policy interpretations of departmental rules, industry standards and technical specifications, law implementation reports, NPC Standing Committee law enforcement inspection reports, white papers and policy documents, prevailing academic views and authoritative textbook opinions, and comparative foreign legal materials. This skill should be triggered when the user's question involves contexts such as "why is it regulated this way", "what is the legislative purpose", "how do regulators handle this in practice", "what special local rules exist" and "what are the industry conventions".
Run a structured rigor audit on how a team validated (or plans to validate) its assumptions — for a discovery plan, experiment, test, or any "we validated it" claim. Produces a severity-rated issue list with concrete fixes — catches testing the comfortable assumption instead of the riskiest, untestable phrasing, method fidelity mismatched to decision risk, stated intent mistaken for behavior, success criteria set after the fact, goalpost-moving, and underpowered evidence. Use when reviewing a validation/discovery approach or as the validation step after generating an assumption-test plan.
Run a structured quality audit on a product decision or its rationale — a build/buy/sunset/re-platform/pricing call, a decision log, a retrospective, or any "we decided X because…". Produces a severity-rated issue list with concrete fixes — catches outcome-based reasoning (resulting), deliberation mismatched to reversibility, uncalibrated confidence, confirmation/anchoring/framing/sunk-cost bias, missing pre-mortems, and undocumented reasoning. Use when reviewing a major decision or its write-up, or as a validation step after a decision is made.
Read any Substack publication as a local, full-text-searchable corpus — keyless for free posts, your own session for what you subscribe to. Trigger phrases: `archive this Substack`, `read this Substack post`, `search my Substack corpus`, `what's new in my newsletters`, `use substack-reader`, `run substack`.
Refine a raw research question into a structured deep research task. Clarify requirements through questions and generate structured prompts that meet OpenAI/Google Deep Research standards, fully replacing ChatGPT's question refinement feature. Use this skill when the user raises a research question, needs help defining research scope, or wants to generate structured research prompts.
Use for Six Thinking Hats or de Bono's parallel thinking, or when a decision or idea needs facts, gut feel, risks, benefits and new options kept apart: "look at this from all sides", "full perspective check". Skip for plain factual questions or single-angle hot takes.
Operate Synology DSM File Station via WebAPI for major file workflows including listing, search, folder creation, rename, copy/move, delete, upload/download, and archive extract. Use when tasks need scripted NAS file operations with service address, username, and password loaded from environment variables. Note: compress is temporarily unavailable in this skill.
Process source files into synthesised wiki pages. Always use this skill when the user says /wiki-ingest, 'import these files', 'process my clippings', 'ingest this article', 'I have new articles to add', 'turn this PDF into a wiki page', 'what's in my raw/ folder', or 'what have I ingested'. Also use when the user mentions dropping a file somewhere to process, wants to turn any document, article, or PDF into a wiki page, or asks about files in raw/ or ingested/ - even if they don't say 'ingest'. Treats raw/ as a flat queue; scans all files, synthesises knowledge into wiki pages, and moves each source to ingested/ as an atomic commit. When in doubt whether source material processing is being requested, use this skill. Requires filesystem read/write/move access.
Collect and research materials for X (Twitter) content creation using multi-round web search strategy. Use when user wants to gather trending topics, research subjects for X posts, or mentions "collect materials", "research topic", "find content for X", "x-collect". Performs 4-round deep research mimicking human research workflow.
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.