Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Scaffold and operate Claude Blog Brain, a source-cited Obsidian brain for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill. Use when the user says "claude-blog-brain", "Claude Blog Brain", "create a blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill.
Eva Lens 2.5.0 is an entry point for diverse perspectives and disciplinary exploration. Use it to examine an undeveloped topic, phenomenon, or question through the discipline that offers the strongest explanatory lens, or to quickly illuminate a developed idea, topic, title, script, retrospective conclusion, business judgment, or plan from four perspectives, target one perspective, or examine it deeply. Triggers: /eva-lens, Eva Lens, “take a look with Lens,” disciplinary exploration, interdisciplinary exploration, looking from sociological, psychological, economic, or other perspectives, opening up more explanatory mechanisms, multiple perspectives, seeing something from different angles, filling blind spots, reader perspective, opponent perspective, industry reality perspective, creator perspective, deep scrutiny, detailed reasoning, finding counterexamples, checking weak assumptions, finding falsification conditions, counterfactuals, and reverse-reviewing a current judgment. Ordinary “help me think this through” or “talk with me” requests are still handled by Eva Think. Lens does not create profiles, save information, simulate personas, or discuss individuals.
When the user wants to identify, evaluate, or prioritize potential investors for a fundraising round. Also activates when the user asks "who should I pitch?", "find me investors", "build an investor list", or mentions VC/angel targeting.
Query patent family information through the Eureka patent data platform, including simple families, INPADOC families, and PatSnap families. Trigger this skill when the user mentions patent families, patent family searches, simple families, INPADOC families, PatSnap families, finding family patents, patent equivalents, family members, finding related patents across countries, Eureka patent families, patent family, family patents, patent equivalents, cross-border patents, Eureka, INPADOC family, or simple family. Even if the user does not explicitly say “patent family,” trigger this skill whenever their request involves querying family members, equivalent patents, or related cross-border applications for one or more patents.
Nuwa creates people: enter a person's name or topic, or even just a vague need, to automatically conduct in-depth research → distill a thinking framework → generate a runnable persona Skill. Two entry paths: (1) a specific name → distill directly; (2) a vague need → diagnose and recommend → then distill. Triggers: "create a skill", "distill XX", "Nuwa", "create a person", "XX's way of thinking", "make an XX perspective", "update XX's skill". Vague needs also trigger it: "I want to improve my decision-making", "Is there a way of thinking that could help me...", "I need a thinking consultant".
Paper Analyst — Responsible for closely reading papers, extracting methodological details, and building comparison tables. Activated when assigned by a research lead or literature scout to analyze papers. Performs structured analysis of the Top 20 core papers and generates paper analysis cards and cross-paper comparison tables.
Know when to move fast and when to move carefully. Master Jeff Bezos' framework for distinguishing high-stakes irreversible decisions from low-stakes reversible ones. Use when: Prioritizing decisions to know where to invest time; Team empowerment to understand what to delegate vs. escalate; Avoiding analysis paralysis on decisions that don't matter; Risk management to identify where caution is truly warranted; Speed vs. thoroughness trade-offs in any context
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint. Includes a reversible curation cull pass (Phase 5) with hard keep/delete/merge verdicts, substance gates, grounding labels, cluster budgets, and merge-with-backlinks salience promotion.
Build and run a business owner's second brain: one vault, two wings (personal + four-layer business), operated through Claude Code with Obsidian as the viewing deck. Routes every entry to one of four modes: Setup, Capture, Distill, Create-My-Jarvis. Use when the user wants a second brain built or their business knowledge organized into a vault ("set up my second brain"), or asks to continue an installation paused between stations ("continue setup", "next station"), wants to move their business in one room at a time ("capture", "move in a room"), asks for the weekly maintenance ritual ("distill", "tidy my vault", "weekly review"), wants their AI given a persona ("create my jarvis"), or asks for a retrofit an older vault lacks: the safety lock, session memory ("make my sessions searchable"), the maintenance doorbell ("update my maintenance doorbell"), the boot gate ("upgrade my command base"), the end-of-day reconcile ("upgrade my end of day"), the Command Deck ("rebuild my deck", "fix my deck", "add my command deck", "my dashboard is empty", a pasted "# Deck edits" block their command base cannot apply yet), or a companion skill that joined the payload after setup ("install the missing skills", "add the wiki sync").
Entry point for open-source intelligence, investigation and verification work. Routes any identifier — a name, phone number, email address, username, domain, company, photo, crypto address, tail number or IMO — to the right investigation workflow, after setting an authorised scope. Use when asked to investigate, research, verify, vet, check out, look up, background-check, trace, attribute or find someone or something; when a request involves due diligence, KYC or KYB, counterparty or vendor risk, sanctions and PEP screening, AML, fraud, business email compromise, verifying a supplier before payment, recruitment or marketplace scams, insider threat, executive protection, attack-surface review, journalism or fact-checking; or when someone asks “who is this”, “who owns this”, “is this real”, “where did this come from” or “where do I start”. Reference at useosint.com/skills
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.
A real-time search tool for Douyin posts. Uses the Redfox interface to search the latest Douyin posts in real time based on user-provided keywords. Supports filtering by sort order and publication time, and returns real-time data (not cached or historical data). Use when the user explicitly requests “real-time,” “latest,” “now,” or “current” Douyin content, or questions the freshness of existing data. Triggers: real-time Douyin search, latest Douyin posts, trending Douyin posts in real time, current Douyin data, real-time Douyin lookup.
High-rigor interview coaching skill for job seekers. Use when someone wants structured prep, transcript analysis, practice drills, storybank management, or performance tracking. Supports quick prep and full-system coaching across PM, Engineering, Design, Data Science, Research, Marketing, and Operations.
Read and manage Google Tasks task lists and individual tasks via the Tasks v1 REST API. Use when the user mentions Google Tasks, todo / pending / overdue tasks, weekly task recap, grouping todos by list, adding or completing a task, or moving / deleting tasks.
Literature Scout — conducts multi-source literature searches, screening, and classification to build a literature matrix. Activated when assigned by a research lead to collect literature. Uses tools such as Exa, ArXiv API, and Semantic Scholar for systematic literature searches.
Review the operating health of a one-person company using lightweight metrics, bottleneck analysis, and stop-loss logic. Use when Codex needs to explain review concepts when needed, verify available outputs, ask one question at a time, present multiple bottleneck hypotheses, and write user-confirmed outputs into `opc-doc/`.
Inventory all founder resources across 8 categories for a one-person company. Use when Codex needs to systematically confirm what resources the founder has — experience, network, skills, relationships, channels, assets, time/money constraints, hard limits — by first doing a broad scan of each category, then drilling into specifics (distribution, usable portions, how to use, cost of use), and producing a confirmed detailed resource inventory written to `opc-doc/`. Does NOT analyze directions, preferences, suitability, or risk tolerance — those belong to downstream skills.
Entry point for reading PANews cryptocurrency/blockchain news, market narratives, and Polymarket smart money leaderboards. Triggers: today’s headlines, breaking news, trending rankings, article search, reading specific articles, browsing columns/series/community topics, industry events and conferences, event calendar, platform hot searches and editorial picks, latest smart money boards, board highlights, and board comparisons.
Make decisions that your 80-year-old self will thank you for. Master Jeff Bezos' mental model for bold choices that minimize long-term regret. Use when: career decisions with long-term implications; startup vs. safe job choices; major life pivots (relocations, relationships, changes); risk-taking decisions where fear is a factor; opportunity evaluation when considering bold moves
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"
Web scraping, search, crawling, and browser interaction via Firecrawl CLI. Use when the user wants to search the web, fetch a URL, scrape content, crawl docs, download a site, extract structured data, or interact with JS-heavy/login-gated pages. Triggers on: "search for", "scrape", "fetch this URL", "get the page", "crawl", "download the site", "extract structured data", "click the button", "fill the form", "log in to". Do NOT use for local files, git, or code editing. For advanced use (bulk crawl, AI agent extraction, browser profiles, parallel jobs): install firecrawl-crawl, firecrawl-agent, or firecrawl-instruct skills.
A complete workspace for structured job description (JD) analysis, role-fit diagnosis, ATS readability audits, and targeted résumé tailoring. Use when the user mentions “JD,” “job description,” “role fit,” “analyze this JD,” “am I a good fit,” “tailor my résumé for…,” “application,” “job search,” “job requirements,” “Job Description,” “ATS screening,” or saving different application versions. Supports JD analysis with a diagnostic report, or one-stop generation of a role-tailored HTML/PDF résumé, match report, and version history.
Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions "browser", "webpage", "open URL", "screenshot", asks to read/interact with any website, or wants a reusable CLI tool or script that automates a specific website. Use even for simple-sounding browser requests — the daemon handles all complexity.
Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).
Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.
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.