Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Diagnose Claude Code usage limits—find out where tokens actually went and why a 5-hour or weekly limit was hit. Use whenever the user mentions hitting a usage limit, being rate limited, burning through their quota, running out of Claude Code usage, unexpected or suspicious token consumption, "why am I hitting limits", phantom usage, or asks to audit, analyze, or track their Claude Code token usage. Also use when the user asks how full their 5-hour window is, whether it is safe to start a big task now, which tool, model, project, file, MCP server, skill or subagent is eating their quota, what their usage would cost on the API, whether a habit or update changed their consumption, whether something is using Claude Code in the background or while they were away, or wants a usage report, a week-over-week comparison, a spreadsheet export, or a shareable redacted summary. Questions about the user's OWN tokens, usage, quota or limits—"where did my tokens actually go this week?"—mean this skill and the local Claude Code logs, NOT product analytics, LLM-cost or billing tools (PostHog, Stripe, cloud dashboards), even when such tools are connected. Trigger even if they don't use the word "tare" or "audit"—a complaint about limits is enough.
Use this skill when conducting comprehensive research on any topic using the OpenAI Deep Research API. It automates prompt enhancement through interactive clarifying questions, saves research parameters, and executes deep research with web search capabilities. Use when the user asks for in-depth analysis, investigation, research summaries, or topic exploration.
Assumption Inversion — list the assumptions behind the current approach and flip each one, then ask where the flipped version could actually be true. Use when requirements encode beliefs nobody has questioned, when a design feels inevitable, or when incumbents all share one blind spot. Triggers include "invert", "flip it", "flip the assumption", "reverse the premise", "what if the opposite were true", "challenge the assumption". Do NOT use for analytical work like debugging, code review, or implementation tasks.
Use this as the main Claude Scholar skill for a vault-first, project-scoped Obsidian research knowledge base rooted at Research/{project-slug}/. It owns bootstrap, routing, daily logging, hub/plan/index maintenance, registry updates, lifecycle actions, and lint orchestration.
Forced Analogy / Structural Transplant — map the problem onto a structurally similar system from a distant domain (immune system, air-traffic control, restaurant kitchen, jazz ensemble) and transfer its mechanisms back. Use when a solution works but feels derivative, when the industry playbook is exhausted, or when a system in nature or another trade already solves this shape of problem. Triggers include "analogy", "forced analogy", "how would a hospital/kitchen/airport handle this", "transplant from another industry", "structurally similar system". Do NOT use for analytical work like debugging, code review, or implementation tasks
Generate project status reports from Jira issues and publish them to Confluence. Use when an agent needs to: (1) create a project status report, (2) summarize project progress or updates, (3) generate weekly/daily reports from Jira, (4) publish status summaries to Confluence, or (5) analyze project blockers and completion. Queries Jira issues, categorizes them by status/priority, and creates formatted reports for delivery managers and executives.
Build or refresh a browser-viewable topic graph over Claude session history using local clustering. Use for mapping or clustering sessions, recent or stale topic analysis, or rebuilding/showing the session graph. Unlike wiki-history-ingest, it indexes raw sessions and never writes to the vault.
Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews. Triggers on keywords like: job posting, job application, CV, cover letter, resume, interview prep, job fit, career, application, apply, ansøgning, stilling
Tavily API integration with managed API key authentication. Perform AI-powered web search, extract content from URLs, crawl websites, map site structure, and run research tasks. Use this skill when users want to search the web, extract page content, crawl websites, discover URLs, or conduct in-depth research with citations. For other third-party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and a valid Maton API key.
A topic research tool for Chinese social media. Searches real discussions from the past 30 days across Xiaohongshu, Douyin, and WeChat Official Accounts, and compares public opinion trends across platforms. Use when users want to research Chinese social media topics, analyze public opinion trends, or compare brand reputation. Trigger terms: Xiaohongshu trends, Douyin trends, WeChat Official Accounts public opinion, cross-platform analysis, social media research, topic analysis, public opinion monitoring
Personalized academic writing assistant for university assignments in Chinese and English. Three modes: write new drafts, revise and polish existing drafts to remove AI markers, and learn the user's own style from writing samples. Always writes in plain language with short sentences. Triggers: academic writing, assignment, report, technical analysis, research review, case study, revise, polish, rewrite, reduce AI tone, match my style. | 个性化学术写作助手，适用于中英文大学作业。三种模式：新写、润色改写（降低AI痕迹）、学习用户文风。行文朴素，少用长难句。触发词：学术写作、作业、报告、技术分析、研究综述、案例研究、项目文档、润色、改写、降低AI痕迹、模仿我的文风。
A standard S0 prerequisite skill for larger page workflows such as `hiui-page-workflow`, focused on refining requirements before generating B2B back-office and HiUI pages. Turns vague or abstract back-office, admin, operations, configuration, and approval-flow requirements into actionable product plans, MVP scope, user flows, business rules, traceable page lists, product PRDs, global generation context, page-level prompts, and HiUI handoff packages. Use to clarify back-office product ideas, turn rough requirements into a PRD or product plan, break down list/detail/edit/configuration work areas, define roles and permissions, data permissions, state machines, and audit rules, and, as needed, fill in permission matrices, state transition tables, field dictionaries, exception and audit matrices, bulk/import/export specifications, and legacy-system upgrade and release strategies. It also provides B2B product expertise, including business value analysis, prioritization, trade-offs, multi-tenant/version/provisioning models, master data and system boundaries, anti-pattern detection, and risk alerts—continually turning vague B2B requirements into actionable inputs. For requirements in an existing project or repository, it also refines them in context using the repository’s pages, modules, APIs, types, and documentation.
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, credit the author (people page only when they pass the notability gate), and cross-link. Use when the user shares a link or says "read this", "save this", "think about this"
Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing
DingTalk contact and directory lookup. Use this skill when the user mentions “DingTalk directory,” “find employee,” “search users,” “look up user information,” “get user details,” “user phone number,” “employee name,” “employee ID,” “find department,” “search departments,” “department members,” “department list,” “department details,” “child department,” “parent department,” “department path,” “total employee count,” “directory search,” “userId to unionId,” “unionId to userId,” “dingtalk contact,” “dingtalk directory,” “find user,” “get user info,” or “department members.” Supports all directory operations, including searching users/departments by keyword, retrieving complete user information (name/phone/employee ID/department/title/unionId), getting department member lists and department trees, finding a user’s department path, and counting total employees.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases
Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dashboards. Use when facing significant choices requiring systematic analysis. Supports multiple cognitive styles and output formats.
Decision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network and reputation signals, red flags, conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica) as workhorses; optional BYOK MCPs enhance coverage. Use when the user asks for background research, diligence, or meeting prep on a specific entity (e.g., 'prep me for a meeting with [person/company]', 'due diligence on [company]'). Honors sensitivity exclusions for journalism + personal-vetting contexts
Warren Buffett's thinking framework and communication style. Based on in-depth research into over 60 years of primary sources, including shareholder letters, annual meeting records, detailed interviews, and authorized biographies, it distills 6 core mental models, 8 decision-making heuristics, and a complete communication profile. Use as a thinking advisor to analyze problems, examine decisions, and provide feedback from Buffett's perspective. Use when the user mentions "用巴菲特的视角", "巴菲特会怎么看", "巴菲特模式", or "Buffett perspective". Trigger even if the user only says "帮我用巴菲特的角度想想", "如果巴菲特会怎么做", or "切换到巴菲特"
Edward de Bono's Provocation (Po) technique — state something deliberately wrong or absurd about the problem, then extract useful "movement" from it instead of judging it. Use when a constraint feels unbreakable, when every design converges on the same shape, or to escape "the way it's always done". Triggers include "provocation", "po", "absurd statement", "deliberately break the rule", "the constraint feels unbreakable", "sacred cow". Do NOT use for analytical work like debugging, code review, or implementation tasks
Generates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake (syllabus input format + course audience + year range) plus a grouping forcing-options checkpoint before any search runs — so the reading list matches the course's level and recency need. Parses the syllabus to extract topics and learning outcomes, searches Consensus for recent peer-reviewed papers per topic, and produces a professionally formatted .docx with clickable Consensus links, plain-language summaries calibrated to audience level, and Bloom-higher-order discussion questions tied to course learning goals. Use when the user uploads a syllabus, course outline, or curriculum document and wants supplementary readings (e.g., “create a reading list from this syllabus,” “find recent papers for my course”) — even casual mentions with a syllabus attached should trigger this skill
Edward de Bono's Concept Fan — climb from the current solution to the concept it serves by asking "what is this a way of doing?", then fan out alternative concepts and concrete implementations for each. Use when the current solution might be answering the wrong question, when all options look like variations of one idea, or to widen a decision before committing. Triggers include "concept fan", "zoom out", "what is this a way of doing", "wrong problem", "widen the options", "abstraction ladder". Do NOT use for analytical work like debugging, code review, or implementation tasks
Write and maintain knowledge base articles from resolved support issues. Use when a ticket is resolved and the solution should be documented, when updating existing KB articles, or when creating how-to guides, troubleshooting docs, or FAQ entries.
Search the latest Amazon policies, regulations, and news. Supports paginated searches of news by marketplace and time range (with AI-generated Chinese summaries), and retrieves full article text by record ID. Trigger this skill when users mention Amazon policies and regulations, seller compliance announcements, platform rule changes, policy alerts, FBA/fee policy updates, multi-marketplace policy developments, original policy text, or news details, as well as Amazon policy feed, seller compliance, policy changes, or regulation alerts. Also trigger it whenever users need official Amazon policies, regulations, or news for sellers, and their original text, even if they do not explicitly mention “policies and regulations.”
Podcast knowledge workflows powered by Podwise CLI: search podcasts and episodes by keyword, monitor followed shows for new releases, find popular episodes, ask questions and extract insights from transcript content, process Podwise episode URLs, YouTube videos, Xiaoyuzhou links, and local audio or video files to retrieve transcripts, summaries, chapters, Q&A, mind maps, highlights, and keywords — plus catch up on your backlog, refine your listening taste, generate weekly recaps, export episode notes to PKM tools, research topics across podcasts, debate episode ideas, and generate language learning cards. Use when the user wants to find, summarize, transcribe, or extract insights from any podcast or audio content, or manage their listening library.
Interact with Google NotebookLM (notebook.google.com) notebooks — chat with the AI, generate artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables), manage sources (add URLs, YouTube, files, text), run research (fast/deep web research), and manage notes. Use whenever the user mentions NotebookLM, a notebook.google.com URL, audio overviews, or wants to query, create content from, or manage their notebook sources — even if they don't say "NotebookLM" explicitly.
Build Google Chat bots and webhooks with Cards v2, interactive forms, and Cloudflare Workers. Covers Spaces/Members/Reactions APIs, bearer token verification, and dialog patterns. Use when: creating Chat bots, workflow automation, interactive forms. Troubleshoot: bearer token 401, rate limit 429, card schema validation, webhook failures.
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.