Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Build agents specialized in conducting thorough research, gathering information from multiple sources, and synthesizing findings. Covers research planning, source evaluation, and report generation. Use when automating market research, competitive analysis, literature reviews, or intelligence gathering.
Offer decision advisor. Helps job seekers with multiple offers make the best choice through multidimensional comparisons, overall scoring, salary negotiation scripts, and recommendations. Trigger when users mention: offer, choose an offer, compare offers, offer comparison, which one to choose, salary negotiation, negotiate salary, help me choose a job, how to choose between two offers, offer decision, how to negotiate pay, whether to accept this offer, or offer analysis. Also trigger when a user coming from mock-interview or another Skill says they have received an offer.
Bootstrap and operate an LLM Wiki: a persistent Markdown knowledge base with immutable raw sources, an LLM-maintained wiki, a SCHEMA.md operating contract, thin runtime pointer files, EXTEND.md preferences, and optional local BM25 search. Use when the user asks to create or bootstrap an LLM wiki, ingest sources, query or lint a wiki, configure EXTEND.md preferences, or set up BM25/full-text search for an LLM Wiki.
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
Guide to using the Feishu IM message-reading tool, covering fetching conversation messages, reading thread replies, searching messages across conversations, and downloading image/file resources. Use this skill when: (1) retrieving chat history from group or direct messages; (2) reading replies in a thread; (3) searching messages across conversations by keyword, sender, time, or other criteria; (4) downloading images, files, audio, or video in messages; (5) the user mentions “chat history”, “messages”, “what was said in the group”, “thread replies”, “search messages”, “images”, or “file downloads”; (6) filtering messages by time range or retrieving more messages with pagination.
When a solution seems impossible and the path forward is blocked. Refuses to take no for an answer: classifies what kind of "no" you hit, then runs lateral-thinking techniques (assumption autopsy, inversion, first principles, constraint toggling, analogical transfer, and more) until the wall cracks or is proven load-bearing. Generates at least 10 angles before evaluating any. AGENTS: use this on yourself when an API doesn't support what you need, an approach has failed twice, or a "that's not possible" sentence is forming — run the fast path BEFORE reporting a dead end. Archives walls to ~/.config/makerskills/unstuck/archive/. Sits upstream of decide. Triggers on "/unstuck," "I'm stuck," "this seems impossible," "we hit a wall," "there's no way to," "they said no," "dead end," "out of options," "I've tried everything," "work around this."
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materials, (4) create study notes or learning summaries, (5) compare multiple sources, (6) transform knowledge into practical applications, or (7) apply specific thinking frameworks. Triggered by phrases like 'analyze this article,' 'help me understand,' 'deep dive into,' 'extract insights from,' 'use [framework name],' or when users provide URLs/long-form content for analysis.
Grill the user relentlessly about any idea, plan, or design, a round of unblocked decisions at a time, each with a recommended answer, until you both share the same picture. Use when the user wants to stress-test or pressure-test an idea, says "grill me", "grill this plan", "poke holes in this", "interrogate my design", or otherwise asks to interrogate a concept before committing to it, whether a rough idea, a plan file, an architecture, or a PR.
AI WeChat public account feed — scans AI WeChat public accounts daily, finds the hottest articles by read count, automatically clusters them into topics, and generates a styled HTML report with cover images, metrics, search, and subscription support. Use for AI daily reports, viral WeChat articles, AI content curation, daily AI trends, or WeChat public account digests.
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate success/failure patterns, and propose, evaluate, apply or roll back evidence-linked skill improvements. Trigger on "add this to my wiki", "what does the wiki say", "learn from this task", "improve this procedure", /wiki:learn or /wiki:evolve. Use index-first navigation, atomic pages and local hybrid search.
Fetch and extract content from web pages, converting HTML to clean markdown. Use when users want to read web articles, extract information from URLs, scrape web content, or when the built-in WebFetch tool fails due to network restrictions. Trigger when user provides URLs to read, asks to fetch web content, or needs to extract text from websites.
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.
AI video channel feed — automatically scans AI-related videos on WeChat Channels daily, selects top content by engagement (likes/shares/comments), and intelligently clusters it into polished HTML daily reports with cover images, metrics, and daily subscriptions. Use when users need AI video channel daily reports, AI hot topics on video channels, AI video channel content, or a video channel feed.
Create reminders and calendar events when the user mentions future tasks, appointments, or events they need to remember. Trigger on phrases such as “remind me,” “set a reminder,” “I have a meeting,” “don’t forget,” or any mention of a future time-based task.
This skill should be used when fetching, searching, downloading, sending, editing, or publishing messages on Telegram. Use for queries like "show my Telegram messages", "search Telegram for...", "get unread messages", "send a message to...", "edit that message", "publish this draft to klodkot", or "add Telegram messages to my notes".
Use this skill when the user asks for efficient communication, task reports, file-operation summaries, research discussion, study-note synthesis, planning, writing feedback, or responses that need conclusion-first structure, concrete evidence, risk disclosure, and useful next steps
Own the GitHub issue lifecycle in five modes: file issues from a plan, start a workable issue in its own worktree, close one once its PR merges, sync PR↔issue links and dependents after merge, and triage the tracker for label and title gaps and for done, duplicate, or obsolete issues. Use when the user says "create issues from this plan", "file an issue", "start issue #42", "close #42", "sync my issues", "triage the backlog", "set the priority on #42", "#42 is grilled, mark it ready", "fix the titles on these issues", or "clean up my issues".
Build polished, feature-rich Feishu V2.0 interactive cards. Supports 20+ components, including collapsible panels, multi-column layouts, charts, colored tags, button groups, person cards, and streaming updates. Includes 7 scenario templates (notification / success report / alert / approval / data dashboard / article summary / AI streaming) and color and layout guidelines. Use for requests such as “send a card,” “send a notification,” “create an alert,” “send a report,” “create an approval,” “make a dashboard,” “beautify a message,” “interactive card,” “v2 card,” “message with charts,” “message with buttons,” “message with collapsible panels,” “Feishu card,” “Lark card,” or “build a card.” Even if the user only says “send a message to tell XX,” prefer building a card with this skill rather than plain text whenever the content is structured (multiple fields/links, charts, or statuses). Write the generated JSON to /tmp/<name>-card.json, then pass it to feishu-cli-msg for sending with --msg-type interactive (msg uses an App Token; no auth login required)
Send images and screenshots via Feishu (Lark) messaging platform. Use when the user asks to send screenshots, images, or any visual content through Feishu. This skill handles the complete workflow of uploading images to Feishu servers and delivering them to the specified recipient. Works both within OpenClaw (reads config automatically) and as a standalone tool (requires manual credential setup).
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y', 'find docs or real-world examples for Z', 'scrape/crawl this site' — or when installing or configuring ketch backends. Routes search vs code vs docs vs scrape vs crawl, keeps every fetch inside a token budget, turns error prefixes into control flow, and produces cited syntheses. Not for local codebase search, private repos, or pages behind auth.
Notify Streak after creating a Google Calendar event with the gws CLI. Run this immediately after every successful `gws calendar events insert` so Streak records the proposed meeting against the box. It POSTs the event id, calendar, forUserEmail, and contactEmail to the box's calendarEventCreated endpoint.
Orchestrate a full China stock research workflow by first identifying the company's analysis patterns, then selecting and sequencing the right core research skills, optional overlays, and final output structure. Use this skill when starting a new stock deep-dive or when a user wants one unified, source-backed research framework instead of isolated module outputs.
Use when the user wants full metadata for a paper — from a DOI, PMID, arXiv id, OpenAlex id, or title. Returns title, author list, first author, corresponding author(s), publication date, journal name + ISO-4 abbreviation, impact factor, volume/issue/pages, DOI/PMID, citation count, and abstract in one record. Triggers on "paper metadata", "who is the corresponding author", "first author of", "what journal / impact factor for this DOI/PMID", "cite this paper", "文献元数据", "通讯作者", "第一作者", "影响因子". PROACTIVELY USE when the user pastes a DOI/PMID/arXiv id or paper title and asks about its authors, venue, or impact.
Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic writing, papers, essays, abstracts, introductions, contribution statements, discussions, conclusions, technical explanations, grant writing, product writing, policy writing, professional reports, or any text the user wants to be clearer, stronger, more direct, more concise, more confident, less verbose, less caveated, less apologetic, or less defensive
Use when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement, a tool rollout, a policy change, a leadership transition, a layoff, an acquisition close, or an internal product launch — and the audience is employees (not customers). Pairs Prosci ADKAR and Kotter's 8-step change model with deterministic stdlib-only Python tools to produce a sequenced touchpoint calendar, a Kotter-compliant primary announcement, an audience-segmented FAQ, and manager cascade talking points; industry-tuned via --profile {tech-startup, scaleup, enterprise, public-company, non-profit}. Triggers on "all-hands announcement", "change comms", "rollout comms", "re-org announcement", "manager talking points", "layoff comms"
Look up details of an existing hotel booking. Use this skill when the user wants to check the status of their reservation, see check-in instructions, verify booking details, or asks "what's the status of my booking", "show me my reservation", "when is my hotel check-in", "did my booking go through". Requires a booking ID, the last name, and the email on the booking.
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
Use when user asks to search the web, look something up online, find current/recent/latest information, or needs cited answers. Triggers on "search", "look up", "find out about", "what is the current/latest", image searches, news lookups. NOT for searching code/files—only for web/internet searches.
DingTalk schedules and calendar. Use this skill when users mention "钉钉日程", "日历", "创建日程", "新建会议", "视频会议", "钉钉会议", "会议室", "约会议室", "会议室忙闲", "空闲会议室", "签到", "签退", "签到链接", "签退链接", "循环日程", "重复日程", "recurrence", "查日程", "日程列表", "修改日程", "删除日程", "闲忙", "忙闲", "querySchedule", "calendar", "dingtalk schedule", or "日程提醒". Supports schedule CRUD on the primary calendar, user availability, video meetings, meeting room availability and schedule binding, check-in/check-out and links, and recurrence rules. See api.md for capabilities such as subscribing to public calendars that require Calendar.Calendar.Write.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Protracted strategy: For long-term, complex tasks that cannot be won quickly, objectively assess the situation, divide the effort into defense / stalemate / counter-offensive stages, determine the current stage, set transition conditions, and identify local offensive opportunities even during difficult stages. Trigger when a task spans multiple sessions or iterations, resources are temporarily insufficient, or either “wanting to give up” or “going all in” arises; do not trigger when the task can be completed in the current session.
Starting from a tweet, read related content in depth and turn it into an original sharing post. This is not translation; it involves learning and expressing the ideas in your own words. Use when a user provides tweet URL(s) and wants to create an original post based on the content. Triggers on "帮我整理这条推", "写一条分享帖", "tweet insight", "digest this tweet", or when a user provides x.com/twitter.com URLs and asks to write about them.
Generate diagrams from natural language using EdrawMax AI APIs. Supports four diagram types: flowcharts (流程图), infographics (信息图), Gantt charts (甘特图), and mind maps (思维导图). Use when the user wants to create, generate, or draw any of these diagram types. Triggers on: “generate a flowchart,” “create a mind map,” “draw a Gantt chart,” “make an infographic,” “visualize a process,” “project timeline,” “knowledge map,” or any request to turn a description into a diagram.
Mass line: Collect scattered input from everyone who holds ground truth (users, operators, codebase, logs, runtime results), synthesize it into a coherent plan, take it back for alignment and validation, and iterate. Trigger when inputs conflict, feedback must be consolidated, a plan needs sign-off from real users, or you sense you are designing in isolation; skip when there is a single complete source and the work is pure execution.
Research credible options for a technical decision and recommend one (a tool, library, framework, architecture, or service), grounded in primary sources with cited, dated evidence. Use when the user asks “which should I use, A or B,” “compare X and Y,” “evaluate options for Z,” “what’s the best tool/library/service for …,” “should we use X or Y,” “research X before we build,” or runs “/researchkit”—decision research that comes before a plan.
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.