Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
For creating independent mind maps with content and reading or writing topics, use dws mind; blank mind maps use wiki, and built-in mind maps in meeting notes use minutes. Covers creating, drawing, saving, and editing standalone DingTalk whiteboards (whiteboard files); embedded whiteboards in documents support graphic-content read/write only when the host document's nodeId and partId are already available (dws whiteboard). These targets are independent; do not infer or switch between them. Whiteboard card containers in documents are outside this skill. A long-tail product collection skill covering less frequently used DingTalk products: OA approval queries and processing, legal smart contracts, attendance, livestreaming, DING urgent messages, Open Platform apps and MCP development, Agoal goal management, logs and daily/weekly reports, spreadsheets, Open Platform document search and OpenAPI escape hatch, DWS skill-market installation, organizational brain Hrbrain, native Markdown, native HTML, PAT action authorization, and multi-organization profiles. Use when users mention any of these products, especially Agoal, goal management, strategy decoding, business agreements and field configuration, scorecards, OKR, goal rules and cycles, personal goals, goal templates, weekly/monthly report rule submission statistics, on-time/late/missing submissions or follow-up; querying or creating contract ledgers, bulk importing contracts, drafting contracts from meeting notes, archiving contracts, managing contract projects/counterparties/accounts; pending approvals or approving/rejecting/transferring/withdrawing approvals; clocking in, scheduling, filling daily/weekly reports; creating standalone whiteboards with content or reading/writing their nodes; reading/writing embedded whiteboard graphics with existing nodeId and partId; cell read/write; searching for or installing skills; developer-console or enterprise apps; checking app status or whether it can be deleted; app member and role summaries; app version history; enterprise app bot configuration, message mode, or online status; local bot connectors; Stream connections; MCP services or tools; publishing or debugging MCP; searching the MCP marketplace; accessing or invoking published MCP; turning OpenAPI, Swagger, Postman, curl, or HTTP interfaces into MCP or making them usable by an Agent; unwrapped OpenAPI; llms.txt; dws api; talent pools, employee profiles, career histories, performance; native .md files, Markdown version comparisons, local draft diffs, Markdown comments; native .html files, creating HTML pages; PAT authorization; switching organizations; cross-organization profiles, and related operations. Filling in weekly/monthly report content belongs to report; rule-level on-time, late, and missing submission statistics and follow-up belong to Agoal; daily, weekly, or briefing submissions with approvers, CC recipients, or an approval flow belong to OA approval. Real-time monitoring of future approval-task or instance changes is outside this skill; use dingtalk-event. Once matched, use this skill's “product index table” to identify the specific subproduct and command prefix, then follow that subproduct's instructions.
Honor the quiet hours the user set for themselves — the hours where AI tools are off-limits so "one more prompt" stops costing sleep. Enforced as refused tool calls where hooks exist, advisory everywhere else, with a deliberate logged override path. Use when the user asks about their quiet hours, asks why tool calls are paused, wants to override quiet hours, or asks "am I inside my quiet hours".
Enforce the sessions-per-day ceiling the user set for themselves — count sessions honestly, refuse new ones past the limit with the same terse message every time, and make raising the limit a deliberate, logged act. Use when the user asks "how many sessions have I used", "am I at my limit", "raise my session limit", "limits report", or asks why a session was refused.
Tacit knowledge mining: extract users’ “hard-to-articulate” judgment criteria through structured conversations. Based on Polanyi’s tacit knowledge theory and CDM/Laddering/Repertory Grid methods. Triggers: mine tacit knowledge, in-depth interview, get to know me, discuss my ideas, tacit, you don’t know me well enough, I want you to understand me better, dig deeper. Should not be triggered by writing or publishing instructions such as “write an article,” “reporting,” or “formatting.”
Configure and verify a Windows 11 PC for macOS-like Logitech keyboard shortcuts, virtual-desktop switching, cross-monitor window movement, and natural scrolling. Use for reproducing or repairing this specific setup without stacking conflicting remappers.
Use this skill when a designer needs to prepare for a business kickoff workshop with a new customer, or needs to fill a Business Model Canvas after the call. Triggers when someone mentions a kickoff call, BMC workshop, business model canvas, or needs to prepare questions for a new customer discovery session.
Query Feishu attendance data (user-task / user-stats). user-task checks clock-in tasks/shifts; user-stats checks attendance statistics (attendance/late arrivals/early departures/leave). Note: Only Tenant Token is supported; SDK v3.5.3 does not accept User Token. Each query is limited to 31 days; longer ranges are rejected. Use when the user asks to “check attendance,” “check clock-in records,” “attendance statistics,” or “attendance details.”
Query Feishu OKRs and report progress. `okr cycle list` lists tenant-level OKR cycles; `okr progress list/create` queries or creates progress records. Note: The API requires the `source_url` field; the default placeholder `https://www.feishu.cn/okr/progress` can be changed. Uses SDK Okr.ProgressRecord + direct HTTP calls to v1/periods (v2/cycles does not exist). Use when the user asks to “check OKR cycles,” “report OKR progress,” or “update OKRs.”
Run a health check on existing memory (the wiki substrate) and goal artifacts. Use this when the user wants to lint the wiki, health-check the knowledge base, find orphan pages, spot broken or missing cross-links, clean up stale claims and unresolved wikilinks with safe local fixes, consolidate a legacy root `overview.md` into `index.md`, or health-check goal artifacts. Not for adding new material; use /loam::adding-to-memory or /loam::learning-from-session for that.
Send reminders and messages to Telegram with cloud-based scheduling. Use when the user wants to send immediate messages or schedule future reminders to Telegram. Supports text messages, timestamp-based scheduling, recurring reminders, viewing and canceling scheduled messages, and message history.
Draft mid-contract messages to a freelance client on Upwork or similar platforms. Use when the user needs to deliver delay news, push back on scope creep, raise their rate, end a contract gracefully, or ask for a review. Triggers include "reply to my client", "tell the client it's delayed", "client keeps adding scope", "raise my rate", "end this contract", "ask for a review", and "client is ghosting". Input is the situation plus the relevant thread context, pasted. Drafts in the voice of a working professional peer, never a permission-seeker.
Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.
Use when you need Azure DevOps CLI guidance to verify installation, configure organization and project context, discover work item IDs by optional WIQL filters, and execute safe work-item create/update operations. Uses an interactive install gate - if `az` or the Azure DevOps extension is missing, ask whether to show installation guidance before any work item commands. This should trigger for requests such as Azure DevOps work item list; List Azure Boards work item IDs; Azure DevOps WIQL query; Azure DevOps CLI planning workflow. Part of Plinth Toolkit
Quickly capture a thought, fact, or reminder into Basic Memory as a lightweight note. Use when the user says "remember that…", "note this", "save this to memory", or runs /basic-memory:bm-remember. For quick deliberate capture — not full decision or session records.
Use when the user asks for "deep research", a "research report on", a "comprehensive analysis of", to "look into X in depth", to "write a report on X", or any question needing multi-source synthesis beyond a single search — an autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop. The LLM drives every decision: what to search, what's relevant, what's missing, and when to stop. Produces a cited, magazine-quality report with inline citations, category-specific formatting, and research stats. For entity vetting/dossiers use entity-research; for news digests use news-monitoring; for source-grounded Q&A use notebooklm-mode.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Compose, verify, and send concise ImmoScout24 landlord contact messages when the user is already logged in on ImmoScout24 and wants to contact one or more rental listings. Use for German rental listing outreach, landlord/broker message templates, profile-based apartment introductions, and troubleshooting ImmoScout24 contact form automation. Do not use for full portal applications with PDF uploads; use a separate apartment application workflow for that.
Olares search via olares-cli search — the Desktop global search over Drive files, Sync (Seafile) libraries, Google Drive, Dropbox, Wise/Knowledge, and installed applications, with paging and JSON output. On Olares 1.12.7+ one `search drive` (alias `search files`) covers all four file sources. Use for Olares search, full-text search, find a file by content, Text Search, global search, search apps, search google drive, search dropbox, search sync, search wise.
Use this skill when the user asks about “how to research,” “research best practices,” “evaluate sources,” “source credibility,” “academic research,” “find reliable information,” “cite sources,” “research methodology,” or needs guidance on conducting thorough web research and evaluating information quality.
Documents work, decisions, and context from the current session by writing structured entries to `.agents/sessions/YYYY-MM-DD.md`. Triggers on `/start`, `/end`, "document this session", "save session notes", or automatically at session wrap-up to capture decisions, files changed, mistakes, and next steps.
This skill provides tools and techniques for e-commerce website automation. Includes advanced search, product comparison, cart management, checkout process and other common shopping scenarios. Suitable for tasks requiring complex operations on e-commerce websites.
Measure how many hours a person really works per day, per client or project, and at what clock times, from the digital exhaust they already leave — Claude Code transcripts, Slack, WhatsApp, meeting recordings, laptop screen time, browser history and chess games — with leisure subtracted and the idle threshold calibrated against their own stated breaks. Use it whenever someone asks "how many hours do I actually work", "how much time do I spend on client X vs Y", "what are my working hours / routine", "am I overworking", "how much of my day is chess / YouTube", or wants a timesheet reconstructed after the fact. Trigger it even when the word "hours" never appears — "how long are my days", "split my time between customers", "when do I usually start and stop" are this skill.
Read, summarize, or send encrypted X Chat (XChat) DMs via the X plugin MCP plus local chatxdk / xchat_lite.py. Use when the user mentions X Chat, xchat, encrypted DMs, Chat PIN, juicebox, inbox messages, or wants to reply in X Chat. Not for classic unencrypted DMs, posting tweets, or always-on daemons. If chat tools or dm.read/dm.write are missing, tell them to reconnect the X plugin — do not create an app or ask for Bearer tokens.
Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app interaction: list apps/windows, get app state, read visible UI, click controls, type, press keys, scroll, drag, set values, or perform accessibility actions. Also use for browser windows, webviews, Orca app UI, or other desktop UI. Triggers include "computer use", "orca computer", "read Spotify", "read Slack", "control/click/read in a desktop app", and "get app state".
Search for job postings across LinkedIn and Indeed. Use when users want to find open roles, monitor hiring signals, identify companies hiring for specific positions, or research competitor hiring activity. Returns job title, company, location, salary, description, seniority level, and direct apply URLs. No login or cookies required.
MaiMemo (墨墨背单词) Open API skill for vocabulary learning. Handles: vocabulary lookup (voc_id), interpretations (CRUD), mnemonics/notes, notepads/word lists, phrases/example sentences, study data study progress/review schedule/study records. Triggers on: 墨墨, maimemo, 背单词, 释义, 助记, 云词本, 例句, study progress, review schedule, words due, forgotten words, study time, export study data.
Applies structured divergent-convergent thinking to generate many creative options, organize them into meaningful clusters, then systematically evaluate and narrow to the strongest choices. Balances creative exploration with disciplined decision-making. Use when exploring product ideas, solving open-ended problems, generating strategic alternatives, developing research questions, designing experiments, or when user mentions brainstorming, ideation, divergent thinking, generating options, or evaluating alternatives.
Use when an agent needs to operate the user's real Chrome session: listing tabs, snapshotting the page into actionable @refs, clicking, filling, typing into rich editors, pressing keys, evaluating JS, capturing screenshots, and reading console/network buffers. All actions go through CDP and run on backgrounded tabs without stealing focus.
Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject. Supports academic papers (arXiv), technologies, trends, comparisons, and general topics.
Use this skill whenever the user wants Claude to directly interact with their Obsidian vault — reading a note or daily note, writing or appending content, searching vault contents, counting or listing notes, managing tasks, moving or renaming files, finding orphaned notes or broken links. Without this skill, Claude has no way to access vault data or execute vault operations. Treat any request that implies “go into my vault and do X” as a trigger — the user is asking Claude to act, not to explain. Also trigger for vault automation, CLI scripting, or cron-based workflows involving Obsidian, managing sync history, querying Bases, restoring file versions via history, managing bookmarks, or running JavaScript against the Obsidian API. Skip for pure conceptual questions: how Obsidian's GUI works, navigating settings menus, theme or plugin installation via the UI, iCloud/third-party sync conflicts, general Dataview query syntax, keyboard shortcuts, or parsing vault files with external scripts — anything where the user needs an explanation rather than Claude performing a vault operation.
Chinese autumn recruitment job search progress management skill: record and update the status of applications, screening, assessments, interviews, offers, rejections, and recruiting emails, and generate a searchable progress tracker; use when the user types "/offer" or asks to manage autumn recruitment progress.
Yuandian legal search and curated reports. Use when querying Chinese laws and regulations, cases, or finding authorities related to case issues. Prefer calling the available Yuandian MCP directly; use the API when MCP is unavailable. Provides lightweight issue understanding, filters out unsuitable candidates, and generates traceable reports as needed. Do not use as a substitute for full evidence review, litigation strategy, or formal legal advice.
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.