Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
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)
Godot expert auditor: Aurelius. Exhaustive never-list enforcement and architectural slap-down for Godot 4.7 projects. Use when auditing signal decay, ObjectDB orphans, typed Array/Dictionary slop, material.duplicate batch breaks, export case-sensitivity, Expression.execute risks, or sector never-lists. Keywords: auditor, Aurelius, never-list, signal decay, ObjectDB orphans, typed Array, export case-sensitivity, instance uniforms, PackedScene.get_state.
Translate legacy HelixDB HQL (.hx QUERY/RETURN syntax) into direct published v3 Rust or TypeScript SDK requests. Use when the input contains HQL concepts such as typed node, edge, or vector sources; AddN/AddE/AddV; Out/In/OutE/InE; FromN/ToN; WHERE/EQ/GT/EXISTS; SearchV/SearchBM25; GROUP_BY/AGGREGATE_BY; ORDER/RANGE; UpsertN; RerankRRF; ShortestPath; Embed; or .hx files. Flags HQL features with no v3 DSL equivalent. When the target is Helix Cloud, always use helix-mcp first.
Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange. Anonymous NTLM Type-2 challenge capture leaks NetBIOS domain, internal DNS forest, computer name, AD timestamp via AV_PAIRS structure. Default Windows-installer hostnames (WIN-XXXXXXXXXXX pattern) signal lazy provisioning. Use when target advertises `WWW-Authenticate: NTLM` or `Negotiate` headers anonymously
Generates Insomnia collection export files from Express, Next.js, Fastify, or other API routes. Creates organized workspaces with request groups, environments, and authentication. Use when users request "generate insomnia collection", "export to insomnia", "create insomnia workspace", or "insomnia import"
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPC_EXT/DPC_EXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this gateway service for S/4", or "replace SEGW with RAP V4".
For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics. Users provide source copy, story beats, or a core concept and may specify aspect ratio, duration, palette, and audio needs. The Skill extracts meaning, proposes visual metaphors, prepares a production plan and storyboard, generates approved halftone collage stills, then creates stop-motion clips with paper movement and tactile sound effects, with optional final assembly. By default it keeps collage SFX and does not add BGM, voiceover, or subtitles unless requested. Best for explainers, viewpoints, story visuals, and social B-roll; not for presenter ads, editable layers, complex typography, or prompt-only tasks.
For creators explaining science, education, or general knowledge through tactile handmade papercraft visuals. Users provide a topic, core knowledge points, or source material and may specify audience, duration, aspect ratio, and deliverable type. The Skill extracts the learning goal and visual metaphor, proposes creative directions, designs paper characters, layered diorama sets, and props, creates preview concepts plus image and video prompts, and plans storyboards, camera movement, transitions, and sound with staged approvals and review checklists. It outputs a production-ready papercraft stop-motion explainer package, or selected assets such as still prompts, image-series prompts, short-video prompts, or storyboards. Best for cut-paper, pop-up-book, layered diorama, and miniature stop-motion explainers; not for standard 2D cartoons, line doodles, live action, or explainers without a paper-art look.
Create, edit, comment on, share, and run human-in-the-loop iteration loops over markdown documents via Proof's web API. Use when asked to "proof", "share a doc", "create a proof doc", "comment on a document", "suggest edits", "review in proof", "iterate on this doc in proof", "HITL this doc", "sync a Proof doc to local", when a caller needs an HITL review loop over a local markdown file (e.g., ce-brainstorm, ce-ideate, or ce-plan handoff), or when given a proofeditor.ai URL. Prefer this skill for any workflow whose output is a Proof URL or that uses a Proof doc as the review surface, even when not named explicitly.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Audit a backlink profile using Ahrefs MCP data: profile health, anchor text distribution, toxic link identification, lost link reclamation, and gap analysis against competitors. Use this skill when reviewing backlink health, scoping a disavow project, recovering from a manual action, planning link building, or doing M&A due diligence on a property's link equity. Triggers on backlink audit, link profile, toxic links, disavow, anchor text analysis, lost links, link reclamation, referring domains, link gap. Also triggers when traffic decline correlates with link loss or when an unnatural link warning appears in Search Console
The meta skill. Turns any raw feature into a properly skilled, tested, resolvable unit of agent capability. Idempotent: running it on an existing skill improves it (bug fix, new input, quality pass) instead of starting from scratch. Every skill declares an EVAL CONTRACT (its goal + skill-specific dimensions + hard-fails) so the cross-modal eval judges THIS skill's real purpose, not generic slop. Cross-modal eval runs BEFORE tests: 3 frontier models from different providers critique the output against the contract; you iterate to quality, THEN write or update tests that lock in the proven-good behavior. NO-REGRESSION LAW: any edit to a skill must score >= the previous iteration's eval — forward only, never back. For skills that back a scheduled job, an edit MUST re-run a representative task and eval it before shipping.
Rewrite AI-sounding text so it reads like a clear, careful person wrote it, using the “80% of the way to ASD-STE100” method that Andrej Karpathy shared. Pass 1 removes the 26 AI tells from Wikipedia's “Signs of AI writing” (not-X-but-Y, one-line closers, forced triads, dashes everywhere, stock AI words, inflated claims, chatbot residue). Pass 2 rebuilds the text with the structure of Simplified Technical English: one idea per sentence, short sentences, active voice, simple tenses, plain words. Use it whenever the user wants text humanized, de-AI'd, made clearer, simpler or less robotic, asks for ASD-STE100 or STE, or wants docs, READMEs, emails, posts or answers tightened.
Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.
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.
Sveltia CMS, a Git-backed content management system and successor to Decap/Netlify CMS. 5x smaller bundle (300 KB), GraphQL performance, and 260+ issues solved. Use for static sites (Hugo, Jekyll, 11ty, Gatsby, Astro, Next.js), blogs, docs, i18n, or when encountering OAuth errors, TOML/YAML issues, CORS problems, or content listing errors
Guide for implementing Angular Accordion components for collapsible content panels, expandable sections, FAQs, multi-step wizards, step-by-step forms, navigation menus, or tabbed navigation. Use this skill when users mention expanding or collapsing content, accordion layouts, step-by-step workflows, or hierarchical content organization. This skill covers initialization, expand modes, data binding, dynamic loading, animations, nested accordions, and real-world patterns.
Guide for implementing Syncfusion Angular Breadcrumb components for navigation trails. Covers installation, data binding, navigation setup, icons, overflow modes, and template customization. Use this when building breadcrumb navigation that displays user location in hierarchies, enables clicking parent items for navigation, adds icons for visual context, or customizes appearance with templates.
Systematic chart reading and technical analysis for NSE/BSE Indian equities. Covers trend identification, support/resistance mapping, volume analysis, indicator dashboards, and probabilistic scenario building. Uses Groww MCP for live data and yfinance for history. Use when the user asks to: read a chart, identify trends, find support/resistance levels, check indicators (RSI, MACD, Bollinger, ADX, Stochastic), analyze volume, or build trade scenarios. Triggers on: “what's the trend on [stock],” “support resistance for [stock],” “indicators for [stock],” “is [stock] bullish or bearish,” “volume analysis,” “chart analysis,” or any request to interpret price action on Indian equities.
Use when working with The Open Network (TON) blockchain, or when the user mentions TON-ecosystem terms the agent may not recognize—such as Tact, FunC, Tolk, Fift, TL-B, TVM, cells, BoC, Jettons, TEPs, TON Connect, workchains, shardchains, or liteservers. Provides a docs-first workflow for fetching and navigating TON documentation accurately, and covers smart contract development, transaction mechanics, wallet standards, token standards, Telegram Mini Apps, and infrastructure.
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows. Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or a single photo of a person/product anchored into the collage (C-roll mode). Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video", "turn my photo/this product shot into a collage video".
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the Agent Observability SDK", or has `ddtrace` installed and wants idiomatic SDK code.
How humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.
Illustrate an article (Markdown, HTML, etc.) with animated-style icons from itshover.com/icons. Fetches icons as clean inline SVG and places them at section headings, key concepts, lists, and callouts. Triggers on: /article-icons, 配图, 给文章配图标, add icons to article, illustrate with icons.
BYMA market data via public API: leading stocks, CEDEARs, sovereign bonds, LECAPs/BONCAPs, corporate ONs, repos, options, and SENEBI. Historical OHLCV data for instruments and indices (MERVAL, BURCAP). Bond fact sheets with amortization schedules. No API key.
CesiumJS primitives and geometry - Primitive, GeometryInstance, Appearance, BufferPrimitive collections, GeoJsonPrimitive, Billboard/Label/PointPrimitive collections, built-in geometry shapes, ground primitives, classification. Use when rendering performance-critical static or vector geometry, loading GeoJSON without entities, creating custom shapes, batching draw calls, or using low-level collections
For users creating a two-player co-op game menu or opening animation. Users provide two player names, a game title, a target visual style, and optional character reference images. The Skill locks identity cues, generates an approval image from a fixed menu framework with coordinated color, buttons, icons, and typography, then uses the approved result to rebuild the character, UI-copy, and event timing instructions for the final video. It outputs a co-op game intro featuring two characters, player cards, and menu interaction motion. Best for game concepts, character-led menus, and social content; not for playable game development, complex multi-page UI, exact brand-logo replication, or generic character-free title sequences.
Generate a Fiori Elements V4 LROP app (list report + object page) driven by @UI.* annotations on a V4 RAP service, using the Fiori MCP server's 3-step (list_functionalities → get_functionality_details → execute_functionality) workflow. Use when asked to "build a Fiori Elements app", "generate LROP from this V4 service", "convert to annotation-driven UI", or "scaffold Fiori Elements V4".
Converts Figma/design specifications into production-ready UI components with accurate spacing, typography, color tokens, responsive rules, and interaction states (hover, focus, disabled, active). Generates Tailwind/shadcn code with design system tokens mapping. Use when translating "Figma to code", "design specs to components", or "implement design system".
Derive a project's design system from the UI it already ships and keep it true as the code moves, producing a spec-compliant DESIGN.md at the repo root, validated by the official linter. Use when the user says "write a DESIGN.md", "document our design system", "extract our design tokens", "our design system is out of date", "audit our design tokens", "what colors does this project actually use", "sync DESIGN.md to our Tailwind theme", or "/designkit".
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.
General-purpose diagramming tool using drawio XML format with 8,900+ stencils. Best for custom diagrams requiring pixel-perfect positioning, diagrams with vendor-specific icons (AWS, Azure, Cisco), or diagrams not covered by specialized skills. Use the network skill for network topology, uml skill for UML diagrams, and architecture skill for layered system views. Not for simple flowcharts (use mermaid) or data-driven charts (use vega)
Surface a Factorial Code process as a button inside the Factorial product UI — the `factorial.uiTrigger` settings in a process's metadata.json (location id, label, icon; `awaitResult` at the block's top level) and the legacy `uiTrigger` block they replace, what the process receives when a user clicks, what a synchronous trigger returns, form-backed triggers and their file uploads, i18n labels, the icon allowlist, and how Factorial's `FactorialCodeTrigger` component renders them. Use when an app process should appear as an action button on a Factorial page, or when wiring the button entry point of a Factorial Action ("Trigger from Factorial" in the console)
Use when the user wants to plan, evaluate, or build a free tool for marketing purposes—such as lead generation, SEO value, or brand awareness. Also use when the user mentions “engineering as marketing,” “free tool,” “marketing tool,” “calculator,” “generator,” “interactive tool,” “lead gen tool,” “build a tool for leads,” or “free resource.” This skill bridges engineering and marketing and is useful for founders and technical marketers
Use this skill to search live software / tech / data / engineering job listings across many countries and markets (and remote) via the freehire.me aggregator's public API, or to look up a specific posting. It aggregates roles from ~50 ATS platforms into one schema, so a single skill covers many markets — but its faceted filtering (skills, category, seniority) is tuned tech-first, so scope triggers to technical roles. Trigger phrases: find a tech job, software job search, developer jobs, engineering vacancies, data/ML jobs, DevOps roles, remote developer jobs, "are there any <tech role> jobs in <place>", look up this freehire job posting
Write and revise queries with the published HelixDB Rust SDK (`helix-db = "3.0.0"`). Use for `read_batch`, `write_batch`, `#[query]`, direct `QueryRequest` values, traversal builders, projections, indexes, vector and BM25 search with traversal-scoped prefiltering, structured remote errors, and `Client::query`. Inspect local labels, edges, properties, and existing query patterns before inventing code. Stored routes, registration, and query bundles are not v3 SDK APIs. When the target is Helix Cloud, always use helix-mcp first.
Designs iOS 18+ SwiftUI experiences with real taste — starting from user goals, not pixels. Use this skill whenever the user asks you to build SwiftUI views, screens, or experiences. Trigger when the user says "build a settings screen", "create a detail view", "design this properly", "I want this to feel like a native app", or any SwiftUI UI task. Also trigger when reviewing SwiftUI code for design quality, or when the user says the output "looks like a demo" or "feels generic." When building any user-facing SwiftUI view, lean toward triggering this skill.
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.