Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Bulk extraction of videos from TikTok profile pages — enter a TikTok profile link/handle and automatically pull all posts from the account's profile and parse watermark-free download links, supporting one-click bulk download to local storage. Use cases: breaking down and frame-by-frame studying competitor account content, saving all works of favorite creators to avoid deletion, bulk sourcing material for secondary editing and creation, saving your own account's works as a local backup against loss, stockpiling course/tutorial videos offline for repeated viewing, providing watermark-free source files when a client requests them, and quickly pulling a creator's works for background research before a collaboration. Trigger words: TikTok profile download, TikTok video download, TikTok bulk download, TikTok watermark-free download, download TikTok works, TikTok account video extraction, bulk extraction of TikTok profile videos, TikTok watermark removal, TikTok video backup, competitor video download.
Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat). Covers ingesting single-sample VCF/BCF files with .csi or .tbi indexes, adding samples incrementally, querying regions and samples in parallel, and exporting to VCF/BCF or TSV, on local disk or S3, Azure, and GCS. Use when building a variant database for a cohort, adding new samples to an existing dataset, querying specific regions across many samples, exporting subsets of a large VCF collection, or preparing population genomics data such as allele frequency or GWAS inputs. Not for multi-sample VCFs, which are unsupported, or for one-off parsing of a single VCF file.
Create a lightweight multi-page HTML/CSS/JavaScript UI prototype from agreed Phat project requirements and context. Use when the user wants to visualize and validate navigation, page structure, UI states, content hierarchy, or interaction flow before finalizing a feature spec. Produces editable prototype files under docs/assets/prototype with stable page revision IDs.
Break a ready feature specification into small, implementation-ready vertical-slice tasks with complete acceptance-criteria coverage, explicit dependencies, session-ready context, and concrete verification. Use when a ready spec is too broad for one focused implementation session or needs durable work items for implementation and review.
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets/PubChem/UniProt/PDB/ChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.
Main control agent for the topic selection system. Coordinates three stages: trend collection, topic generation, and topic review, and supports iteration until a qualified topic is produced. Triggers: (1) "start today's topic selection" launches the full workflow (2) "today's AI trends" only collects trends without generating topics (3) "I have a topic" enters single-topic analysis (4) "recommend some good topics" directly outputs recommendations. Output is saved to the Obsidian topic library.
Generate a topic-focused briefing in HTML from public news sources. Use when user asks for a briefing / observation / digest / 简报 / 观察 on any subject — region (Middle East, ASEAN, India), industry (semiconductors, EV supply chain, AI), policy issue (AI regulation, critical minerals, cross-border payments), institution (Fed, ECB, IMF), or theme. Output is a single self-contained HTML file with blue-color "TOPIC BRIEF" branding, optimized for both browser viewing and direct copy-paste into 微信公众号 / WeChat Official Account editor. Walks through 5 steps with one user confirmation midway. Do NOT use this skill for short summaries (<1000 字), single-piece news commentary, or already-defined report templates.
Transcribe and automatically rough-cut a newly recorded Chinese talking-head video containing slips, false starts, repetitions, unclear delivery, and retakes, then create a verified preview and an editable Jianying draft. Use when a user asks an AI agent to clean up a Chinese spoken video, with or without an authoritative .md/.txt script, while preserving intended content and exposing every omission or uncertain take.
The full guide to Traceway, the observability platform. Explains every part of the product and how it is meant to be used: issues and exception grouping, endpoints and the impact score, tasks, spans and traces, logs, metrics and dashboards, sessions, AI traces, profiles, monitors, incidents, status pages, post-mortems, alert rules and channels, on-call teams, schedules, overrides, escalation policies and pages, contact methods, roles, organization views, settings, and agent access. Use when the user asks how a Traceway page or feature works, where to find something, what a term means, or how to set up a workflow such as paging or a status page.
Design and audit public trust centers, security pages, privacy/compliance portals, subprocessors, uptime/status links, data protection summaries, policy libraries, evidence request flows, customer assurance, sales enablement, and review cadence. Use when a SaaS, developer tool, marketplace, AI product, or enterprise product needs credible trust proof before procurement or launch.
One-on-one tutor skill for solving math problems and generating HTML explanation documents and voiced Manim animation videos. Core workflow: math analysis → HTML visualization → storyboard script → TTS audio → verification update → scaffolding → Manim code → render verification. Triggers: the student pastes an image of a math problem, needs a teaching video, or needs HTML explanation materials
Analyze Taiwan's manufacturing industry structure including semiconductor, electronics, machinery, and petrochemical sectors. Use this skill when the user needs to understand Taiwan's industrial landscape, evaluate manufacturing sector opportunities, assess supply chain positioning, or contextualize Taiwan in global manufacturing — even if they say 'Taiwan manufacturing overview', 'semiconductor supply chain', 'what does Taiwan make', or 'industrial analysis of Taiwan'.
Use when the user asks how Twingate works, wants to design or evaluate a Twingate deployment, needs to understand components (Controller, Client, Connector, Relay), or is planning a ZTNA rollout. Activate for: zero trust, ZTNA, remote access architecture, network design with Twingate, VPN replacement, microsegmentation, split DNS, NAT traversal, P2P vs Relay, Remote Network topology, Resource definition strategy, or deployment sequencing. Also activate for community/reference deployment patterns: exposing a self-hosted AI chat assistant (OpenClaw, WhatsApp/Telegram bots) with no public inbound ports, private Railway/PaaS app deployment with zero-ingress, or "what does the twingate-assistant plugin itself do" meta-questions.
Use when the user needs to deploy, configure, upgrade, or troubleshoot Twingate Connectors on any platform. Activate for: Docker connector, Linux connector, systemd connector, ECS connector, Azure Container Instances, GCE, Helm chart connector, connector tokens, connector HA, connector health, connector metrics, connector logging, connector upgrades, DEAD_NO_RELAYS, DEAD_NO_HEARTBEAT, or connector placement questions. Also activate for connector deployment tooling and unofficial platform support: Raspberry Pi, Ubiquiti/UniFi (UDM Pro, UDM SE, UXG) gateways, Unraid, Home Assistant, Steam Deck / Decky Loader, Hyper-V, Chocolatey packaging, custom or hardened connector containers, GitHub Codespaces, Coder workspaces, render.com, Spacelift CI runners, connector log shipping to S3, connector fleet autoscaling, Grafana connector dashboards, PagerDuty connector alerting, or Docker container auto-updating for connector hosts.
Use when the user deploys Twingate in Kubernetes, uses the Twingate Helm chart or operator, manages TwingateResource or TwingateRemoteNetwork CRDs, routes traffic from cluster pods outward through Twingate, gates kubectl access via Twingate, or integrates Twingate into a GitOps workflow. Also trigger when an existing K8s stack needs connector deployment, token secret management, or declarative Twingate resource definitions. Also trigger for Helm chart `values.yaml` fields, operator CRD kinds (`TwingateConnector`, `TwingateResource`, `TwingateResourceAccess`, `TwingateGroup`, `TwingateGateway`, `TwingateCertificateAuthority`), kubeconfig sync automation, or running the Twingate headless client as a Kubernetes sidecar container.
Use when the user writes, debugs, or reviews Twingate Pulumi code in any language (TypeScript, Python, Go, C#/.NET). Activate on mentions of Pulumi, pulumi-twingate, @pulumi/twingate, or pulumi_twingate, or when an existing Pulumi stack needs to add Twingate resources. Also trigger when the user is migrating from Terraform to Pulumi for Twingate, or building a multi-language Pulumi stack that needs Twingate provisioning. Also trigger for local-plugin build/install errors (`pulumi plugin install`, 404 on `pulumi up`/`pulumi preview`, `+dirty`/alpha version strings), or requests for SE reference quick-start Pulumi scripts per cloud.
Use when the user writes, debugs, or reviews Twingate Terraform configuration. Activate for any .tf file that touches Twingate resources, the Twingate Terraform provider, IaC provisioning of Remote Networks, Connectors, Resources, Groups, or Service Accounts, provider version questions, and terraform apply errors involving Twingate. Also trigger when existing AWS, Azure, GCP, or Kubernetes Terraform stacks need to add Twingate. Also trigger for provider source/schema questions (`internal/provider/`), `group_ids` / `access` block migration errors, provider release version and changelog questions, or requests for SE reference quick-start Terraform modules per cloud.
Create, update, review, or refactor VS Code Copilot skills, hooks, and MCP configs. Use when the user wants to build or maintain reusable skills, lifecycle hooks, MCP integrations, or the supporting references and validation flow around those artifacts, or needs help deciding between a skill, hook, or MCP config.
Use this skill for Tailwind setup, migration, integration, and utility-first styling. Apply it when the task mentions Tailwind directives or utilities, @import "tailwindcss", @theme, plugin wiring, legacy-to-modern migration, token bridging with CSS variables, or framework-specific Tailwind build issues.
Build or extend an extensible UI self-check framework for Web UIs (React/Vite or plain HTML) using Playwright. Use when asked to add/upgrade ui-check or ui-watch flows, enforce data-qa/data-testid discovery, add theme/contrast checks, animation verification, loading state-machine checks, layout stability/overlap checks, modal scroll rules, or to document QA tagging standards and UI testing commands.
Design and refine coherent, content-led UI within an authorized prototype or implementation scope. Use as a supporting skill when creating a screen, choosing hierarchy or visual direction, or correcting generic AI-generated UI; skip routine UI changes already determined by established components.
Expert visual design craft, UI systems, and pixel-perfect implementation. Activates when building, styling, reviewing, or polishing any interface -- websites, apps, dashboards, component libraries, design systems, landing pages, or any screen needing visual polish. Triggers on: CSS styling, component design, layout, spacing, typography, color, dark mode, responsive design, design tokens, Figma, UI audits, visual hierarchy, icons, shadows, border-radius, animations. Also activates on: 'make it look good', 'improve the design', 'it looks off', 'spacing', 'colors', 'typography', 'design system', 'component library', 'pixel perfect', 'modern design', 'layout', 'responsive', 'dark mode', 'style this', 'polish', 'improve visual'. Applies whenever a visual interface is created or refined, even without saying 'UI'. Hands off to ux-designer for flow strategy and psychology. Hands off to design-system for tokens, component infrastructure, and DS audits. Do NOT activate for: user research methodology, psychology theory, backend logic, database schemas, API design without UI, DevOps, casual mention of design vocabulary in a non-design context (e.g., planning, discussing, writing about design without building/styling), tasks where the actual problem is data, performance, infrastructure, or content even if a UI is involved. Require explicit visual/styling intent -- do not activate by reflex on trigger words alone.
Premium neutral-first UI/UX design system and frontend workflow for product interfaces. Use when designing or reviewing pages, components, dashboards, settings screens, editors, forms, tables, modals, drawers, or interaction patterns that should feel calm, premium, responsive, system-driven, and production-ready. Also use when making design decisions about hierarchy, tokens, spacing, dark/light parity, component states, and cross-page consistency.
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
Master UI/UX redesign skill that audits every screen in the project, ranks them by priority, then redesigns each one recursively until pixel-perfect — applying color theory, typography, hierarchy, spacing, and accessibility principles automatically. Use when user wants to improve, redesign, or polish the UI/UX of an app, says "make the UI better", "redesign this", "pixel perfect", or invokes /uiux.
Removing signs of AI-generated text from Ukrainian. Use to edit or check text so it sounds naturally Ukrainian. Detects and fixes: Russianisms, anglicisms, bureaucratic clichés, pleonasms, AI lexicon, excessive emphasis of significance, promotional language, hidden Unicode watermarks, statistical AI patterns (low perplexity, low burstiness). Triggers: humanize Ukrainian text, зробити текст українським, прибрати AI, виправити суржик, редагувати українською, nature Ukrainian, remove AI patterns from Ukrainian, fix Russian calques, виправити русизми, канцелярит.
Integrate Univer Sheets, Docs, or Slides into React, Vue 3, HTML, or Node.js projects. Use when embedding Univer, choosing preset or plugin mode, initializing instances, configuring themes/locales/workers, or manipulating workbooks, worksheets, ranges, formulas, permissions, and events through the Facade API.
Remove machine-written code tells from a diff without changing behavior: narrating comments, one-caller wrappers, impossible guards, unused options, decorative logs, and leftover scaffolding. For behavior-changing fallback cleanup use `fail-fast`; for prose use `deslop`.
Coordinate docs.tenzir.com updates alongside code changes. Use when preparing the `.docs/` checkout, creating a matching docs branch, opening a `tenzir/docs` pull request, or cross-linking docs and code PRs. Also use when the user mentions "update the docs", "docs PR", ".docs/", or when a code change affects user-facing behavior that should be reflected on docs.tenzir.com.
This skill should be used when upgrading dependencies, bumping packages, resolving outdated dependencies, or performing dependency updates. It guides safe Bun-based package upgrades with breaking-change handling, runtime pin alignment, and grouped version coordination.
Plan, run, and synthesize usability tests and produce a Usability Test Pack (test plan, tasks/script, logistics, notes template, issue log, findings + recommendations). Use for usability test, user test, prototype test, user testing, usability study, Wizard of Oz, fake door.
Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.
Generate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis. Produces detailed PDF reports covering TMT, consumer, healthcare, and industrials. Triggered by requests to analyze an industry, create a market report, write a sector deep-dive, or generate any PE/VC-style research document in Chinese or English.
Route a prompt to the right Venice text model based on privacy tier (anonymized / private / TEE / E2EE), modality (vision / audio / video input), capability (reasoning, reasoning effort, code, function calling, X search, large context, structured output), uncensored needs, and cost. Use when a local agent (Claude Code, Hermes, NanoClaw, Codex CLI, etc.) needs to decide whether to handle a prompt locally or escalate to Venice, and if escalating, which Venice text model to call. Sits one level above venice-models (model discovery) and before venice-chat (the call surface).
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.