Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guide for creating logos, brand identities, and visual assets with AI tools: which tool fits which scenario (Recraft, Midjourney, Firefly, DALL-E, Stable Diffusion), prompt engineering per tool, vectorization pipelines, mockups, Python automation, and IP safety. The skill text is in Portuguese.
Adds Animate.css (v4.1.1) animations to HTML, React/JSX, and WordPress PHP templates. Includes scroll-trigger via Intersection Observer, RTL directional flipping, and prefers-reduced-motion compliance. Bundles the Animate.css library, so no CDN is needed.
Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.
Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this materialized view failing?", "are any of my views wasting compute?", or wants a one-shot triage of view health. For source/sync health use `auditing-warehouse-source-health`.
Use when you see 'actor-isolated', 'Sendable', 'data race', '@MainActor' errors, or when asking 'how do I use async/await', 'my app crashes with concurrency errors', or 'how do I fix data races'. Covers Swift 6 concurrency, @concurrent, and actors.
Build, edit, test, enable, and monitor PostHog workflows over MCP. Author the action/edge graph so it runs and opens cleanly in the visual editor, then change drafts surgically with patch operations. Use when asked to build, set up, automate, change, fix, or debug a workflow, campaign, broadcast, drip sequence, or event-triggered automation in the workflows product, including first-time messaging setup (email channel, sending domain, frequency cap) before the first workflow.
Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved, or regressed between two points or periods — "how much did X change from A to B", "before vs after", "start vs end", "week over week", "compare this month to last", "change over time" — or mentions a "slope chart" / "slopegraph". Two readings of "change" need different charts: the whole trend (a line, every interval) versus just the two endpoints (a slope, start vs end). Ask which they want, then render it. Not for choosing a saved insight ChartDisplayType in the insight editor.
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating on a stage (a black void for dark products, a high-key studio for light ones), with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. It also shoots stills, the same look frozen into single photographs. Use when asked for a launch video, product film, feature trailer, teaser, promo clip, hero shot, or any "cinematic" footage of an app, UI, or website, and also for a hero image, key visual, product photo, poster frame, launch-post image, Open Graph or social card, or any "cinematic" still of a UI. This skill covers camera, framing, light, and edit. It is stack-agnostic.
AI public finance inspector. Simulates a complete DGFIP tax audit of a French company's accounts (SASU, EURL, SAS, SARL). Analyzes the FEC, tax return, deducted expenses, shareholder current account, TVA, and IS across 9 review areas. Identifies potential tax reassessments with amounts, legal basis, and risk levels. Triggers: contrôle fiscal, redressement, vérification comptabilité, DGFIP, FEC, déductibilité, audit fiscal, tax audit
Dodo Payments customer management, covering customer CRUD, saved payment methods, real-money customer wallets and ledger entries, entitlements, and hosted customer portal sessions. Use when linking app users to cus_ IDs, opening a Manage billing portal, listing or deleting payment methods, or crediting wallets; use credit-based-billing for usage credits.
Use this skill when the user wants to add or update metadata in DataHub: descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, documents, or field-level metadata. Triggers on: "add tag to X", "update description for X", "set owner of X", "add glossary term", "deprecate X", "create a domain", "create a glossary term", "add a document", or any request to modify DataHub metadata.
Use this skill when the user wants to manage data quality in DataHub: create or run assertions, check assertion outcomes, raise or resolve incidents, create notification subscriptions, or diagnose health problems across their estate. Triggers on: "create assertion", "run assertion", "check quality", "data quality", "health check", "raise incident", "resolve incident", "subscribe to", "failing assertions", "active incidents", or any request involving data quality, assertions, incidents, or quality notifications
dontbesilent AI writing fingerprint detection. Scans copy for signs of AI generation and outputs a detection report. Diagnosis only by default; no edits. Triggers: /dbs-ai-check, /AI检测, “帮我看看有没有 AI 味”, “检测一下 AI 特征”. AI writing fingerprint detection. Scans copy for AI-generated patterns and outputs a diagnostic report. Diagnosis only by default. Triggers: /dbs-ai-check, “check for AI writing”, “does this sound like AI”
Integrate the Didit Proof of Address standalone API (POST /v3/poa/) to verify address documents. Use when the user wants to verify a proof of address, validate a utility bill, bank statement or government letter, extract and geocode the address on a document, enforce a maximum document age, cross-check a document against an expected name, address or country, detect edited PDFs, or perform PoA checks using Didit. Returns Approved or Declined with itemized warnings, the parsed address with coordinates, issuer, dates, holder name, bank fields and QR/barcode data.
Read, write, search, reply to and forward DingTalk Mail. Use when the user says send email / check email / reply to email / forward email / unread email / email search / mailbox attachment. For one-sentence email sending, first use dingtalk-contact to resolve and confirm the recipient, then send via this skill; does not handle DingTalk messages (use dingtalk-chat) or urgent notifications (use dingtalk-misc). Command prefix: dws mail.
Build a complete distribution system (posting, DM delivery, retargeting, tracking) that turns your hooks into a predictable pipeline, based on Lasse Flagstad’s A4 methodology from Marketing Swarm. Use when: **Launching a LinkedIn/X content machine** — cadence, review flow, posting engine; **Automating DMs after engagement** — trigger → message → tag → booking; **Setting up retargeting** — Email + Meta/IG so you never lose a lead; **Creating a simple dashboard** — the 6 ...
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Searches Google Fonts enriched with personality and mood tags, suggests proven pairings, generates CSS custom properties, Tailwind config, and embed links, and offers modular type scales. Works as a skill with bundled Python scripts, or as an MCP server.
Based on Huawei Cloud Flexus L API for instance management and operations. Supports querying instance list and details, querying traffic packages, batch start/stop/reboot instances, resetting passwords, and modifying instance information. Suitable for daily operations, lifecycle management, configuration changes, traffic monitoring, and other scenarios for Flexus L instances. Triggers: Flexus L, Huawei Cloud ops, query instance, start, stop, reboot, reset password, modify info, check traffic, traffic package (中文触发词: L实例运维，查询L实例，L实例开机，L实例关机，L实例重启，L实例重置密码，查询L实例流量包).
Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature.
Guide for the Infisical Kubernetes Operator — syncing secrets from Infisical into Kubernetes Secrets and ConfigMaps, pushing secrets from Kubernetes to Infisical, and managing dynamic secret leases in-cluster. Covers the v1beta1 CRDs (InfisicalConnection, InfisicalAuth, InfisicalStaticSecret) and the legacy v1alpha1 CRDs (InfisicalSecret, InfisicalDynamicSecret, InfisicalPushSecret), Helm installation cluster-wide or namespace-scoped, all 7 operator auth methods, sources and targets, creationPolicy Owner vs Orphan, refreshInterval, the secrets.infisical.com/auto-reload annotation for automatic Deployment rollouts, and Go templating of rendered secrets. Use this skill when someone asks about: Infisical Kubernetes Operator, InfisicalSecret CRD, InfisicalStaticSecret, syncing Infisical secrets into a Kubernetes Secret, auto-reloading pods on secret change, pushing Kubernetes secrets to Infisical, or 'how do I get Infisical secrets into my Kubernetes cluster'. Not for self-hosting Infisical on Kubernetes (infisical-self-host) — that is a different Helm chart — nor for rendering secrets to files (infisical-agent).
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.