Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create and refine vertical short-drama scripts: high-level structure, episode writing, pacing and dialogue, and comeback or suspense ideas. Use when writing a short drama from scratch, revising a script, or designing an outline and hooks.
Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Skyline WXSS style support skill. Provides information on the CSS properties, values, and limitations supported by Skyline. Trigger keywords: WXSS, CSS support, style compatibility, property support, unsupported properties, display grid, position sticky, overflow, filter, gradient, linear-gradient, radial-gradient, conic-gradient, border-style, white-space, font-weight, text-decoration, text-overflow, aspect-ratio, will-change, calc, env, mask, mask-image, background-image, transition, animation, transform, font-feature-settings.
Sets up and uses Tailwind CSS v4 in Capacitor apps - CSS-first config (`@import "tailwindcss"`, `@theme`, `@utility`, `@custom-variant`, `@source`, `@plugin`), `@tailwindcss/vite` / `@tailwindcss/postcss`, upgrading from v3 `tailwind.config.js` with `npx @tailwindcss/upgrade`, WebView browser floor (Safari 16.4+ / Chrome 111+ vs Capacitor iOS 15/16 targets), safe-area utilities built on `env(safe-area-inset-*)`, platform variants (`ios:`/`android:` via a root class), class-based dark mode, `pointer-coarse:` touch targets, and hover-on-touch behavior. Use when installing Tailwind in a Capacitor project, styles do not apply after upgrading to v4, colors look wrong on older iPhones, or building mobile layouts with Tailwind. Do not use for Konsta UI components (konsta-ui), Ionic theming (ionic-design), native system bar / edge-to-edge config (safe-area-handling), or keyboard overlap (capacitor-keyboard).
Twitter/X thread writing with hook tweets, thread structure, and engagement optimization. Covers tweet formatting, character limits, media attachments, and posting strategies. Use for: Twitter threads, X posts, tweet storms, Twitter content, social media writing. Triggers: twitter thread, tweet thread, x thread, twitter post, tweet writing, thread creation, tweet storm, twitter content, x post, twitter writing, twitter hook, tweet formatting, thread structure
AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, repaint, continuation, or musical composition tasks.
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
External agent skill (MIT, github.com/DietrichGebert/ponytail). Forces the laziest solution that actually works: question whether the task needs to exist at all (YAGNI), reuse what is already in the codebase, reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Climb the ladder on every coding task — writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Supports intensity levels: lite, full (default), ultra. Never cut validation, error handling, security, or accessibility.
Use for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.
Create AI avatar videos with precise control over avatars, voices, scripts, and backgrounds using HeyGen's v3 API (POST /v3/videos). Two modes: type="avatar" with avatar_id, or type="image" with an image AssetInput (Avatar IV). Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Animating a photo into a speaking video (type="image"), (4) Transparent background videos with remove_background, (5) Integrating HeyGen avatars with Remotion, (6) Batch video generation with exact specs, (7) Brand-consistent production videos with precise control.
Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide resource audits. Produces curl commands or scripts. Triggers: 'cloudflare api', 'bulk dns', 'custom hostname', 'email routing', 'cache purge', 'waf rule', 'd1 query', 'r2 bucket', 'kv bulk', 'vectorize query', 'audit resources', 'fleet operation'.
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
Creates a fully functional Drizzle ORM setup with a provisioned Neon database. Installs dependencies, provisions database credentials, configures connections, generates schemas, and runs migrations. Results in working code that can immediately connect to and query the database. Use when creating new projects with Drizzle, adding ORM to existing applications, or modifying database schemas.
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure via OPENCLI_DIAGNOSTIC, patching the adapter, and retrying. Works with any AI agent.
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Build crypto wallets using Circle Modular Wallets SDK with passkey authentication, gasless transactions, and extensible module architecture. Use when: creating crypto wallets with passkey-based (WebAuthn) registration and login, sending gasless transactions using Circle Gas Station paymaster, batching multiple transactions into a single user operation, implementing passkey recovery using BIP-39 mnemonic phrases, building advanced onchain wallets with custom modules (multisig, subscriptions, session keys). Triggers on: MSCA, passkey authentication, WebAuthn, paymaster, Gas Station, ERC-4337, ERC-6900, toCircleSmartAccount, toModularTransport, sendUserOperation, 2D nonce, passkey recovery, EIP-1193 provider.
Remove repeated NuGet restores from multi-step .NET builds safely. Use for build/test/publish steps that each restore, Directory.Build.rsp with -restore, safe restore suppression, NETSDK1004/NETSDK1047 after --no-restore. Do not use for slow first restore, only one restore, version or lock errors, or unranked build slowness (use build-perf-baseline).
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Route audio, video, transcript, subtitle, and edit-prep requests into the right media-understanding workflow before execution. Use this when the user wants transcription, subtitle generation, beat mapping, B-roll planning, or edit-ready outputs and the first question is which skill and model chain should run.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Track parcels and check delivery status for Australian and international couriers. Searches Gmail for dispatch/shipping emails and provides tracking links for all major Australian couriers including AusPost, StarTrack, Aramex, CouriersPlease, Sendle, Toll, Team Global Express, DHL, FedEx, TNT, Hunter Express, Border Express, Direct Freight Express, and UPS. Triggers: 'where is my parcel', 'track my order', 'has my package arrived', 'tracking status', 'check tracking', 'where is my delivery'.
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.
OmniStudio OmniScript creation and validation with 120-point scoring. Use when building guided digital experiences, multi-step forms, or interactive processes that orchestrate Integration Procedures and Data Mappers. TRIGGER when: user creates OmniScripts, designs step flows, configures element types, or reviews existing OmniScript configurations. DO NOT TRIGGER when: building FlexCards (use sf-industry-commoncore-flexcard), creating Integration Procedures directly (use sf-industry-commoncore-integration-procedure), or analyzing dependencies (use sf-industry-commoncore-omnistudio-analyze)
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
Tailwind CSS patterns and conventions. Use when writing responsive designs, implementing dark mode, creating reusable component styles, configuring Tailwind, or migrating from v3 to v4. Triggers on tasks involving Tailwind classes, responsive design, dark mode, CSS styling, or "migrate to Tailwind v4".
Build non-custodial wallets where end users retain control of their private keys via Circle's user-controlled wallets SDK. Supports Google, Apple, Facebook social login, email OTP, and PIN authentication with MPC-based key management. Covers wallet creation, token transfers, message signing, smart contract execution, and wallet management. Triggers on: user-controlled wallets, social login wallet, email OTP wallet, PIN wallet, w3s-pw-web-sdk, executeChallenge, MPC wallet, userToken, deviceToken, contract execution
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.
Anthropic's method for training harmless AI through self-improvement. Two-phase approach: supervised learning with self-critique and revision, then RLAIF (RL from AI Feedback). Use for safety alignment and reducing harmful outputs without human labels. Powers Claude's safety system
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "this sounds like ChatGPT", or before any caption, script, comment, reply or DM is shown to the user.
Use this skill whenever users need help with resume creation, updating professional profiles, tracking career experiences, managing project portfolios, or generating tailored resumes for job applications. On first use, it extracts data from the user's existing resume and maintains a structured database of experiences, projects, education, and skills. Generates professionally styled one-page PDF resumes customized for specific job roles by selecting only the most relevant information from the database
Retrieves MLflow traces using CLI or Python API. Use when the user asks to get a trace by ID, find traces, filter traces by status/tags/metadata/execution time, query traces, or debug failed traces. Triggers on "get trace", "search traces", "find failed traces", "filter traces by", "traces slower than", "query MLflow traces".
Review an existing game codebase for architecture, performance, and best practices. Use when the user says "review my game", "code review", "check my game architecture", "is my game well structured", or "audit my game code". Do NOT use for making changes — this is read-only analysis. Use improve-game to implement fixes.
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.