All Agent Skills
Browse every verified Agent Skill in the current snapshot. Use search to find a tool, task, publisher, or workflow.
Linkedin Growth
Two-phase LinkedIn lead pipeline driven by linkedin-cli. Phase A imports leads from a search URL or filters, qualifies them against a configurable ICP via sub-agent, and stores them in a local SQLite database with round-robin assignment across one or more LinkedIn accounts. Phase B runs on a schedule per account — sends connection invites up to a daily limit and withdraws stale pending requests. Use when the user wants to grow their network from LinkedIn searches, manage outgoing invites at scale, ask status questions (counts, conversion, pending older than N days, last imports), pause/resume an account, change ICP, or install the recurring scheduler.
Cypress Author
Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for this file'). Prefer cypress-explain when the user only wants to explain or review tests without changing code.
Cypress Cloud Cli
Runs the cy-cloud CLI to inspect Cypress Cloud organizations, projects, runs, specs, tests, failure screenshots, and Test Replay data. Use when the user mentions Cypress Cloud, cy-cloud, cypress-cloud-cli, a Cloud run or test URL, failing or flaky Cypress tests, Test Replay, run triage, Cloud artifacts, or asks why a recorded test failed.
Cypress Docs
Search and extract Cypress information from official documentation (docs.cypress.io, cypress.io); prefer LLM markdown under /llm/* and refuse unverified API or behavior claims.
Cypress Explain
Explains Cypress tests (E2E and component tests), and answers questions about Cypress use and behavior. Use when the user asks to explain how a test works, explain how Cypress works, review or critique a test without writing code. Apply even when the user does not say 'Cypress' (e.g. 'explain this test'). Prefer the cypress-author skill when the user wants to create, fix, or update tests.
Cypress Tap
Drives a running Cypress open-mode session through `cypress tap` to run and rerun specs, wait for fresh results, inspect reporter and command logs, and query or rewind the app under test through DOM, accessibility, styles, and snapshots. Use when authoring or debugging Cypress e2e or component specs, discovering selectors, diagnosing failures, or verifying test behavior without GUI interaction. Not for one-shot headless runs. Requires Cypress 15.21+, a Chromium-family browser, and a running `cypress open` session.
Adapting Formats
Resizes an existing image ad into the other shapes it has to run in — reads the ad first, then regenerates it at each ratio with the original passed in as a reference, so the product, the copy and the look carry across. Each shape is recomposed rather than cropped, with the background extended into the space the new proportions open up and the headline and call to action kept clear of the buttons and captions the platform draws over the top. Use when the user has an ad and needs it in another size, in a ratio family, or in every size a channel takes. Not for making an ad that does not exist yet — that is generating-image-ads; not for writing the words of the ad — that is writing-ad-copy.
Analyzing Brand
Analyzes a brand from its own website — its colours and fonts, the logo and imagery it uses, how it sounds, who it sells to, the claims it makes, and what it sells. Reads the site and its pictures with a vision model, and marks anything the site doesn't evidence as unconfirmed rather than guessing. Facts only — nothing is generated, planned or judged here. Use when a brand's guidelines, palette, typography, voice, tone or positioning need establishing, or when another skill needs the brand before it plans or generates.
Analyzing Own Ads
Audits the ads a company is running itself — what's live now, what it has already stopped, and which have run longest. Watches the video ads and reads the image ads with a vision model, then maps what the account already covers — the angles, hooks, formats and offers — what was dropped and how fast, and which long-runners have nothing newer beside them. Read from the public ad library, so it carries run lengths rather than spend or results. Research only — nothing is generated or changed here. Use when the user wants their own ads audited, wants to know what they are running, which of their ads is holding, what they already cover, or whether anything is going stale.
Cloning Video Ads
Clones an existing video ad — reads a supplied reference ad, keeps its structure, pacing, shots, camera and hook, and rebuilds it as a new video with the user's own product in place of the original's. Use when the user wants to copy, clone, recreate, or remake an ad or a competitor's video, or make an ad "like this one" with their product. Not for a product ad built from scratch with no reference video, not for a creator sharing their own take on a product and not for cloning image ads.
Identifying Competitors
Finds out who a brand competes with. Reads what the brand sells from its site, searches the web for the alternatives buyers compare it against, and proposes a shortlist with competitor names and websites. Use when the user asks who their competitors are, or to find or refresh their competitor list, or when another skill needs competitors named first.
Onboarding User
Onboards a new user — sets up their brand for the first time from their website. Analyzes the brand, finds its competitors, and saves both to the company profile that every later session reads from. Use when the user wants to onboard, get started, or set up their brand or company profile. Not for just analyzing a brand from its website — that is analyzing-brand.
Planning Campaigns
Decides what to make next — turns the brand, the product, your own running ads and competitor research into the concepts worth testing next. Each concept is a full description of one ad, the buyer it targets, the bet it tests and the evidence it rests on — complete enough for a producer to build from directly. Nothing is generated before the plan is approved — it asks which concepts to build, and only then hands each approved concept to the skill that builds it. Use when the user asks what to make, what to test next, what hooks or angles to try, for campaign concepts, or a creative plan — or wants the whole campaign run end to end, from research to finished ads. Not for a single ad with no plan behind it — that goes straight to the producer skill.
Researching Competitor Ads
Analyzes the ads competitors are running — the ones live now, the ones they have already stopped, and which have run longest. Watches the video ads and reads the image ads with a vision model, so every finding comes from the ad itself rather than its caption. Finds the patterns across the set — what is holding, what was dropped, and what nobody runs. Research only — nothing is generated or recommended here. Use when the user wants competitor ads researched, an ad teardown, a competitive or category analysis, to see what ads a named brand is running, or to find what is working and what nobody has tried yet.
Supercmo Setup
Diagnoses which capabilities are ready or blocked, sets up the keys, then sets up the brand from its website. Use when the user asks to "set me up," "setup," "help me get set up," "get started," "help me get started," "get me started," "what can you do," or to configure or finish setting up SuperCMO, or on a no_provider_configured error.
Sendmux Attachments
Use Sendmux attachment workflows without wasting model context on base64. Use when uploading, downloading, reading, forwarding, or sending email attachments through Sendmux MCP, CLI, SDKs, or direct HTTP, especially when choosing file_path vs presigned upload URL vs inline base64, reading inbound attachments with mailbox_read_attachment, fetching short-lived download_url links, or attaching local files to outbound mail.
Sendmux Cli
Use the Sendmux command-line interface for terminal-driven Sendmux work. Use when the user wants install commands, profiles, key-scope preflight, --json output, colon-namespaced Sendmux commands, request body/path/query/header flags, or CLI examples for Management, Mailbox, or Sending API operations.
Sendmux Email For Agents
Design and route Sendmux email workflows for AI agents, including skill installation, self-registration, secure agent credential-bundle storage, owner approval, and runtime email operations. Use when a user wants to give an AI agent its own inbox or email address, let an agent receive/search/triage/reply to mail, draft human-approved replies, send notifications, monitor mailbox state, or build email-based agent workflows even when the user does not mention Sendmux by name.
Sendmux Getting Started
Sendmux setup, skill installation, API key validation, agent access, secure agent credential-bundle storage, and first-call guidance. Use when the user wants to install Sendmux tooling or skills, check whether an smx_root_, smx_mbx_, or smx_agent_ credential works, choose MCP vs CLI vs SDK, connect an agent to Sendmux email, configure auth, self-register an agent, or make the first harmless Sendmux API call from an agent, terminal, or application.
Sendmux Mailbox Agent
Work efficiently with one Sendmux mailbox from an AI agent. Use for reading, searching, counting, syncing, triaging, filing, deleting, threading, or replying from a mailbox with an smx_mbx_ key or scoped smx_agent_ token, especially when the user asks an agent to inspect an inbox, find relevant messages, mark messages, or continue from a prior mailbox sync state.
Sendmux Management
Manage Sendmux account-level resources with an smx_root_ key. Use for domains, mailbox provisioning, mailbox API keys, sending accounts, webhooks, billing, spend, delivery logs, incoming logs, metrics, and other team administration tasks; route mailbox reading, triage, sync, and replies to sendmux-mailbox-agent.
Sendmux Mcp Setup
Configure Sendmux Model Context Protocol servers for AI agent clients, using hosted OAuth first when supported and secret-backed local env config otherwise. Use when the user wants to install sendmux-mcp, connect the hosted Sendmux MCP endpoint, run local stdio or HTTP MCP servers, set mailbox/management/sending key scopes, add bearer headers, or write MCP config for Claude Code, Cursor, Codex, VS Code/Copilot, Copilot CLI, Gemini CLI, Cline, or Windsurf/Cascade.
Sendmux Send Email
Send email with Sendmux, including owner-approved Sending-resource smx_agent_ tokens from claim-token exchange. Use when the user wants to send one email, send multiple emails, choose single vs batch sending, add idempotency keys, include attachments, compare HTTP Sending API vs SMTP, or use Sendmux MCP, CLI, SDK, or direct HTTP for outbound email.
Sendmux Token Efficient Usage
Choose the cheapest correct Sendmux surface and call. Use whenever a Sendmux task could be done through MCP, the sendmux CLI, an SDK, or direct HTTP and the user needs low-token, low-round-trip usage: batch sends, mailbox search/count/batch reads, sync deltas, cursor pagination, ETags, conditional requests, idempotency keys, attachment file transfer, or avoiding broad mailbox/log fetches.
Compress Images
Compress images for web/SEO performance using cwebp. Use when optimizing images for faster page loads, reducing file sizes, or converting JPG/PNG to WebP format.
Customer Empathy
Deep-dive into customer empathy and user journey thinking. Use when designing onboarding, improving UX, planning features, or trying to understand how to delight users faster.
Download Video
Download videos from social media URLs (X/Twitter, YouTube, Instagram, TikTok, etc.) using yt-dlp. Use when saving a video locally, extracting content for transcription, or archiving video references.
Transcribe Video
Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe. Use when creating captions, extracting spoken content, generating transcripts for notes, or making video content searchable.
X Post
Post to X (Twitter) from the command line. Text, images, and video.
Analyzing Products
Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category, how it's used, its moving/opening parts, and key visual details). Use when a product URL or photo needs turning into inputs for image/video generation, or when another skill needs product facts before generating.
Generating Ad Videos
Makes a product ad video — a product showcase with no one on screen, or a story or lifestyle commercial where a presenter or actor plays a role in the brand's spot, with or without a voiceover. Use when the user wants a product ad, commercial, TV ad, brand film, or product-hero video. Not for a creator or customer sharing their own take on a product, like a review, unboxing, try-on or testimonial — that is generating-ugc-videos; not for a video with no product being sold — that is generating-videos.
Generating Ai Actors
Generates one photorealistic person as a single image — an AI actor, influencer, presenter or model. The image is reusable, so passing it into any later generation brings the same face, hair and build back and one person can hold across a whole set of images or videos. Use when the user wants an AI actor, or when something needs a person and no photo of one was supplied.
Generating Audio
ALWAYS read this skill before generating spoken audio or calling audio_generate — a voiceover, narration, an ad read, a character line, or any script read aloud. Turns a script into speech — picks the model and voice, prepares the text for reading, and splits a long script into clips. Use whenever the user asks for text-to-speech, a voiceover, narration, or to have something read or spoken aloud.
Generating Cartoon Videos
Generates a cartoon video for a product — a drawn, animated, anime, illustrated or painted spot that holds one art style and the same characters across every cut. A cartoon character presents, uses or sells the product, and the product itself is either kept exactly as photographed or drawn into the style. Use when the user wants a cartoon, animated, anime, illustrated or hand-drawn video, an animated ad, explainer or mascot spot, or any video whose look is drawn rather than filmed. Not for a photorealistic ad or a live actor or for animating a supplied photo.
Generating Image Ads
Turns a product photo or URL into a static image ad — one image, or a set. Reads the real product first and holds it identical across every frame and ratio. Triggers: "image ad", "make an ad", "static ad", "promo graphic", "offer graphic", "sale creative", "social ad", "banner ad", "ad creative", "before/after ad", "testimonial ad". Not for generating product photography.
Generating Images
ALWAYS read this skill before generating or editing any image, or calling image_generate — text-to-image or image-to-image, simple or complex. Turns a text brief, optionally guided by reference images (a character, a style to follow, an existing photo to edit), into a still image. Analyzes intent, routes to the best model, and structures the prompt. Use whenever the user asks to generate, create, make, design, or edit an image — except commercial photography of a product being sold, which belongs to generating-product-photos.
Generating Product Photos
ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate. Turns a product photo or URL into commercial photography - packshots, lifestyle and campaign frames, on-model, macro detail, flat lays, seasonal staging, infographics, concepts and floating shots. Reads the real product first and holds it identical across every frame. Triggers: "product photo", "packshot", "shoot my product", "studio shot", "lifestyle shot", "hero image", "on a model", "flat lay", "product infographic", "floating product".
Generating Storyboards
Generates the storyboard sheets for a video — one image per clip, panels in a row, each panel one action. Divides each clip into panels itself, then builds the sheets one at a time, each taking the previous one as a reference, so the person and product stay consistent except where the story deliberately changes them. Use when a video's clip lengths and story are settled and it needs sheets before anything is animated. Not for a still image on its own — that should be made using generating-images.
Generating Ugc Videos
Generates a UGC video — a creator or customer, on camera as themselves, sharing their own authentic take on a product. Use when the user wants a UGC video, creator video, influencer ad or endorsement, tiktok-style review, unboxing, try-on, OOTD, fit check, haul, tutorial, talking head, or creator testimonial. Not for a produced advertisement in the brand's voice, where a presenter or actor plays a role in the brand's spot — that is generating-ad-videos; not for a video with no person in it, or a person with no product to show.
Generating Videos
ALWAYS read this skill before generating or animating any video, or calling video_generate — text-to-video, image-to-video, a start→end transition, or a reference / motion / audio-guided clip. Generates a video from a brief — one clip, or several clips joined into a single file at any length. Use when the user wants to make or generate a video, animate a photo, bring an image to life, produce b-roll, film a described scene, or move from one held frame to another. This skill should also be used when the video takes its motion or style from an existing video, or has to run to an existing audio track.
Writing Ad Copy
Writes the words of an ad — the headline, primary text, description and call to action that go into the ad platform's own fields, shaped to the channel it runs on. Handles one channel or several, returning copy sized to each platform's limits. Nothing is generated here — text only. Use when the user wants ad copy, ad text, headlines, primary text, a description or captions written for a paid ad.
Writing Video Prompts
Writes the motion prompt for a video clip — what moves, how the camera behaves, the physics and the audio, in the shape the chosen model wants. Works from a brief alone, from a start frame, from a source video, or from a storyboard sheet where each panel becomes a cut. Handles one clip or a whole set, returning one prompt per clip. Nothing is generated here. Use when a clip's model, duration and content are settled and it needs the prompt written.
Writing Video Scripts
Writes what is said in a video — the words a person speaks on camera, or a voiceover heard over the picture. Fits the writing to the time available, so lines are never rushed to fit or padded to fill. A video longer than a single clip gets its script split into one piece per clip, each sized to that clip's seconds. Outputs the words as text only — nothing is recorded or voiced here. Use when the user wants a script, dialogue, or a voiceover written for a video.
Zero
Use Zero for capabilities beyond Hermes.
Speed
Launch RSVP speed reader for text
Nutrient Document Processing
Process documents with Nutrient DWS. Use when the user wants to generate PDFs from HTML or URLs, convert Office/images/PDFs, assemble or split packets, OCR scans, extract text/tables/key-value pairs, redact PII, watermark, sign, fill forms, optimize PDFs, or produce compliance outputs like PDF/A or PDF/UA. Triggers include convert to PDF, merge these PDFs, OCR this scan, extract tables, redact PII, sign this PDF, make this PDF/A, or linearize for web delivery.
Courier
Use when building notifications with Courier across email, SMS, push, in-app inbox, Slack, Teams, and WhatsApp: sends, templates, Elemental, journeys, preferences, routing, CLI and MCP.
Swiftui Wcag Accessibility Auditor
Audit SwiftUI iOS feature code for accessibility against WCAG 2.2 Level A/AA and return patch-ready fixes. Use when reviewing SwiftUI views/screens (including auth, forms, settings, and custom controls) and you need both standards traceability (WCAG + WCAG2Mobile interpretation) and practical, minimal code changes in a concise priority-grouped Markdown format with user follow-up checks for code-indeterminate behavior.