Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once (`<hf-audio-group>`). Don't use for sourcing or generating audio — finding BGM, SFX, or making a voiceover is `/media-use`. Don't use for clip timing or track layout, which is `/hyperframes-core`.
Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.
The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md plan formats. Read before writing composition HTML.
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.
Use when a HyperFrames composition needs a punch-in, punch-out, zoom, reframe, Ken Burns treatment, camera move, visual match/whip handoff, or other seek-safe 2D/3D keyframes; also for GSAP, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.
Install, discover, and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).
Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.
Smart router for any "generate" or "edit/modify/repurpose" request on an image or video. Introspects connected MCP servers, locates the Arcads MCP, reads its live tool list, picks the best-matching tool for the user's intent, and runs it end-to-end (upload, call, poll, deliver). Use proactively when the user asks to "generate an image", "make a picture of…", "generate a video", "create a video of…", "edit this image", "remove the background", "extend this video", "add captions", "add a voice-over", "translate this ad", "upscale this", "change the background", "repurpose this video", "make a version with…", "add a logo", "swap the product", or any phrasing implying media creation, modification, repurposing, captioning, voice work, translation, or enhancement — text-only, image, or video input. Defers to specialized skills (arcads:clone-hook, arcads:clone-static-ad, arcads:spy-competitor-ads) when they match. Do not trigger for read-only/analytical queries.
152mo agoReviewMountCreate a free account to mount
Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.
Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on "graphic overlays", "on-screen graphics", "package / dress up my video". Not plain subtitles (/embedded-captions). Unclear → /hyperframes.
152mo agoReviewMountCreate a free account to mount
Case Study. Turns the first customer into proof, with their permission. Once the product has shipped, it writes a short before-and-after from their real numbers and their real words, and keeps it marked as a draft until they have approved that exact text in writing. Change a word and it asks again. Use when the user says "case study", "testimonial", "customer story", "get a quote from them", "write up the result", "social proof", "can I use their name", or once a customer has seen results.
Demo Builder. Builds a demo showing how your product solves the problem, before the product exists. Turns a small spec into one self-contained HTML page that runs anywhere with no server: sample records, one button, every row moving through its statuses and a total counting up, with a banner that always says it is a demo with sample data. Claude can then make it look and behave more like the real thing for this buyer. Use when the user says "build a demo", "mock this up", "show how it would work", "I need something to show them", "prototype", or "make a clickable demo".
Follow-Up. Keeps the deal moving. Tells you who is due today after a pitch or an offer, drafts the next note (a bump, something useful, a last note), waits for your yes, logs it, and stops at the first "no", the moment a demo is booked, after 3 follow-ups or after 30 days. Logs their replies and knows when it's your turn. Use when the user says "follow up", "who do I need to follow up with", "they haven't replied", "chase", "nudge", "bump this", "they replied", "they said no", or every morning.
Launch Planner. Plans the launch once it is paid for. Works backwards from the earliest date you promised a paying customer: requirements confirmed, feature complete, customers testing, fixes, first ship, then the rest. The public launch comes last, behind a gate that stays closed until someone has the product, nobody is late, and everything they paid for is built. Use when the user says "launch plan", "when do we launch", "are we on track", "what's next", "plan the launch", "can we launch yet", "launch checklist", or once customers have paid.
Market Researcher. Finds problems businesses already pay thousands to solve. Looks for money that is already leaving their accounts: vendors, agencies, outsourced services and salaried jobs that exist only because of one painful problem. Builds a table of the problem, who pays and what they pay today, with a source for every number or a clearly marked estimate with its working, then helps you pick the one to go after and sets up the board the other ten Whale skills share. Use when the user says "what should I build", "find me a problem", "market research", "validate this idea", "who would pay for this", "what do businesses pay for", or "set up the whale skill".
Objection Handler. Answers every objection, and knows a no when it hears one. Matches what they said ("it isn't built yet", "what if you never ship it", "why pay up front", "too expensive", "I need to ask my CFO") to an honest answer filled in from your own terms, and shows why it works. A real no gets no answer at all: it stops the deal for good. Every answer is a draft for your yes. Use when the user says "they said", "how do I answer this", "what do I say to", "they pushed back", "objection", "they think it's too expensive", or pastes a reply they don't know how to answer.
Offer Builder. Writes the offer they can say yes to. One page: the problem in their own numbers, what they get, the price, the date it ships, and the way out, with the plain statement that it isn't finished yet. A lint refuses an offer that leaves any of that out or that leans on fake urgency, made-up proof and promises nobody can keep. Every offer waits for your yes. Use when the user says "write the offer", "make them an offer", "offer page", "proposal", "one-pager", "what do I send them", "they asked for details", or "founding customer offer".
Pre-Sale. Gets customers to pay up front, and uses what they ask for to build the exact product. Sets honest terms (it isn't finished, the date it ships, how they get their money back), checks them, prepares a Stripe Payment Link in your own account for one buyer, logs real payments, and tells you when enough companies have paid to call it validated. Then it holds you to the date: it flags every promise coming due and writes the delay notice with the refund offer. Use when the user says "pre-sell", "pre-sale", "get them to pay up front", "take a deposit", "charge before I build", "send a payment link", "validate with money", "who has paid", "am I validated", or "they said yes".
Pricing. Sets the price from what they pay today. Takes the money already leaving their account for this problem, works out the year, and gives three prices with what each one leaves them, or checks a price you already have in mind, with the working shown so it can be argued with. Then puts the chosen price on the deal. Use when the user says "what should I charge", "pricing", "how much is this worth", "set the price", "founding price", "am I charging too little", or before writing an offer.
Requirements. Turns what paying customers asked for into the build list. Captures each ask in their own words with the feature it becomes, merges the same feature across customers, and ranks the list by how much paid money is behind each line, so you build exactly what was paid for and nothing else. Asks from people who haven't paid wait on a separate list. Logs each customer confirming the list, and marks features done. Use when the user says "what should I build", "requirements", "build list", "they asked for", "what did they want", "scope", "spec", "feature requests", or right after a customer pays.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
JakeschincariolSkill