Coco Ads logo

Coco Ads

Community
coco-research
coco-ads

Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames. Use when someone says "/coco-ads", "make a launch video", "brag about this", "turn this into a promo", "make an ad for this", or wants to share what they built. Reads the project code directly — no live URL or screenshots needed. Renders locally.

Overview

Publishercoco-research
Repositorycoco
Skill namecoco-ads
Stars
550
Forks
12
Bundled files
281
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 281 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by coco-research on GitHub. Read the source before you install it.

Installation

Install the Coco Ads AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/coco-research/coco/tree/main/skills/coco-ads
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/coco-research/coco.git /tmp/coco
mkdir -p .claude/skills
cp -r /tmp/coco/skills/coco-ads .claude/skills/coco-ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Coco Ads in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Coco Ads on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Coco Ads is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/coco-ads — launch videos from your repo

You built it. Now let CoCo make the ad.

/coco-ads turns the current project into a short (15–25s), polished, shareable launch video using the HyperFrames toolchain, rendered locally. It is narrow, opinionated, and fast.

Credit / lineage. This skill adapts the launch-video flow from brag by Shunit Haviv and runs on the HyperFrames HTML-composition + render engine by HeyGen. Music is not bundled: the skill is tuned for "Happy Beats / Business Moves" by ende.app, which you download yourself (see assets/music/README.md); bundled SFX are CC0 (Kenney.nl). See CREDITS.md. Re-implemented in CoCo's voice with attribution. Upstream brag is MIT-licensed (Copyright (c) 2026 Shunit Haviv Hakimi); its notice is retained at LICENSE in this skill directory.

Requirements

The render path is fully local (HeyGen cloud/Lambda paths are never used). It needs:

  • Node 22+ and FFmpeg on PATH.
  • The HyperFrames CLI, run via npx hyperframes … (auto-fetched on first use). The composition skills install once with npx hyperframes skills.
  • A quick environment check: npx hyperframes doctor (Chrome headless-shell + FFmpeg). "Docker not running" is fine — Docker is only for distributed cloud renders, which this skill does not use.

No data leaves the machine on the default render path. If GEMINI_API_KEY is set, the optional snapshot frame-analysis would call Gemini — keep it off (--describe false) when bragging about anything you would not paste in public.

What this skill does

  1. Reads the current project code to understand the app.
  2. Plans a short concept specific to this project.
  3. Scripts and storyboards the video.
  4. Hands a focused composition brief to HyperFrames.
  5. Validates, renders locally, and writes share copy.

Parsing the invocation

/coco-ads
/coco-ads --tone chaotic
/coco-ads --tone polished --format vertical
/coco-ads this. Make it feel like a ridiculous startup launch.
OptionValuesDefault
--tonepreset or freeform descriptioninferred
--formatlandscape, vertical, squarelandscape
--durationsecondsauto (15-25s)
--no-musicflagmusic on
--no-sfxflagsfx on
--titlestringinferred from project

Tone can be a preset (default, polished, yc-parody, chaotic, deadpan, cinematic, app-store) or a creative direction such as "fake Series A launch from 2016". When the user gives freeform direction, map it to the nearest preset for pacing and structure, but preserve the user's direction in the plan and composition brief.


Output directory

By default, output goes to coco-ads-output/. To avoid overwriting previous runs, use a timestamped directory (coco-ads-output-YYYY-MM-DD-HHmmss/) when the user asks for a new run or one already exists. Generate the timestamp once at the start of the run and use it consistently for the plan, brief, composition, render, and share copy. Keep coco-ads-output/ out of version control.


Step 1: Inspect the project

Read: references/step-1-inspect.md

Scan the project directory and extract what you need to plan the video.

Gate: You can answer all 9 questions in the planning rubric.


Step 2: Plan and storyboard

Read: references/step-2-plan.md

Write <output-dir>/coco-ads-plan.md. Answer the planning rubric, commit to a creative angle, and write the beat-by-beat storyboard (scenes, text, timing, transitions, SFX cues). Include a compact Music cue guidance section when music is selected.

Gate: <output-dir>/coco-ads-plan.md exists with a full storyboard; scene durations sum to 15–25 seconds.


Step 3: Hand off to HyperFrames

Read: the installed HyperFrames composition skills (npx hyperframes skills if absent), then references/step-3-compose.md and references/audio.md.

Write <output-dir>/composition-brief.md, then build the composition in <output-dir>/composition/. /coco-ads owns product angle, source material, storyboard, tone, format, audio selection, and delivery; HyperFrames owns the concrete composition structure, animation mechanics, and render workflow.

Gate: npx hyperframes lint passes with zero errors inside <output-dir>/composition/.


Step 4: Validate, render, and deliver

Read: references/step-4-deliver.md

Validate (npx hyperframes validate + inspect), render to <output-dir>/brag.mp4, and write <output-dir>/share-copy.txt.

Gate: the rendered MP4 exists and share copy is written.


Tone system

Seven presets ship with /coco-ads. Each changes scripting energy, pacing, typography personality, and transition style. Presets are defaults, not limits — always allow a freeform creative direction to refine or override.

Full definitions: references/tones.md

ToneEnergyOne-liner
defaultPlayful, clean, postableThe good-vibes default
polishedSerious, elegantFor projects that are not jokes
yc-parodyDeadpan startup energyFake seriousness applied to absurd projects
chaoticFast, loud, aggressiveOver-the-top and unhinged
deadpanCalm, dry, understatedThe joke is that nothing is a joke
cinematicDramatic, trailer-scaleBig motion, bigger claims
app-storeSmooth, feature-card cleanCorporate but not boring

Creative laws

These apply to every video regardless of tone.

Short. 15–25 seconds. Not one second more without a reason.

Readable. Keep the pace high through motion and cuts, never by flashing text. Every line a viewer must read holds long enough to read it (short label ~0.8s settled; a sentence ~0.3s per word). Fast-in, then hold — never fast-in, then gone.

Specific. The video must feel like it was made for this exact project, not any project.

Show the thing. At least one scene must display actual UI, copy, or a key visual from the product. No abstract filler.

No generic SaaS language. "Streamline your workflow" is banned. Use the project's actual copy and claims.

The hook is everything. The first 2 seconds decide whether someone keeps watching. Plan the hook before anything else.

Funny earns its place. Humor should come from the project's absurdity, not from trying to be funny.

Pattern:

Hook (2-3s) → Reveal (2-4s) → 2-3 sharp highlights (5-12s) → Punchline/outro (2-4s)

Adapt this. The pattern is a starting shape, not a template.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 140 more files.

Frequently asked questions

What does the Coco Ads AI skill do?

Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames. Use when someone says "/coco-ads", "make a launch video", "brag about this", "turn this into a promo", "make an ad for this", or wants to share what they built. Reads the project code directly — no live URL or screenshots needed. Renders locally.

Why use Coco Ads on TypingMind?

Because you install it once and use it with any model. Coco Ads is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Coco Ads in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coco-research/coco/tree/main/skills/coco-ads. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Coco Ads?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Coco Ads?

As many as you like. As long as a model supports skills, you can use Coco Ads with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Coco Ads AI skill free?

It is published on GitHub by coco-research. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇