Agent skill

Reel Builder

by Ootto-AI in Ootto-AI/claude-content-skills

Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel.

MITAuto-check: notesMedia & Creative

Install Reel Builder

skills CLI
$ npx skills add Ootto-AI/claude-content-skills --skill reel-builder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ootto-AI/claude-content-skills reel-builder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ootto-AI/claude-content-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reel-builder .claude/skills/reel-builder && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
reel-builder
GitHub stars
130
Token cost
~1.5k tokens
SKILL.md length
662 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel.

  • Works in 6 steps: The hook needs a gripping VISUAL, not… → The character ACTS through a progressive… → Sync the visual to the VOICEOVER, not a… → …
  • The user says build the reel
  • SKILL.md covers When to use, What you'll need, Instructions and Rendering the reel — the video…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reel Builder is an agent skill from Ootto-AI/claude-content-skills. Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel. Claude writes the beat-by-beat script in your voice and lays out the on-screen text, the scene for each beat, the pacing cues, and the caption — your words on a proven structure. Use when the user says "build the reel", "make the reel", "write the full reel", "turn this into a reel", "script and storyboard this", or hands over a breakdown/idea and wants the whole thing assembled.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Comics and storyboards. The repository describes itself as: Free, copy-paste Claude skills that run your content growth factory — turn ideas + your NotebookLM memory into scroll-stopping Instagram reels. By Ootto. The licence is MIT.

When your agent uses it

  • The user says build the reel
  • Write the full reel
  • Turn this into a reel
  • Script and storyboard this

Example prompts

  • “build the reel”
  • “make the reel”
  • “write the full reel”
  • “/reel-builder”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. The hook needs a gripping VISUAL, not just text. Open on something that grabs (e.g. a creator
  2. The character ACTS through a progressive action — never ping-pong/loop a few poses. Looping a small
  3. Sync the visual to the VOICEOVER, not a wall-clock. Transcribe the VO (word timestamps) and cut/act
  4. Emphasis text must be high-contrast and readable on every background (e.g. bright amber #FFCC33
  5. Close on an on-screen CTA card, tied to the comment system. End with a themed "Comment [KEYWORD] and
  6. No fabricated numbers. If a metric can't be verified, don't put it on screen.

What it can do on your machine

Read from SKILL.md and the folder at commit 5263be7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • ootto.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Reel Builder loads about 1.5k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:88
    tem for a key or read another product's `.env` — if you don't have the key, stop and ask.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ootto-AI/claude-content-skills at commit 5263be7, republished under its MIT licence (© Ootto-AI). 662 words, ~1,474 tokens.

Download SKILL.mdSave it as .claude/skills/reel-builder/SKILL.md (or your agent's skills folder).
name
reel-builder
description
Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel. Claude writes the beat-by-beat script in your voice and lays out the on-screen text, the scene for each beat, the pacing cues, and the caption — your words on a proven structure. Use when the user says "build the reel", "make the reel", "write the full reel", "turn this into a reel", "script and storyboard this", or hands over a breakdown/idea and wants the whole thing assembled.
user-invokable
true
argument-hint
[a reel-analyzer teardown, or a topic + the structure to follow]
license
MIT
metadata.author
Ootto
metadata.version
1.0.0
metadata.category
content

Reel Builder — Claude assembles the whole reel for you

The last step of the factory. Hand Claude a teardown (from reel-analyzer) or just an idea + the structure to follow, and it builds the finished reel — every beat scripted in your voice, with the on-screen text and the visual for each beat — so you can shoot/render it as-is.

When to use

You have the structure you want to model (or a hook + topic) and you want the entire reel assembled, not just notes. Run this after the analyzer + hook writer, or standalone with your own outline.

What you'll need

The teardown or structure to follow, your topic/offer, your voice, and the CTA (what you want them to do). Optional: your past winners (via ai-brain) so it sounds like you.

Instructions

You are my reel builder. Build a complete, ready-to-make reel.
STRUCTURE TO FOLLOW: [paste the reel-analyzer teardown, or describe the beat structure].
TOPIC: [what it's about] · VOICE: [yours] · GOAL/CTA: [save / follow / comment / DM].

Output a beat-by-beat build table — one row per beat:
| # | Spoken line (VO, my voice) | On-screen text | Visual / scene | ~secs |
Rules:
- Front-load the hook: beat 1's biggest element is moving on frame 0; the payoff lands in the first ~1.5s.
- The visual CHANGES every beat (show what's said — never plain text for a demo line).
- Original words on the modeled structure; total length matches the reference (±2s).
- End on ONE clear CTA that matches the deliverable.
Then give me: the final hook (3 options), the full VO script as one paragraph, and a caption + hashtags.

Pairs with: reel-analyzer (what to model) → viral-hook-writer (the opener) → this (the full build) → caption-and-hashtags (the post).

Rendering the reel — the video engine (make it, not just script it)

Scripting is half the job; this is how you turn the build table into a real, cinematic reel that actually gets watched. Use a hybrid engine, matched to the tier:

  • Character-acting / cinematic beats → Seedance (image-to-video). Seedance runs on Runway via the RunwayML SDK with model: "seedance2" (portrait 720:1280 for a 9:16 reel, ~5s per clip). Generate a conditioning still of the character/scene, then i2v it so the subject genuinely MOVES and performs. Cost ≈ $6–12 per reel — reserve it for the premium ($599 done-for-you) tier, not the $20 self-serve one.
  • Hook, chapter, text, payoff, CTA beats → Remotion code-render ($0). Fast, free, on-theme. This is the whole $20-tier reel and the text scaffolding of the premium one.

Non-negotiables (each of these was a real failure once — do not repeat them):

  1. The hook needs a gripping VISUAL, not just text. Open on something that grabs (e.g. a creator hacking a glowing terminal, a lock cracking, sparks) — the payoff word lands in the first ~1.5s.
  2. The character ACTS through a progressive action — never ping-pong/loop a few poses. Looping a small pose set back-and-forth (A→B→A→B) reads as "replaying" and plays actions in reverse. Each beat is ONE forward action, start to finish. Seedance i2v does this natively; posed-frame Remotion does NOT (it loops and reads choppy — avoid it for real acting).
  3. Sync the visual to the VOICEOVER, not a wall-clock. Transcribe the VO (word timestamps) and cut/act ON the word — the action must match what's being said. Lead the cut ~10 frames.
  4. Emphasis text must be high-contrast and readable on every background (e.g. bright amber #FFCC33 with a dark outline stroke reads on both dark and light beats).
  5. Close on an on-screen CTA card, tied to the comment system. End with a themed "Comment [KEYWORD] and I'll DM you [the thing]" card (an IG-composer graphic that types the keyword) — use the SAME keyword the caption uses and that the auto-responder is wired to, so comment → auto-DM → lead actually fires. Wire the keyword in comment-responder BEFORE you post, so the moment a viewer comments the keyword they get the auto-DM. Honest only: the keyword must be really wired.
  6. No fabricated numbers. If a metric can't be verified, don't put it on screen.
Show full SKILL.md (133 more words)Show less

Verify before you ship — WATCH and MEASURE the playback, never trust a still. Extract frames at ~12fps and confirm: motion is progressive (no repeating/ping-pong autocorrelation period), no frozen beats while the VO talks, and each action's cut aligns to its narration cue. Then eyeball the whole thing end to end. A reel that was never watched ships broken.

Credentials: use an API key you were explicitly given, from your OWN project's env only. Never search the filesystem for a key or read another product's .env — if you don't have the key, stop and ask.

Honesty: only promise a CTA you can deliver (if "comment WORD → I'll DM it", actually send it).


Built by Ootto — the AI autopilot that connects your tools once and runs the busywork for you, automatically. Book a demo →

© Ootto-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/reel-builder of Ootto-AI/claude-content-skills.

Open the folder on GitHubat commit 5263be7

Compare with similar skills

Reel Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Reel Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reel Builder this skillOotto-AI/claude-content-skills130—~1.5kAutomated safety check: NotesMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone
Tutti UI Systemtutti-os/tutti3.8k—~2.7kAutomated safety check: PassApache-2.0
3D Animation Short Generatortl2012tl/comfyUI-llama-TE2414 repos~3.7kAutomated safety check: PassNone
Text to PNG Card Casterlijigang/ljg-skills7.5k—~1.9kAutomated safety check: PassMIT
H3 Cinematic Directorjtydhr88/ComfyTV1.1k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed
  • Tutti UI System

    tutti-os/tutti

    A skill your agent uses when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business…

    3.8k GitHub stars~2.7k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • 3D Animation Short Generator

    tl2012tl/comfyUI-llama-TE

    Create complete stylized 3D animated shorts from a story idea through an ordered production workflow covering project brief, story outline, character and environment cards, standardized shot…

    241 GitHub starsUsed in 4 repos~3.7k tokens
    Media & CreativeAuto-check passed
  • Text to PNG Card Caster

    lijigang/ljg-skills

    Turns text, URLs or local files into tall PNG cards through HTML typography, with four modes: long reading card, full-text layout, comic and whiteboard.

    7.5k GitHub stars~1.9k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • H3 Cinematic Director

    jtydhr88/ComfyTV

    Convert approved scripts, shot briefs, storyboards, keyframes, character sheets, scene assets, prop sheets, and sound briefs into director-level storyboards and production-ready MiniMax H3 prompts.

    1.1k GitHub stars~2.7k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Scroll Promo Site Builder

    kangarooking/kangarooking-skills

    Create a scroll-controlled cinematic product website with rich motion (动效网站) from product materials, reference pages or videos, and brand assets.

    662 GitHub stars~2.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from Ootto-AI/claude-content-skills

All 52 skills in this repo
  • Agent Reach

    Ootto-AI/claude-content-skills

    MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g.

    130 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed
  • Ab Hook Tester

    Ootto-AI/claude-content-skills

    Generates two genuinely distinct hook variants for the same reel so you can post-test which opening actually wins.

    130 GitHub stars~484 tokensUpdated 3 days ago
    Auto-check passed
  • AI Brain

    Ootto-AI/claude-content-skills

    Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store.

    130 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Caption And Hashtags

    Ootto-AI/claude-content-skills

    Write the caption, hashtag set, and first comment for a reel or post.

    130 GitHub stars~508 tokensUpdated 3 days ago
    Auto-check passed
  • Collab Outreach

    Ootto-AI/claude-content-skills

    Drafts personalized pitches to creators and brands for collab reels, shoutouts and partnerships.

    130 GitHub stars~489 tokensUpdated 3 days ago
    Auto-check passed
  • Comment Responder

    Ootto-AI/claude-content-skills

    Turn every comment into a lead on autopilot. An agent skill from Ootto-AI/claude-content-skills.

    130 GitHub stars~717 tokensUpdated 3 days ago
    Auto-check passed

Questions about Reel Builder

What does Reel Builder do?

Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel. Reel Builder is an agent skill from Ootto-AI/claude-content-skills. Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel.

When should I use Reel Builder?

Reel Builder fits situations like: the user says build the reel; write the full reel; turn this into a reel; script and storyboard this.

How do I install Reel Builder in Claude Code?

Run `npx skills add Ootto-AI/claude-content-skills --skill reel-builder -a claude-code`. Or copy the skill folder (skills/reel-builder in Ootto-AI/claude-content-skills) into .claude/skills/reel-builder in your project. Claude Code loads it when a task matches its description.

How do I install Reel Builder in Codex?

Run `npx skills add Ootto-AI/claude-content-skills --skill reel-builder -a codex`. Or copy the skill folder (skills/reel-builder in Ootto-AI/claude-content-skills) into .agents/skills/reel-builder in your project. Codex loads it when a task matches its description.

Can I use Reel Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ootto-AI/claude-content-skills --skill reel-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reel-builder, .gemini/skills/reel-builder, .github/skills/reel-builder and .opencode/skills/reel-builder in your project.

What does Reel Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Reel Builder is instructions for the agent only.

Does Reel Builder access the network?

SKILL.md names 1 domain. As links in the text: ootto.ai. This is read from the text; nothing was executed.

Is Reel Builder safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Reel Builder use?

Reel Builder is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reel Builder use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Reel Builder?

Skills that share tags, products or a category with Reel Builder: Canghe Comic (freestylefly/canghe-skills, 461 stars), Tutti UI System (tutti-os/tutti, 3.8k stars), 3D Animation Short Generator (tl2012tl/comfyUI-llama-TE, 241 stars) and Text to PNG Card Caster (lijigang/ljg-skills, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reel Builder?

Ootto-AI (a GitHub organization) maintains it in Ootto-AI/claude-content-skills, which has 130 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 8, 2026.

Source: Ootto-AI/claude-content-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.