ai-reels-pipeline

ai-reels-pipeline is a skill for Claude Code from Samin12/claude-course. It costs 97 tokens per session (15,809 once invoked), scanned B, original, MIT.

An automated production pipeline for Instagram Reels, short vertical videos that combine a script, an AI avatar, supporting footage, and generated video clips.

In plain words
What is it for?
Use it to create avatar videos, find or generate supporting footage, plan storyboards, generate clips, assemble split-screen videos, and render them with Remotion.
Why use it?
It coordinates many separate video-making steps and produces a shared configuration for assembly and review, reducing the need to manage each stage manually.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is ../public/avatars/avatar-my-reel.mp4.

Good fit Use it to create avatar videos, find or generate supporting footage, plan storyboards, generate clips, assemble split-screen videos, and render them with Remotion.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Samin12/claude-course
agentmods
npx agentmods add skills/samin12/claude-course/ai-reels-pipeline

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-reels-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/samin12/claude-course/ai-reels-pipeline/github.svg)](https://agentmods.dev/skills/samin12/claude-course/ai-reels-pipeline)
Your own site
<a href="https://agentmods.dev/skills/samin12/claude-course/ai-reels-pipeline"><img src="https://agentmods.dev/badge/skills/samin12/claude-course/ai-reels-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-reels-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/samin12/claude-course/ai-reels-pipeline"><img src="https://agentmods.dev/badge/skills/samin12/claude-course/ai-reels-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,809 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.15809
Opus 5 $0.00048 $0.07905
Sonnet 5 $0.00019 $0.03162
Haiku 4.5 $0.00010 $0.01581

Measured 12d ago against content hash d6301ce59912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ai-reels-pipeline scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

# or: sudo apt install ffmpeg # Linux

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

resp = requests.get(f"{API_BASE}/v2/avatars", headers=headers(api_key))

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(cmd, capture_output=True, text=True, timeout=15)
skills/ai-reels-pipeline/SKILL.md · 1,822 lines

How it starts

The opening of the file, as written. The whole thing — 1,822 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Reels Pipeline - Build Automated Instagram Reels with Claude Code

A complete, open-source pipeline for producing professional Instagram Reels using AI avatars, AI-generated B-roll, and automated video rendering - all orchestrated through Claude Code.

What it does: You write a script, the pipeline generates an AI avatar speaking it, finds/creates B-roll footage, plans a visual storyboard using Claude, assembles everything into a JSON config, and renders a polished split-screen reel via Remotion - with quality gates at every step.

Stack: Python + TypeScript/React (Remotion) + Claude API + HeyGen API + Google Veo API + FFmpeg + Whisper


Table of Contents

  1. Architecture Overview
  2. Prerequisites
  3. Project Setup
  4. Directory Structure
  5. Pipeline Flow
  6. Stage 0: Pre-Pipeline (Script + Avatar + Transcribe)
  7. Stage 1: Asset Curator
  8. Stage 2: Storyboard Agent
  9. Stage 2.5: Image Resolver
  10. Stage 3: Veo Agent (AI Video Generation)
  11. Stage 4: Assembly
  12. Stage 5: Review
  13. Remotion Rendering System
  14. JSON Config Schema (ReelConfig)
  15. All Source Code
  16. Claude Code Integration
  17. Design Principles
  18. Troubleshooting

Architecture Overview

1080x1920 (9:16 portrait, 25fps)
+--------------------------+
|                          |
|    TOP HALF (960px)      |  B-roll: video clips, screenshots, AI-generated
|    JSON-driven segments  |  Ken Burns zoom, crossfade transitions
|                          |
+--[purple pill caption]---+  Word-by-word caption at the seam
|                          |
|   BOTTOM HALF (960px)    |  AI avatar video (HeyGen)
|   Cropped + centered     |  Audio source for the entire reel
|                          |
+--------------------------+

Read the full file on GitHub · 1,822 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 1,822 lines · 97 tokens per session scan B d6301ce59912

Subscribe to this mod's changes

ai-reels-pipeline is a skill published in the GitHub repository Samin12/claude-course (23 stars, last pushed 4mo ago), licensed MIT. It adds 97 tokens to every session and 15,809 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens