skill(remotion): programmatic video generation with AWS Lambda#1893
Open
jorgenclaw wants to merge 1 commit into
Open
skill(remotion): programmatic video generation with AWS Lambda#1893jorgenclaw wants to merge 1 commit into
jorgenclaw wants to merge 1 commit into
Conversation
…mbda Battle-tested V2 skill for creating MP4 videos from React components, rendered serverless on AWS Lambda. Includes: - Host skill (.claude/skills/add-remotion/) — setup walkthrough: IAM user, Lambda deploy, credential wiring, container mounts - Container skill (container/skills/remotion/) — agent instructions for creating compositions, TTS narration, and rendering via remotion-render CLI - CLI tool (tools/remotion-render) — wraps site deploy + Lambda render + S3 download into a single command - IAM policy (aws-policies/) — scoped to remotion-render-* functions and remotionlambda-* buckets (not wildcard *) Proven settings documented: gpt-4o-mini-tts echo voice at 1.15x, WAV format, BUFFER=80 frames, --frames-per-lambda=60 for 10-concurrency cap. Production-proven: 20+ videos rendered on NanoClaw V2 since April 2026. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.claude/skills/add-remotion/) walks through setup: IAM user, Lambda deploy, credential wiringcontainer/skills/remotion/) teaches the agent how to create compositions, generate TTS narration, and rendertools/remotion-render) wraps site deploy → Lambda render → S3 download into one commandremotion-render-*functions andremotionlambda-*buckets (not wildcard*)377 lines across 4 files. Zero npm dependencies on trunk — Remotion packages install per-group.
How it works
/add-remotion→ Claude mergesskill/remotion-v2, walks through AWS setupremotion/src/directoryremotion-render <CompositionId> <output>.mp4deploys to Lambda, renders, downloads the MP4How it was tested
Production-proven on NanoClaw V2 since April 2026 — 20+ videos rendered including product demos, social media content, and showcase reels. Proven settings documented: gpt-4o-mini-tts echo voice at 1.15×, WAV format, BUFFER=80 frames,
--frames-per-lambda=60for AWS free-tier 10-concurrency cap.Change type
🤖 Generated with Claude Code