amazon-nova-reel
Produce and operate Amazon Nova Reel video-generation jobs through Amazon Bedrock. Use for Nova Reel text-to-video, image-conditioned animation, automated or manual multi-shot storyboards, async S3 delivery, cost and approval gates, production continuity, output custody, and AWS-specific safety, privacy, IAM, and provenance decisions.
Profile →npx skills add calesthio/generative-media-skills --skill amazon-nova-reel --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Treats Nova Reel as an asynchronous production service for video-generation tasks via Amazon Bedrock. It plans shots, validates inputs, requires an exact approval before submission, submits with an idempotency token, persists the invocation ARN, and promotes only validated S3 artifacts. It enforces staying within the supported model/region, checks completion before EOL, and requires an explicit paid asynchronous run with recorded exit routes.
How it works
- Establishes the current contract and cautions against setting Nova Reel as default due to lifecycle constraints; communicates model availability and EOL dates.
- Requires choosing one of three modes: TEXT_VIDEO, MULTI_SHOT_AUTOMATED, or MULTI_SHOT_MANUAL, with specific input limits and guarantees (fps, dimension, seed handling).
- Provides guidelines for direct motion description, continuity, and shot planning using a production heuristic (continuity bible).
- Builds valid requests with explicit structures for each mode, including taskType, text/images, and videoGenerationConfig (duration, fps, dimension, seed).
- Implements gatekeeping for paid submissions with explicit pricing guidance, approval records, and validation of digest-based approvals before execution.
- Includes dry-run example logic that computes a digest from an approval envelope and requires EXECUTE=1 to proceed; enforces region/model constraints and EOL checks.
- Emphasizes that the job is asynchronous, has no native audio, and that outputs must be delivered to S3 with proper approvals and provenance.
When to use it
Use when you need to produce video content with Nova Reel capabilities in a controlled, auditable manner: ensure the exact model in the exact region is available, confirm completion before EOL, and require an explicit approval envelope before running.
What it can touch
- Model identifiers: "amazon.nova-reel-v1:1" in region us-east-1 (and possibly others for legacy contexts only).
- Output: S3 URIs for input and output as part of the approval and invocation process.
- Configuration fields: taskType, textToVideoParams, multiShotAutomatedParams, multiShotManualParams, videoGenerationConfig.
Caveats
- Requires up-to-date verification of price and lifecycle evidence prior to execution; EOL date is 2026-09-30 for Legacy access.
- Legacy access constraints prevent migrating new work to legacy models; only approved workloads may use Reel 1.1 in supported regions.
- Production relies on asynchronous execution, with potential for failure if approvals, region, or lifecycle conditions are not met.
# Amazon Nova Reel production Treat Nova Reel as an asynchronous production service, not a synchronous clip function. Plan the shots, validate every input, obtain an exact approval, submit once with an idempotency token, persist the invocation ARN, and promote only validated S3 artifacts. All volatile facts in this skill were verified against first-party AWS sources on **2026-07-10**. Recheck mode
What does the amazon-nova-reel skill do?
Produce and operate Amazon Nova Reel video-generation jobs through Amazon Bedrock. Use for Nova Reel text-to-video, image-conditioned animation, automated or manual multi-shot storyboards, async S3 delivery, cost and approval gates, production continuity, output custody, and AWS-specific safety, privacy, IAM, and provenance decisions.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill amazon-nova-reel --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.