How do I install the Narova Runway skill?

Run npx skillmds@latest add ammar-hasan/narova-runway in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Narova Runway safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Narova Runway?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Narova Runway free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Narova Runway?

ammar-hasan (@ammar-hasan) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Narova Runway by ammar-hasan — Agent Skill

Name: Narova Runway
Author: ammar-hasan

Narova Runway

Use this optional Narova companion when the user explicitly requests Runway video generation, a Runway model such as gen4.5, or a Runway-generated clip for a Narova scene. It installs and registers a separate Runway video worker without adding cloud dependencies or credentials to the main Narova skill. Do not use it for ordinary local rendering; Narova remains local-first.

ammar-hasan Updated Sep 17, 2026

File contents

Narova + Runway

Use this skill as an optional external video-generation provider for Narova. Keep every Runway API detail in this companion and communicate through the generic narova-video-provider/v1 JSONL protocol. Let Narova own staging, provenance, generation recipes, the asset registry, caching, and rendering.

Requires the standalone Narova CLI, the Narova skill, Python 3.10+, network access, a Runway API account with model access, and RUNWAYML_API_SECRET.

Setup

Install the standalone Narova CLI as described by the narova skill, then install narova and narova-runway as independently selected skills from ammar-hasan/narova.
Locate this installed skill from the directory containing this SKILL.md; call it <narova-runway-skill-dir>.

Verify the worker:

bash <narova-runway-skill-dir>/tool/setup.sh

Set the key only in the environment that runs Narova:
```
export RUNWAYML_API_SECRET="..."
```

Explicitly register and verify the worker:

narova providers add \
  <narova-runway-skill-dir>/tool/provider.json
narova providers doctor runway

Read references/configuration.md before generating. It documents option mapping, errors, security, billing, and removal.

Operating rules

Treat generation as an explicit, billed network operation. The authored prompt is sent to Runway.
Keep RUNWAYML_API_SECRET only in the process environment or a user-managed secret store; never put it in reel.config.mjs.
Do not add the Runway SDK to Narova or modify Narova's setup. This worker uses the Python standard library.
Do not copy this worker into the Narova skill. Registration composes two independently installed skills.
Do not automatically retry a failed submission. The remote task may already exist and may be billed even if the connection fails before Narova sees it.
Let Narova publish the generated clip and its recipe only after worker success; worker failures leave the final asset and registry unchanged.

---name: narova-runwaydescription: Use this optional Narova companion when the user explicitly requests Runway video generation, a Runway model such as gen4.5, or a Runway-generated clip for a Narova scene. It installs and registers a separate Runway video worker without adding cloud dependencies or credentials to the main Narova skill. Do not use it for ordinary local rendering; Narova remains local-first.license: Apache-2.0---# Narova + RunwayUse this skill as an optional external video-generation provider for Narova.Keep every Runway API detail in this companion and communicate through thegeneric `narova-video-provider/v1` JSONL protocol. Let Narova own staging,provenance, generation recipes, the asset registry, caching, and rendering.Requires the standalone Narova CLI, the Narova skill, Python 3.10+, networkaccess, a Runway API account with model access, and `RUNWAYML_API_SECRET`.## Setup1. Install the standalone Narova CLI as described by the `narova` skill, then install `narova` and `narova-runway` as independently selected skills from `ammar-hasan/narova`.2. Locate this installed skill from the directory containing this `SKILL.md`; call it `<narova-runway-skill-dir>`.3. Verify the worker: ```bash bash <narova-runway-skill-dir>/tool/setup.sh ```4. Set the key only in the environment that runs Narova: ```bash export RUNWAYML_API_SECRET="..." ```5. Explicitly register and verify the worker: ```bash narova providers add \ <narova-runway-skill-dir>/tool/provider.json narova providers doctor runway ```Read [references/configuration.md](references/configuration.md) beforegenerating. It documents option mapping, errors, security, billing, andremoval.## Operating rules- Treat generation as an explicit, billed network operation. The authored prompt is sent to Runway.- Keep `RUNWAYML_API_SECRET` only in the process environment or a user-managed secret store; never put it in `reel.config.mjs`.- Do not add the Runway SDK to Narova or modify Narova's setup. This worker uses the Python standard library.- Do not copy this worker into the Narova skill. Registration composes two independently installed skills.- Do not automatically retry a failed submission. The remote task may already exist and may be billed even if the connection fails before Narova sees it.- Let Narova publish the generated clip and its recipe only after worker success; worker failures leave the final asset and registry unchanged.

Frequently asked questions