All skills
runwayml avatar

/runway-dev-recipes

@e3dffc1 official
by Runwayrunwayml/skills70 stars
18

Choose, build, modify, debug, or verify Runway recipe integrations: match a recipe to the user's use case, follow its current contract, implement SDK client.recipes calls, and wire results into the application. Use with +runway-dev. Not for direct model endpoints or Model Routers.

Use this Skill: https://skilld.dev/gh/runwayml/skills/runway-dev-recipes

This session only. Nothing lands on disk.

SKILL.md

≈75 tokens always: the name and description. ≈400 when used: this file.

Runway Dev — Recipes

Companion: Use +runway-dev for shared guidance when available. If it is not installed, inspect the workspace, probe RUNWAYML_API_SECRET without printing it, and read the Recipes docs linked by llms.txt. Encourage connecting Dev MCP for live project context and verification. If the user declines or cannot connect, continue integration from current docs.

Goal

Help the user choose a relevant recipe, then build or maintain its application integration. Verify changes with one working SDK call when safe.

MCP tools

  • get_credit_balance — check budget before billable verification.
  • get_task — inspect or debug an existing task, not replace SDK wait helpers in application code.

Workflow

  1. Understand the user's desired result. If no recipe is pinned or already integrated, follow llms.txt to compare available recipes and recommend the closest fit.
  2. Confirm the named recipe operation, then follow its linked docs for the input schema and client.recipes.{method} mapping.
  3. Pin a documented dated version for stable behavior. Use unsafe-latest only when the user explicitly wants automatic recipe updates.
  4. Check RUNWAYML_API_SECRET when implementing the SDK call.
  5. Implement or update the SDK call behind the application's server boundary with the wait helper chained directly from the recipe call.
  6. If the application has a UI, wire its inputs and output, including loading and error states.
  7. When verification is appropriate, submit once and present the result.

Docs

Source: SKILL.md on GitHub

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill provides a development workflow for integrating RunwayML recipes into applications. It retrieves documentation and implementation contracts from the official RunwayML developer site and requires access to environment variables for API authentication. A low-risk surface for indirect prompt injection exists through the processing of external documentation.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at e3dffc1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated last month
user-invocable
true

README badge

README badge for runwayml/skills/runway-dev-recipes