What are Agent Skills?
Agent Skills are structured playbooks that encode the complete API call sequence, async completion pattern, error handling, and rate limit considerations for a common Framelane workflow. They are designed to be loaded by AI agents (Claude, GPT-4, Cursor Agent, etc.) to eliminate the need for the agent to figure out the multi-step API flow from scratch.Loading skills via MCP
Skills are exposed as MCP resources from the Mintlify-hosted MCP server:Available skills
| Skill | What it orchestrates |
|---|---|
render-video | source URL → create render → await webhook → download |
transcribe | audio/video → transcribe → return transcript with word timestamps |
generate-social-clip | source + time range → trim, crop 9:16, transcribe, multi-style captions → render |
remove-background | image/video → task → await → download |
super-resolution | upscale → task → await → download |
batch-tasks | submit N tasks in parallel, track all, return results map |
webhook-setup | register endpoint, verify signature, handle retries |
Skill format
Each skill is a structured YAML document that encodes:- Goal: what the skill accomplishes
- Prerequisites: required API keys, webhook setup
- Steps: ordered API calls with exact request shapes
- Async pattern: how to wait for job completion
- Error handling: which error codes to expect and how to recover
- Rate limits: relevant limits to respect