Skip to main content
A skill is one unit of work. The picker, the pricing table, the API, and MCP all read the same catalogue. Slugs on /skills/<slug> match POST /api/v1/run/{skill}.
Skills catalogue with Everything, Photo, Video, Audio chips and Popular cards for Background remover, New perspectives, and Add captions

The public skills catalogue. Filter by photo, video, or audio. Popular sits at the top.

Prices below are the defaults. Some skills change price with an option (upscale target, model, clip count). GET /api/v1/skills is the live list, and it does not need a key.

Kinds

No skill is gated on plan name today. Credits do the gating. Cyclops can run any skill it can afford. See Free tools and Generators.
Add captions skill page with a before and after talking-head clip and the Workbench dropzone

Add captions. Each skill page is the Workbench with that step already on the line.

Podcast clip maker skill page with before and after vertical clips

Clips. A long episode becomes a set of short cuts. Captions can sit under it and run on each clip.

Podcast cover art generator with a Hard Refresh cover example and a spelling caveat on the Workbench

Podcast cover art. Drop an episode, a photo, a logo, or paste an Apple Podcasts, Spotify, or RSS link.

Background remover skill page

Background remover. Two credits per image.

Credit-priced skills

Per-minute rates round up to a whole minute, with a one-minute floor.

Make

Clips, YouTube thumbnail, Video Multiplier, and Graphic Multiplier make a set. Steps below run once on each file. Two sets cannot share a line.
YouTube thumbnail skill page with a before-and-after talking-head and a caveat that headlines are written from speech

YouTube thumbnail writes a set of 1280×720 frames. Headlines come from what is said.

Fix

Change

Describe

Finish

API-only skills

These need a second image (reference_url or reference_job_id). They have no Workbench page. See Run a skill.

Caveats worth reading on the skill page

A few skills contradict a promise the marketing line makes. Those caveats are shown on the tool page before you spend:
  • Poster — read the headline before you post it. Set type is still the thing a model gets wrong.
  • Clips — moments are picked from speech, not from the picture.
  • YouTube thumbnail — headlines are written from what is said.
  • Clean audio — heavy room echo is the one thing this cannot undo.
  • Smart reframe — follows faces. A product demo with nobody in frame is centre-cropped.
  • Lip-sync — works best on one face looking at the camera.
Prompts are capped at 2,000 characters.