Skip to main content
A skill is a reusable creative recipe — a named markdown playbook the agent follows end-to-end when you invoke it. Think of it as a prompt template with teeth: structured enough that the agent executes it reliably, flexible enough that you can still hand it new subjects and contexts. Good candidates for skills:
  • A “hero shot” recipe that always produces the same composition, lighting, and finish
  • A “story reel” that always builds a 4-scene narrative from a single product
  • A “platform pack” that turns one idea into Instagram square + Reel + LinkedIn variants
  • A “brand audit” that runs a consistent visual analysis across saved inspirations
If you’re copy-pasting the same multi-step prompt more than twice, it belongs in a skill.

​
Where skills live

Open Assets from the nav and switch to the Skills section. This is your library — every skill in the workspace shows up here. Two ways to view the library, switchable with the Grid / List toggle next to search:
  • Grid — thumbnail cards showing each skill’s name, /slash-command, description, referenced images, author, and when it was last updated.
  • List — the same open rows used by Collections: a thumbnail or icon, name and description, updated date and author, plus a row menu (⋯) for quick Edit and Delete without opening the editor.
Your choice is remembered per browser. The author beside each row shows which workspace member created each skill — “You” for your own, and skills created by a connected agent are attributed to whoever connected it. From here you can:
  • Create a new skill (the New Skill card or row)
  • Edit a skill’s playbook, references, scope, and model pins
  • Search by name or content as the library grows
  • Delete skills you don’t use (confirmation-guarded)
When the library is empty, the Create Skill action appears directly in the first-run state so there is still one obvious way forward.

​
Memo-official starters

Every workspace ships with a starter pack authored by Memo. They sit in the same library, are read-only (open one and Duplicate it to make your own version), and connected agents get them through list_skills / get_skill like any other skill:
  • Naming Convention — the tag grammar and never-overwrite rules that keep a multi-asset production findable.
  • Scene Engine — stress-test a scene or sequence against Goal, Obstacle, Tactic, Reversal, Value Shift before spending credits.
  • Acting Task — direct character performance with playable tasks instead of emotion labels.
  • Blocking Map — exact multi-character staging via a color-coded schematic sent as a reference.
  • CINEDANCE — production-ready cinematic video prompts: references, blocking, optics, physics, lighting.
  • Motion Design — render-ready 15-second launch and motion-graphics video prompts: one core mechanic, locked palette, beat sheet, copy-list contract, fully silent.

​
The editor

Click New Skill and the editor opens as one focused document:
  • Name + description in the header. The description is the one-liner shown in the / menu and the hint that tells the agent when this skill applies.
  • Applies to — scope the skill to one brand kit or keep it General (all brands). Kit-scoped skills show up on that kit’s page and are labeled in the library.
  • Workflow — the markdown playbook. Write it like a brief, or just paste a prompt that already works — if you’ve refined a multi-step prompt anywhere else, dropping it in here is creating a skill. ## Step headings become the numbered plan the agent presents before executing. Type @ to reference brand assets, colors, or instructions inline — each mention becomes a chip and travels with the skill.
  • Attached references — optional, per skill. Attach images only when the skill should reproduce something specific every run — a product, a character, a style. Attached images are shown to the agent and included in every generation the skill makes. Leave it empty and you have a pure text skill; you can still @mention assets at invocation time for one-off turns. Brand assets attach directly, and picks from Generations or Inspirations are automatically promoted to brand assets first, so any image you’ve ever made or saved can anchor a skill.
Style and extra directions live inside the playbook as ## Style and ## Directions sections — one document, nothing to drift. Which model renders the output is deliberately not part of a skill: you choose that where you generate (workspace default, or per-deliverable on a brief), so one recipe works across every model.

​
Ask the agent instead

In Studio chat, select an image on your canvas and ask the agent to turn it into a skill (“save this as a reusable recipe”). The agent drafts a skill card in the conversation — playbook + references — and Save Skill puts it in your library with the /slug ready to use.

​
Invoking a skill

Two ways to call a skill in Studio chat:

​
Slash command

Type / in the composer. A picker appears showing your skills (and Workflows — they share the same rail), filtered as you type.
The agent reads the playbook as the brief for the turn — your free-text addition is the subject. Referenced images are injected automatically: the agent sees them, and their IDs are attached to every generation server-side, so brand consistency doesn’t depend on the model remembering.

​
@mention

Type @ followed by a skill name — useful when combining a skill with a brand kit mention in one message (@Acme Brand @story-reel ...).

​
Plan-then-execute

For skills that produce multiple deliverables (a storyboard recipe, a platform pack), the agent proposes a numbered plan first — usually as a creative brief on your canvas. You review, adjust ratios and references, and click Generate. The skill’s prose controls the plan; your confirmation controls execution. Skills slot neatly into the Creative Brief flow.

​
How aspect ratio and quality get chosen

Skills hold the creative intent — style, references, directions. They don’t hold a fixed aspect ratio or quality, so one /hero-shot can produce a 1:1 feed post AND a 16:9 banner:
  • Single-output skills — the agent asks once for ratio and quality, then generates. If the playbook already specifies a ratio (“produce a vertical 9:16”), it skips the question.
  • Multi-deliverable skills — the agent builds a brief with one deliverable per output, each with its own ratio and quality row, enforced server-side at generation.

​
Combining skills with brand kits

A General skill works with any brand: @mention a kit in the same message and the skill provides the recipe while the kit provides the identity.
A kit-scoped skill carries its brand by itself — it lives on that kit’s page and is what a connected agent gets pointed to when it loads that brand’s kit.

​
Skills over MCP

Connected agents (Claude, or anything speaking MCP) work with the same library:
  • list_skills returns lightweight summaries — name, slug, description, step count — so an agent can pick the right skill cheaply.
  • get_skill returns the full markdown playbook for the chosen skill; the agent follows it like a brief.
  • create_skill / update_skill let an agent capture a workflow you refined in conversation, or improve an existing playbook — attributed to you in the library’s Author column. Updates keep an automatic copy of the previous version, so an agent rewrite is never a one-way door.
This is the same skill either way: edit it in the app, run it from an agent, or the reverse.

​
Editing skills

Changes apply to future invocations immediately — already-generated work doesn’t change. If a skill produces inconsistent output, tighten its prose: be specific about deliverable count, style anchors, and required references. The editor opens with every attached reference tokenized inline as chips, so you can see what the skill relies on at a glance.

​
Tips

  • Start from a prompt you’ve already perfected. If a multi-step prompt keeps working, paste it into a skill and name it.
  • Make skill names short. You’ll type them after a slash. /hero-shot beats /product-hero-shot-three-angles.
  • Keep each skill single-purpose. One recipe per skill. If it’s drifting into “and also does X,” split it.
  • Write the playbook in the agent’s voice. Be specific about what to produce; leave room in how, so your brand kit can do its job.
  • Attach the concrete references. If the prose mentions “the character” or “the product,” make sure that image is actually attached — otherwise the agent has prose pointing at nothing.
  • Use ## Style for the through-line, ## Directions for the rules. Style = tone (“warm editorial, matte finish”). Directions = constraints (“never crop the logo, always leave margin top”).
  • Test each skill with two different subjects before relying on it. If output quality differs wildly between subjects, the prose needs tightening.