sergekostenchuk/ui-ux-agent-skill-system

figma-canvas-editor

Create and edit native Figma canvas objects with MCP when explicitly scoped.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/sergekostenchuk/ui-ux-agent-skill-system --skill figma-canvas-editor

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Figma Canvas Editor

Use this skill for direct Figma mutations. Read-only understanding belongs to figma-context-reader; token/library governance belongs to figma-design-system-sync.

Modes

  • create: add frames, sections, components, objects, or layouts.
  • update: change selected nodes, layout, styles, variables, text, or component instances.
  • delete: remove effects, nodes, variants, or obsolete objects only with explicit scope.
  • figjam: edit FigJam objects, sections, connectors, and shapes.
  • slides: edit Figma Slides content when the Slides skill is available.

Workflow

  1. Confirm target file/page/frame/node and exact mutation scope.
  2. Prefer duplicating important frames before broad changes.
  3. Invoke figma:figma-use before any use_figma call. For FigJam or Slides, invoke the relevant installed Figma skill as well.
  4. Read current metadata before editing.
  5. Apply changes using native Figma objects, auto layout, components, variables, and styles where possible.
  6. Read metadata back after editing and capture screenshot/export evidence when available.
  7. Report changed targets, evidence, skipped checks, and rollback path.

Mutation Boundaries

  • Do not make broad destructive changes without explicit approval.
  • Do not detach instances, flatten vectors, rasterize editable text, or remove variables/styles unless the user requests that outcome.
  • Do not invent node IDs or claim a selected node exists without MCP evidence.
  • Keep design-system naming consistent with the existing file when visible.

Output Shape

Use assets/canvas-edit-report.md.

Validation And Eval

  • Verify that every mutation report includes target, scope, before evidence, after evidence, and skipped checks.
  • Treat missing readback as Skipped or Blocked, not as successful mutation evidence.
  • Use evals/evals.json to forward-test scoped creation and destructive-delete prompts.

Related by task

from this repository

More skills

All skills
sergekostenchuk
Community

admin-ui-builder

Use when admin/CMS/back-office screens need to be built or specified after admin-ui-orchestrator defines roles, permissions, workflows, and safety gates. Covers tables, forms, editors, moderation queues, dashboards, CRUD surfaces, and state coverage without production destructive actions.

installs
1
GitHub stars
32
Updated
Sep 13
sergekostenchuk
Community

admin-ui-orchestrator

Use when a project needs admin/CMS/back-office UI architecture: roles, permissions, content workflows, AI assistant boundaries, audit logs, destructive-action confirmations, and builder handoff. Planning only; do not perform production admin actions or expose secrets.

installs
1
GitHub stars
32
Updated
Sep 13
sergekostenchuk
Community

analytics-setup-architect

Use when a website or web app needs privacy-aware analytics architecture: GA4, Yandex Metrica, self-hosted analytics, consent, UTM, event taxonomy, funnels, dashboards, and launch verification. Do not mutate real analytics accounts or store credentials without explicit approval.

installs
1
GitHub stars
32
Updated
Sep 13
sergekostenchuk
Community

image-layer-alignment-validator

Validate whether two raster image layers are suitable for reveal, before/after, morph, mask-compositing, or interactive cursor reveal effects. Use when comparing base/reveal images, checking whether the main subject stayed in the same position, separating primary subject drift from background or secondary-object differences, producing annotated overlays/difference maps, or deciding whether an image layer must be shifted, scaled, cropped, or regenerated before frontend compositing.

installs
1
GitHub stars
32
Updated
Sep 13