Design teams need consistent prompts for Stitch projects. This skill analyzes project screens and produces a DESIGN.md guide with colors, typography, components, and layout rules.

Hard-coded styles and raw platform elements create inconsistent interfaces. This skill applies reusable design tokens, core components, and established layout patterns.

Managing Canva designs, exports, assets, and folders manually slows content teams. This skill gives Claude, Codex, and Claude Code structured Rube MCP workflows for Canva automation.

Brand assets can drift from Anthropic color and typography guidance. This skill helps apply referenced colors, fonts, and visual styling to presentations, documents, and design drafts.

Teams need consistent Anthropic-style visuals across documents and slides. This skill provides palette, typography, and layout guidance for Claude, Codex, and Claude Code.

Accessibility barriers can exclude users and create compliance risk. This skill structures WCAG audits, testing evidence, prioritized findings, and remediation guidance.

Teams often design flows from assumptions and miss accessibility issues. This skill guides research, structure, interaction design, and review using UX best practices.

Responsive email work often fails across clients, devices, and dark mode. This skill guides structured audits, module planning, and handoff checks for reliable email production.

Template builders can drift from Sent contracts and expose unsafe submission flows. This skill guides precise editors, previews, validation, and review controls.

Mascot concepts often become detailed illustrations that fail at small sizes. This skill creates simple, product-relevant logo directions with consistent generation constraints.

Teams need repeatable text-to-video prompts without guessing every RunComfy option. This skill gives Claude, Codex, and Claude Code a focused Wan 2.7 workflow for prompts, audio URLs, durations, aspect ratios, and outputs.

Changing video aspect ratios can crop important action or leave empty space. This skill guides RunComfy outpainting workflows that extend the frame while preserving the subject.

Short generated clips often need more time, cleaner endings, or connected story beats. This skill helps Claude, Codex, and Claude Code extend approved videos with RunComfy.

Video edits often fail when the wrong model handles the job. This skill routes each request to a RunComfy model with matching prompts and limits.

Teams need a repeatable way to run RunComfy media models from scripts. This skill guides CLI install, authentication, model runs, polling, and downloads.

Image edit workflows can drift when prompts do not protect identity, framing, or brand details. This skill gives Claude, Codex, and Claude Code a practical RunComfy workflow for targeted Nano Banana 2 edits.

Teams need clear controls for Kling 3.0 video generation across quality tiers. This skill helps choose the right RunComfy endpoint and prepare text-to-video or image-to-video requests.

Still images need the right model and prompt to become useful video clips. This skill routes image-to-video requests to RunComfy models with matching settings and examples.

Mask-driven image edits can be slow when prompts, masks, and model choices are handled manually. This skill guides Claude, Codex, or Claude Code to run RunComfy inpainting with the right model and inputs.

Choosing the right image editing model can waste time and credits. This skill maps each edit request to the best RunComfy route and prompt pattern.