balise-affinity-mcp
Automate Affinity by Canva through the Affinity MCP and JavaScript SDK for manipulating open documents, selected objects,…
Direct and produce contemporary rendered motion graphics from brief to validated export. Use for brand motion, launch teasers, social clips, title sequences, kinetic typography, animated explainers, event videos, identity motion, loops, storyboards, animatics, critiques, or fast
$ npx -y skills add mrstev3n/balise-skills --skill balise-motion-graphic --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/balise-motion-graphicContext preview
The summary Claude sees to decide when to auto-load this skill.
Direct and produce contemporary rendered motion graphics from brief to validated export. Use for brand motion, launch teasers, social clips, title sequences, kinetic typography, animated explainers, event videos, identity motion, loops, storyboards, animatics, critiques, or fast
name: balise-motion-graphic description: Direct and produce contemporary rendered motion graphics from brief to validated export. Use for brand motion, launch teasers, social clips, title sequences, kinetic typography, animated explainers, event videos, identity motion, loops, storyboards, animatics, critiques, or fast prototypes—especially with HyperFrames or Remotion. Guide users who want to arbitrate, and autonomously choose direction, tools, assets, sound, format, and prototype scope when the user delegates decisions or lacks motion expertise. Do not use as the primary skill for interactive web motion, hover or tap feedback, scroll choreography, page transitions, or gesture-driven UI.
Act as motion director and producer. Turn an incomplete request into a contemporary visual, temporal, asset, sound, and delivery system, then carry it through the cheapest useful proof to a validated render when production is authorized.
First respect what the user authorized:
Then choose how decisions are made:
1. **Guided mode.** Use when the user asks for options or wants to approve the creative direction. Present up to two genuinely distinct directions and pause only at declared decision gates. 2. **Autonomous mode.** Use when the user requests speed, delegates choices, provides a vague brief, or clearly lacks motion vocabulary. Choose the direction, engine, assets, sound posture, format, fallbacks, and first prototype; explain decisions after producing evidence. 3. **Hybrid mode — default.** Recommend one direction, state the rationale briefly, and produce the smallest representative proof. Surface alternatives only for meaningful tradeoffs.
Inspect the project before asking. Ask at most three questions, only when facts, rights, cost, or distribution context would materially change or block the work. Never make a novice design the production process.
Use this skill for motion that becomes a rendered video or self-contained graphic sequence such as MP4, WebM, GIF, Lottie, image sequence, or deterministic composition.
Route interactive behavior—hover, press, menus, scroll, navigation, gestures, runtime interruption, and UI frequency—to `balise-webmotion` when available, otherwise to an equivalent interactive web-motion workflow. Three.js and shaders belong here only as deterministic rendered layers. Treat Lottie here as an asset or delivered sequence, not a state-driven UI system.
For inspiration, copying, reconstruction, and remix are legitimate inputs. A faithful reprise is acceptable when requested. Otherwise adapt the material through context, combination, or execution. Do not create provenance records for inspiration-only references. Record usage terms only for external assets, fonts, footage, or audio actually integrated or redistributed.
Use specialized capabilities when available: `balise-visual-references` for live research, image generation for visual assets, `create-video-storyboard` for shot planning, `motion-design` for craft, and exposed HyperFrames or Remotion skills for implementation. Continue with direct research, storyboarding, composition, and rendering when those capabilities are absent. Verify actual tool exposure first; never claim an unavailable MCP, skill, CLI, or render path was used.
For local video references, run:
python3 scripts/extract_reference_frames.py reference.mp4 frames/ --frames 16
Des skills portables pour Claude Code, Codex, Cursor, le Figma Agent, Figma Make et les autres outils compatibles avec le standard Agent Skills. Installez un skill précis ou une collection prête à l’emploi. Chaque skill utilise SKILL.md comme format canonique.
Automate Affinity by Canva through the Affinity MCP and JavaScript SDK for manipulating open documents, selected objects,…
Understand, audit, and reason about Affinity by Canva documents, workflows, object choices, text modes, UI overlays,…
Structurer une idée de marque encore floue et produire une exploration argumentée du nom et du territoire de marque. Utiliser…
Stress-tests UI content resilience across design files, screenshots, prototypes, source code, and rendered interfaces. Use when…
Architecturer, auditer, construire, intégrer et faire évoluer un design system robuste de Figma au code. Utiliser pour cadrer un…
Audits and prepares designs, specifications, prototypes, design-system artifacts, and implemented interfaces for developer…