ai-visual
$
npx mdskill add arcasilesgroup/ai-engineering/ai-visualVisual design artifact creation. Generates custom design philosophies (aesthetic movements interpreted through form/space/color/composition + images/graphics/shapes/patterns) and expresses them visually with minimal text accent (90% visual, 10% essential text). User input is foundation, not constraint — the philosophy emphasizes visual expression and artistic interpretation.
SKILL.md
.github/skills/ai-visualView on GitHub ↗
--- name: ai-visual description: Produces static visual design artifacts (posters, banners, flyers, branding pieces, cover art, identity compositions) by composing aesthetic philosophies into HTML/SVG and rendering to PDF/PNG. Trigger for 'create a poster', 'design a banner', 'branding visual', 'marketing graphic', 'cover art for', 'identity composition'. Not for UI interfaces; use /ai-design instead. Not for animation; use /ai-animation instead. Not for presentation decks; use /ai-slides instead. Not for AI-generated photographs; use /ai-media instead. effort: mid argument-hint: "[visual artifact description or brief]" mode: agent tags: [visual-design, poster, banner, branding, artifact] model_tier: sonnet mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-visual/SKILL.md edit_policy: generated-do-not-edit --- # Visual ## Purpose Visual design artifact creation. Generates custom design philosophies (aesthetic movements interpreted through form/space/color/composition + images/graphics/shapes/patterns) and expresses them visually with minimal text accent (90% visual, 10% essential text). User input is foundation, not constraint — the philosophy emphasizes visual expression and artistic interpretation. ## When to Use - Creating posters, banners, flyers for events or campaigns - Designing branding pieces and identity materials - Building marketing and communication visuals - Composing visual artifacts for presentations or reports - Creating art-directed pieces with strong aesthetic philosophy - Any static visual output (PDF, PNG) with high artistic direction ## Process 1. **Understand the brief** -- what is the artifact for? Who is the audience? What feeling should it evoke? 2. **Read handlers/philosophy.md** -- create a design philosophy (aesthetic movement) for this artifact 3. **Name the movement** (1-2 words) -- e.g., "Brutalist Joy", "Chromatic Silence", "Metabolist Dreams" 4. **Articulate the philosophy** (4-6 paragraphs covering: space/form, color/material, scale/rhythm, composition/balance, visual hierarchy) 5. **Read handlers/canvas-creation.md** -- apply the visual standards and craftsmanship rules 6. **Deduce the subtle reference** -- identify conceptual threads from the brief. Embed within the art -- sophisticated for those who know the subject, masterful abstract composition for others 7. **Create the canvas** -- express the philosophy visually. 90% visual design, 10% essential text 8. **Self-review** -- does this look like it belongs in a museum or magazine? If not, refine. 9. **Read handlers/examples.md** for inspiration if needed ## Rendering Generate as self-contained HTML, then render to PDF via browser print or Puppeteer. For vector output, use SVG. ## Refinement Rules When told work isn't perfect enough: - Refine what exists rather than adding new graphics - Make composition more cohesive with the art - Ask: "How can I make what's already here more of a piece of art?" - Avoid new functions or shapes -- polish existing elements ## Multi-Page Support Additional pages should follow the same design philosophy but distinctly vary. Bundle in same PDF or multiple PNGs. Pages should almost tell a story in tasteful way while exercising full creative freedom. ## Integration Called by: user directly, `/ai-design`, `/ai-media`. Consumed by: `/ai-slides` (aesthetic philosophy), `/ai-media` (visual direction). Calls: none — produces final artifacts. See also: `/ai-design` (UI), `/ai-animation` (motion). ## Examples ### Example 1 — event poster User: "design a poster for a developer conference called 'Edge Runtime 2026'" ``` /ai-visual event poster for Edge Runtime 2026 developer conference ``` Defines a movement (e.g. "Brutalist Compute"), articulates philosophy across space/color/composition, and renders an HTML→PDF poster with 90% visual / 10% text emphasis. ### Example 2 — branding piece for product launch User: "create cover art for the v1.0 release announcement" ``` /ai-visual cover art for product v1.0 release announcement ``` Generates a multi-page PDF where each page follows the same philosophy with distinct variation, suitable for press kit and social. ## Common Mistakes - Using generic stock photo aesthetics instead of creating a philosophy - Lack of craftsmanship -- every spacing, color choice, and alignment must scream expertise - Announcing the conceptual reference instead of embedding it subtly $ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.