Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add valtterimelkko/agent-workflow-skills --skill artifact-variationsgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/artifact-variations)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/artifact-variations"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/artifact-variations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/artifact-variations"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/artifact-variations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00164 | $0.02528 |
| Opus 5 | $0.00082 | $0.01264 |
| Sonnet 5 | $0.00033 | $0.00506 |
| Haiku 4.5 | $0.00016 | $0.00253 |
Grade A, and why
artifact-variations scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact Variations
Use this skill when the user needs to pick a favorite from a set of options visually rather than describe what they want in words.
The core idea: instead of iterating over a single design through many rounds of feedback, generate N distinct variations in one HTML artifact, let the user scroll through, pick the one (or few) they like, and then apply that choice to the real codebase. This collapses design exploration from many turns to one.
This is Layer 1 of the interactive artifact pattern — a static, one-shot artifact used as a decision surface.
When to use this skill
Use it when:
- the user asks for "variations", "options", "takes", "versions", or "a few different ways"
- the task involves picking a design direction and the user struggles to describe what they want
- the choice is subjective (layout, typography, color direction, copy tone, illustration style)
- iteration-by-description is slow and picking-by-eye would be fast
- the component, section, or output is visual enough that side-by-side viewing helps
Good examples:
- "give me 10 hero section variations for this landing page"
- "I'm not sure what the settings screen should look like — show me some options"
- "draft a few versions of this LinkedIn post so I can pick the tone"
- "what are some ways this pricing card could look"
Do not use this skill for:
- building the final artifact after the direction is already known → use the appropriate frontend/implementation skill directly
- generating a single polished component → use
frontend-designorui-ux-pro-max - design discovery that needs a full
DESIGN.mdfirst → usecli-design-studio - exploring reference sites → use
skill-uiorawesome-design-md
The workflow
1. Clarify scope and mode
Before generating, nail down:
- What is the unit? One component, one section, one full page, or just the copy
- How many variations? Default to 6–10. Go higher (15–25) when the user explicitly wants to explore widely, lower (3–5) when the decision space is small or the user has already narrowed down candidates
- What stays constant? Brand, theme, content structure, or nothing? The constants anchor the comparison
- What should vary? Layout, typography, color direction, density, tone, illustration style, or a mix
- Wide or refinement round? If this is a first pass, maximise diversity across the full option space. If the user has already picked rough favourites from a previous round, bias toward winners and prune the rest — don't serve 10 near-identical refinements when 3–4 focused ones would do
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 171 lines · 164 tokens per session scan A 325576638ad4
artifact-variations is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 2,528 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.