DS Skills Pipeline is a command-line workflow that turns a design system's source code into structured skills for coding agents. It extracts verified tokens, components, icons, assets, usage patterns, and import paths, then generates and verifies reference files that agents can use when working with the design system.
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.
git clone --depth 1 https://github.com/vercel-labs/design-systems-to-agent-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/commands/vercel-labs/design-systems-to-agent-skills/1-interview)<a href="https://agentmods.dev/commands/vercel-labs/design-systems-to-agent-skills/1-interview"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/1-interview/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/commands/vercel-labs/design-systems-to-agent-skills/1-interview"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/1-interview.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 | $0.00000 | $0.02737 |
| Opus 5 | $0.00000 | $0.01368 |
| Sonnet 5 | $0.00000 | $0.00547 |
| Haiku 4.5 | $0.00000 | $0.00274 |
Grade A, and why
1-interview 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 1: Discovery Interview
Required Capabilities
- File read/write
- Shell command execution (mkdir, git)
- User interaction (asking questions, receiving answers)
Objective
Run Stage 1 of the design system skill generation pipeline: interactive discovery.
You are the entry point of a 6-stage pipeline that transforms design systems into agent-consumable skills. Your job is to interview the user about every scoping decision, then persist those decisions to disk so subsequent stages can run from a fresh session if needed.
The pipeline stages:
- Interview — YOU ARE HERE. Scope decisions through conversation.
- Extract — Extract verified facts from source code.
- PRD — Generate a closed PRD with zero open questions.
- Generate — Parallel skill file generation (fresh session recommended).
- Assets — Exhaustive asset catalog generation (icons, logos, etc.).
- Verify — Programmatic verification (no agent session needed).
Process
Step 1: Identify the source
If the user provided a source repo path, use that. Otherwise ask:
Where is the design system source code on disk?
Once you have the path, verify it exists, then read ONLY these high-level files:
README.mdor equivalentavailable-components.mdor equivalent component inventoryinstructions/directory (if present — may contain AI-friendly docs)- Root
package.json(for name, version, peer dependencies)
Do NOT read individual component source files (TypeScript interfaces, style files). That is Stage 2's job. Budget ~15% of your context window for this entire interview.
Step 2: Setup
Determine the design system short name (lowercase, no spaces — e.g., "andes", "geistcn"). Ask the user to confirm.
Then create the output structure:
mkdir -p context/{ds}/01-decisions
mkdir -p context/{ds}/02-verified-facts/components
mkdir -p skills/{ds}/references/{guides,components}
Create the initial decisions file at context/{ds}/01-decisions.md:
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 · 274 lines · 0 tokens per session scan A 4f590653f1d0
1-interview is a command published in the GitHub repository vercel-labs/design-systems-to-agent-skills (37 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,737 tokens. 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 2026-08-30.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
team-ui
Orchestrate UI/UX design team.