Vercel Labs' DS Skill Extraction Workshop is a starter repository for a workshop that teaches developers to turn a design system into reusable agent skills and use one to generate a Primer React interface. It guides participants through setup, generation, and visual review of the resulting application. The catalogue entries provide the skills and instructions used in the workshop.
Borrowing it
Nothing to install: this file belongs to vercel-labs/ds-skill-extraction-workshop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vercel-labs/ds-skill-extraction-workshop/main/.claude/skills/extract-ds-skill/SKILL.mdgit clone --depth 1 https://github.com/vercel-labs/ds-skill-extraction-workshopWrote 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/vercel-labs/ds-skill-extraction-workshop/extract-ds-skill)<a href="https://agentmods.dev/skills/vercel-labs/ds-skill-extraction-workshop/extract-ds-skill"><img src="https://agentmods.dev/badge/skills/vercel-labs/ds-skill-extraction-workshop/extract-ds-skill.svg" alt="Measured on agentmods" 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 | $0.15242 |
| Opus 5 | $0.00082 | $0.07621 |
| Sonnet 5 | $0.00033 | $0.03048 |
| Haiku 4.5 | $0.00016 | $0.01524 |
Grade A, and why
extract-ds-skill scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
After the user confirms (with "go" or adjustments), run `mkdir -p .extract-ds-skill-scratch/handoffs/` and write the phase-1 handoff from the template in `references/discovery.md` (`## Handoff document — phase-1.md templ How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission (what a DS skill IS)
A design-system skill is an adapter that teaches an agent how to build high-fidelity UI with a specific design system. It is not a copy of the design-system documentation. It tells the agent what to read, what APIs are public, what sources are authoritative, and how to verify that generated UI uses the system correctly.
This skill BUILDS such a skill from a real DS source. The output is the skill; this file is the recipe.
Scope (locked)
In scope: tokens, assets, component descriptions, component APIs. Out of scope: tone of voice, marketing copy, product copywriting. When you encounter a copy/naming/casing rule during extraction (e.g. "Title Case the label", "placeholder is action-oriented"), recognize it, route it - mention it in the discovery summary as a candidate for a sibling copy skill - but do NOT extract it into this DS skill.
This scope block is quoted by downstream rules (Quick Triage step 1, Agent Stance bullet 3, Anti-fabrication "Do not" list, references/component-extraction.md Shape 3). Do not paraphrase or trim it when re-citing.
One shipped (not extracted) artefact rides alongside this scope: references/design-craft.md, a DS-agnostic design-craft reference (layout, hierarchy, typography, color, spacing, motion, interactive states, anti-slop restraint) copied verbatim into every produced skill during Phase 3 from the meta-skill's assets/design-craft.md. It is static material, not extraction output — the file:line citation contract and the [VERIFY] discipline do not apply to it, it never varies by DS, and its own precedence header defers to the DS on every conflict. See references/persist.md (Design-craft materialization).
The skill runs in three labeled phases. The single human gate sits at the boundary between Phase 2 and Phase 3. Phase 1 closes with a confirmation prompt; Phase 2 closes with an approval prompt; Phase 3 writes to disk. Phase 1 and Phase 2 close with a hard stop (write handoff → cutoff message → EXIT); the user resumes in a FRESH Claude Code session via an explicit validate: / persist: resume parameter so the context window is cleared between phases.
What ships with it
60 files 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.
- AGENTS.md 4.4 KB
- assets/design-craft.md 8.3 KB
- README.md 1.4 KB
- references/anti-patterns.md 44 KB
- references/component-extraction.md 23 KB
- references/coverage-gaps.md 3.1 KB
- references/discovery.md 36 KB
- references/foundation-extraction.md 20 KB
- references/inheritance.md 7.9 KB
- references/persist.md 29 KB
- references/reference-project.md 26 KB
- references/skill-template.md 27 KB
- references/validate.md 45 KB
- scripts/check-skill-docs.sh 58 KB runs code
- scripts/check-token-coverage.sh 8.8 KB runs code
- scripts/inspect.sh 3.4 KB runs code
- scripts/probe-rendered.sh 39 KB runs code
- scripts/scaffold.sh 11 KB runs code
- scripts/tests/fixtures/fail-design-craft-drift/produced-skill/references/design-craft.md 569 B
- scripts/tests/fixtures/fail-design-craft-drift/produced-skill/SKILL.md 620 B
- scripts/tests/fixtures/fail-handoff-emission/extract-ds-skill/SKILL.md 758 B
- scripts/tests/fixtures/fail-handoff-if-confirmed/extract-ds-skill/references/discovery.md 716 B
- scripts/tests/fixtures/fail-handoff-if-confirmed/extract-ds-skill/SKILL.md 368 B
- scripts/tests/fixtures/fail-handoff-missing-components/extract-ds-skill/references/discovery.md 390 B
- scripts/tests/fixtures/fail-handoff-missing-components/extract-ds-skill/SKILL.md 341 B
- scripts/tests/fixtures/fail-inline-phase-transition/extract-ds-skill/SKILL.md 1.5 KB
- scripts/tests/fixtures/fail-lexical-deny-list/extract-ds-skill/SKILL.md 610 B
- scripts/tests/fixtures/fail-missing-examples-index/produced-skill/references/components/button.md 87 B
- scripts/tests/fixtures/fail-missing-examples-index/produced-skill/references/examples/home.md 168 B
- scripts/tests/fixtures/fail-missing-examples-index/produced-skill/references/examples/issues.md 168 B
- scripts/tests/fixtures/fail-missing-examples-index/produced-skill/SKILL.md 370 B
- scripts/tests/fixtures/fail-missing-foundations-index/produced-skill/references/components/button.md 77 B
- scripts/tests/fixtures/fail-missing-foundations-index/produced-skill/references/foundations/colors.md 362 B
- scripts/tests/fixtures/fail-missing-foundations-index/produced-skill/references/foundations/typography.md 361 B
- scripts/tests/fixtures/fail-missing-foundations-index/produced-skill/SKILL.md 368 B
- scripts/tests/fixtures/fail-no-hardcoded-paths/extract-ds-skill/SKILL.md 609 B
- scripts/tests/fixtures/fail-skill-mode-attribute-orphan/produced-skill/references/anti-patterns.md 403 B
- scripts/tests/fixtures/fail-skill-mode-attribute-orphan/produced-skill/references/components/button.md 87 B
- scripts/tests/fixtures/fail-skill-mode-attribute-orphan/produced-skill/SKILL.md 1.9 KB
- scripts/tests/fixtures/fail-skill-shell-invariants-absent/produced-skill/references/components/button.md 87 B
- scripts/tests/fixtures/fail-skill-shell-invariants-absent/produced-skill/SKILL.md 1.5 KB
- scripts/tests/fixtures/fail-slate-coverage/produced-skill/references/components/button.md 87 B
- scripts/tests/fixtures/fail-slate-coverage/produced-skill/SKILL.md 569 B
- scripts/tests/fixtures/fail-token-coverage/ds-pkg/dist/css/functional/color/accent.css 40 B
- scripts/tests/fixtures/fail-token-coverage/ds-pkg/dist/css/functional/color/border.css 39 B
- scripts/tests/fixtures/fail-token-coverage/ds-pkg/dist/css/functional/color/surface.css 40 B
- scripts/tests/fixtures/fail-token-coverage/ds-pkg/package.json 81 B
- scripts/tests/fixtures/fail-token-coverage/scratch/examples/button.md 244 B
- scripts/tests/fixtures/fail-token-coverage/scratch/wiring-extracted.md 636 B
- scripts/tests/fixtures/fail-wiring-uncited/produced-skill/references/components/button.md 87 B
- scripts/tests/fixtures/fail-wiring-uncited/produced-skill/SKILL.md 672 B
- scripts/tests/fixtures/fail-worked-example-ds-bias/extract-ds-skill/references/foundation-extraction.md 528 B
- scripts/tests/fixtures/fail-worked-example-ds-bias/extract-ds-skill/SKILL.md 289 B
- scripts/tests/fixtures/foundation-out-of-scope/extract-ds-skill/references/discovery.md 730 B
- scripts/tests/fixtures/foundation-out-of-scope/extract-ds-skill/SKILL.md 386 B
- scripts/tests/fixtures/handoff-with-components/extract-ds-skill/references/discovery.md 553 B
- scripts/tests/fixtures/handoff-with-components/extract-ds-skill/SKILL.md 376 B
- scripts/tests/fixtures/handoff-with-exclusions/extract-ds-skill/references/discovery.md 898 B
- scripts/tests/fixtures/handoff-with-exclusions/extract-ds-skill/SKILL.md 381 B
- scripts/tests/fixtures/pass-design-craft-verbatim/produced-skill/references/design-craft.md 40 B
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.
- 8d ago First seen · 474 lines · 0 tokens per session scan A 1c38c19112f1
extract-ds-skill is a skill published in the GitHub repository vercel-labs/ds-skill-extraction-workshop (11 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 15,242 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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 $ralph 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.