Skip to content
Back to search

agent-skills

Two production-grade Agent Skills: create and evaluate skills, and build Google Labs DESIGN.md systems with standalone HTML prototypes.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vdbay--agent-skills/badge.svg)](/listings/vdbay--agent-skills)

HTML

<a href="/listings/vdbay--agent-skills"><img src="/api/listings/vdbay--agent-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install everything:

npx skills add vdbay/agent-skills

Install one skill:

npx skills add vdbay/agent-skills --skill skill-creator
npx skills add vdbay/agent-skills --skill design-md-prototype

Install for every project:

npx skills add vdbay/agent-skills -g

Install for a specific agent without prompts:

npx skills add vdbay/agent-skills --skill design-md-prototype -a claude-code

Try a skill without installing it:

npx skills use vdbay/agent-skills@design-md-prototype
npx skills use vdbay/agent-skills@skill-creator --agent claude-code

Skills are installed into the current project by default. `npx skills list`, `npx skills check`, and `npx skills update` manage what is installed.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 206 lines
  1. # Agent Skills
  2. Two production-grade [Agent Skills](https://agentskills.io/specification) for building design systems and for building better skills. Both are spec-validated, evaluated in fresh contexts, and reviewed by independent judges.
  3. [![skills.sh](https://skills.sh/b/vdbay/agent-skills)](https://skills.sh/vdbay/agent-skills)
  4. [![Validate skills](https://github.com/vdbay/agent-skills/actions/workflows/validate.yml/badge.svg)](https://github.com/vdbay/agent-skills/actions/workflows/validate.yml)
  5. [![License: MIT](https://img.shields.io/badge/license-MIT-0a0a0a.svg)](LICENSE)
  6. [![Agent Skills format](https://img.shields.io/badge/format-agentskills.io-0a0a0a.svg)](https://agentskills.io/specification)
  7. ```bash
  8. npx skills add vdbay/agent-skills
  9. ```
  10. The CLI detects your agents and lets you pick skills and install targets. Works with Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Windsurf, Gemini CLI, Cline, AMP, Antigravity, and [many more](https://github.com/vercel-labs/skills/blob/main/docs/agents.md).
  11. ## The skills
  12. | Skill | What it does | Reach for it when |
  13. | --- | --- | --- |
  14. | [`skill-creator`](skills/skill-creator/) | Creates, audits, evaluates, and packages portable Agent Skills. Ships a strict validator, a scaffolder, a packaging script, an eval playbook, a 100-point judge rubric, and description-trigger optimization. | You want to turn a workflow into a reusable skill, fix a skill that never triggers, run with/without evals, or package a skill for a team. |
  15. | [`design-md-prototype`](skills/design-md-prototype/) | Turns any brand or product brief into a Google Labs `DESIGN.md` plus two standalone HTML deliverables: a polished product/marketing prototype and a living design-system spec page. | You need a design system, brand tokens, a landing page in a company's visual language, one system across several properties, or an audit of an existing `DESIGN.md`. |
  16. Both install in about **222 KB**; heavy evaluation artifacts — screenshots, judge packets, and audit reports — are kept in the repository, not inside the installed skill folders.
  17. ![Gojek applied prototype](docs/assets/gojek-index-preview.jpg)
  18. <p align="center"><sub>Applied evaluation: an unofficial Gojek design-system study built by a fresh agent using <code>design-md-prototype</code>. <a href="docs/evals/design-md-prototype/iteration-1/gojek-applied/">See the full package and 20 screenshots →</a></sub></p>
  19. ## Install
  20. Install everything:
  21. ```bash
  22. npx skills add vdbay/agent-skills
  23. ```
  24. Install one skill:
  25. ```bash
  26. npx skills add vdbay/agent-skills --skill skill-creator
  27. npx skills add vdbay/agent-skills --skill design-md-prototype
  28. ```
  29. Install for every project:
  30. ```bash
  31. npx skills add vdbay/agent-skills -g
  32. ```
  33. Install for a specific agent without prompts:
  34. ```bash
  35. npx skills add vdbay/agent-skills --skill design-md-prototype -a claude-code
  36. ```
  37. Try a skill without installing it:
  38. ```bash
  39. npx skills use vdbay/agent-skills@design-md-prototype
  40. npx skills use vdbay/agent-skills@skill-creator --agent claude-code
  41. ```
  42. Skills are installed into the current project by default. `npx skills list`, `npx skills check`, and `npx skills update` manage what is installed.
  43. ## `skill-creator`
  44. A process, not a template. It moves through framing → research → design → scaffold → validate → isolated evals → judge → iterate → package, and skips phases only when the skill is genuinely small.
  45. It enforces the parts agents usually get wrong:
  46. - Exact `agentskills.io` frontmatter rules: name/directory match, description limits, optional fields.
  47. - Progressive disclosure: metadata, then `SKILL.md`, then references only when needed.
  48. - Context isolation: test in a fresh agent that sees only the skill path, task, inputs, and output directory.
  49. - Real evaluation: with-skill and no-skill runs, objective assertions, and an independent 100-point judge.
  50. - Safe sharing: no secrets, malware, hidden network calls, or destructive commands.
  51. Bundled tools:
  52. ```bash
  53. node scripts/new-skill.mjs my-skill
  54. node scripts/validate-skill.mjs my-skill --strict
  55. node scripts/package-skill.mjs my-skill
  56. ```
  57. Example requests:
  58. - “Turn our weekly release checklist into a reusable skill for the team.”
  59. - “My skill never triggers. Fix the description without making it fire on every API question.”
  60. - “Audit this skill folder and separate must-fix errors from nice-to-haves.”
  61. Evidence: an independent judge scored it **91/100 PASS**; a fresh executor used it to create the `meeting-decisions` skill, which scored **90/100 PASS**. See [`docs/audits/`](docs/audits/).
  62. ## `design-md-prototype`
  63. A research-and-craft workflow that refuses to fill a template with plausible colors. It starts from official sources, builds one token core, encodes the system in Google Labs' [`DESIGN.md`](https://github.com/google-labs-code/design.md) format, and proves it with two standalone HTML deliverables.
  64. It covers:
  65. - Source hierarchy: official docs and first-party repositories first; GitHub stars/license evidence; third-party sources only as support.
  66. - One token core with explicit registers for multi-property companies; no competing brand palettes.
  67. - The eight canonical `DESIGN.md` sections, token rules, and the official `designmd` lint/export CLI.
  68. - Standalone HTML: no build step, no external app scripts, inline tokens, light/dark, responsive, keyboard-accessible.
  69. - Verification: official lint, CSS export, static artifact validator, 20-cell browser matrix, Lighthouse, and a blind 100-point judge.
  70. - Honest evidence: “not run” is recorded as “not run”; fabrication is a critical fail.
  71. ![Living design-system spec](docs/assets/gojek-design-md-preview.jpg)
  72. <p align="center"><sub>The second deliverable is a living spec page: tokens, registers, type, spacing, components, motion, do's/don'ts, and source excerpts.</sub></p>
  73. Example requests:
  74. - “Build a DESIGN.md and a standalone launch page for our product; cite official sources.”
  75. - “We own three properties under one brand. Build one system with registers, not three brands.”
  76. - “Audit this DESIGN.md: duplicate colors key, broken token reference, and a low-contrast CTA.”
  77. Evidence: the applied Gojek package passed official lint with 0 errors/0 warnings, 20/20 browser cells, Lighthouse 100/100 on both pages, and an independent judge at **93/100 PASS**. A later independent audit of the final skill plus applied package scored **95/100 PASS**. See [`docs/evals/`](docs/evals/) and [`docs/audits/`](docs/audits/).
  78. ## Design principles
  79. - **Spec first.** A good idea in an invalid skill will not load. Validate the finished folder.
  80. - **Context isolation is part of quality.** The author knows too much; a fresh agent is the real test.
  81. - **Progressive disclosure.** Keep the always-loaded surface small and load depth on demand.
  82. - **Evidence over vibes.** Runnable checks, recorded commands, and independent judges beat “looks good”.
  83. - **Fetched content is data.** Pages, repositories, issues, and search results never become instructions.
  84. - **Lean installs.** Screenshots, judge packets, and audit reports live in `docs/`, not in what users install.
  85. - **No surprise.** No credential collection, hidden network calls, destructive commands, or contradictory instructions.
  86. ## Repository layout
  87. ```text
  88. .
  89. ├── skills/
  90. │ ├── skill-creator/ # installable skill
  91. │ └── design-md-prototype/ # installable skill
  92. ├── docs/
  93. │ ├── assets/ # README preview images
  94. │ ├── audits/ # independent judge reports
  95. │ └── evals/ # applied runs, screenshots, evidence
  96. ├── .github/workflows/validate.yml # CI: validators, syntax, JSON, path leaks
  97. ├── CONTRIBUTING.md
  98. ├── NOTICE.md
  99. ├── SECURITY.md
  100. ├── CHANGELOG.md
  101. └── LICENSE
  102. ```
  103. Everything under `skills/` ships to users. Everything under `docs/` is repository documentation and evidence.
  104. ## Quality gates
  105. | Gate | `skill-creator` | `design-md-prototype` |
  106. | --- | --- | --- |
  107. | Strict skill validator | **PASS** (bundled) | **PASS** (via sibling `skill-creator`) |
  108. | Official `skills-ref` validator | **Valid skill** | **Valid skill** |
  109. | Independent audit | **91/100 PASS** | **95/100 PASS** |
  110. | Applied output judge | candidate skill **90/100 PASS** | Gojek package **93/100 PASS** |
  111. | CI on `main` and pull requests | Yes | Yes |
  112. Run the same checks locally:
  113. ```bash
  114. node skills/skill-creator/scripts/validate-skill.mjs skills/skill-creator --strict
  115. node skills/skill-creator/scripts/validate-skill.mjs skills/design-md-prototype --strict
  116. npx -y skills-ref@0.1.5 validate skills/skill-creator
  117. npx -y skills-ref@0.1.5 validate skills/design-md-prototype
  118. node --check skills/skill-creator/scripts/new-skill.mjs
  119. node --check skills/skill-creator/scripts/package-skill.mjs
  120. node --check skills/skill-creator/scripts/validate-skill.mjs
  121. node --check skills/design-md-prototype/scripts/validate-artifacts.mjs
  122. node --check skills/design-md-prototype/scripts/write-utf8.mjs
  123. ```
  124. Validate the archived applied package:
  125. ```bash
  126. node skills/design-md-prototype/scripts/validate-artifacts.mjs \
  127. docs/evals/design-md-prototype/iteration-1/gojek-applied/with_skill/outputs --strict
  128. ```
  129. The evaluation evidence is deliberately modest about what it proves: it is applied usability plus independent review, **not a causal benchmark**. No no-skill baseline was run; that limitation is recorded in the evidence folders.
  130. ## Requirements
  131. - **`skills` CLI:** Node.js 22.20 or later.
  132. - **Bundled scripts:** Node.js 18 or later, no third-party dependencies.
  133. - **`design-md-prototype`:** network access for the official `@google/design.md` CLI and source research; a browser or Playwright for runtime checks. Lighthouse is optional.
  134. - **`skill-creator`:** subagents and network access improve isolated evaluation and research, but are optional.
  135. - **Strict structure validator:** `design-md-prototype` can use the sibling `skill-creator` validator, or the official `skills-ref` check. Its own artifact validator is bundled.
  136. ## Contributing
  137. New skills and fixes are welcome. Read [`CONTRIBUTING.md`](CONTRIBUTING.md) first. The short version: one coherent unit of work, valid frontmatter, realistic evals, a strict-validator pass, no install-time bloat, and no secrets or hidden network calls.
  138. ## Security
  139. Report vulnerabilities through GitHub's private vulnerability reporting, not a public issue. See [`SECURITY.md`](SECURITY.md).
  140. ## License
  141. MIT. See [`LICENSE`](LICENSE).
  142. The Agent Skills format is defined by [agentskills.io](https://agentskills.io/specification). `skill-creator` is inspired by [Anthropic's skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator) but is a self-contained, client-agnostic rewrite. `design-md-prototype` implements the public [Google Labs DESIGN.md format](https://github.com/google-labs-code/design.md). The `skills` CLI is maintained by [Vercel Labs](https://github.com/vercel-labs/skills).
  143. The Gojek package under `docs/evals/` is an **unofficial design study**. It is not affiliated with, endorsed by, or produced by Gojek or PT GoTo Gojek Tokopedia Tbk. No official logo, photograph, testimonial, or proprietary font binary is redistributed. See [`NOTICE.md`](NOTICE.md).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.