Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

21st Dev

BSecurity

21st.dev is a community registry of 12,000+ production-ready React components, templates, shadcn themes and SVG logos. Code is copied into the repo (not a dependency) — search first, install what fits, hand-write UI only when nothing matches.

6 stars
0 votes
0 copies
2 views
Added 9/30/2026
ai-agentspythongobashreactapifrontend

Works with

cliapi

Security Analysis

B88/100
criticalSends environment variables or credentials to an external URL

Pro scans all 5 files and shows the line behind each finding

Scanned 9/30/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill 21st-dev --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 21st Dev?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for 21st Dev
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-21st-dev/badge)](https://www.skillsdirectory.com/skills/aicodedecode-21st-dev)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
# 21st.dev — UI component registry skill

21st.dev is a community registry of 12,000+ production-ready React components,
templates, shadcn themes and SVG logos. Code is copied into the repo (not a
dependency) — search first, install what fits, hand-write UI only when nothing
matches.

## Docs (official, fetched 2026-09-30 from https://21st.dev/api/skills/)

- `21st-cli-use.md` — search/get/add components via the `21st` CLI; auth, metering, logos
- `21st-ai.md` — generate/iterate sketch loop with hosted 21st AI
- `21st-registry.md` — publishing components/themes/templates
- `21st-design-sync.md` — publish a project's design tokens as a theme

Read the relevant doc before acting.

## CLI

`npx -y @21st-dev/cli` (bin `21st`). Verified runnable 2026-09-30.

## Auth

- **Secure Vault (connected 2026-09-30):** `custom.21st` holds the API key.
  Never read the real key. Fetch a short-lived surrogate and pass it where the
  key goes — authd swaps it at egress:
  ```bash
  export TWENTYFIRST_TOKEN="$(authdc cred surrogate custom.21st | python3 -c 'import json,sys; print(json.load(sys.stdin)["credentials"][0]["surrogate"])')"
  npx -y @21st-dev/cli search "animated hero" --limit 5
  ```
  Never print or log the surrogate. If the API returns 401/403, ask the user to
  reconnect the key via the Secure Vault rather than retrying blindly.
- Fallbacks: `npx @21st-dev/cli login` (interactive), or `--api-key` /
  `TWENTYFIRST_TOKEN` / `API_KEY_21ST` env var.
- Check `21st usage` before retrieving code or generating.

## Metering (free tier)

- Search, previews, theme CSS: free.
- Component code retrieval (`21st get`, `21st add`): free daily quota.
- 21st AI generation: needs AI explicitly enabled + credits; never retry after
  `ai_subscription_required`.
- Logo search (`21st logo`): free, no login (open svgl.app library).

## Workflow (user's directive 2026-09-30: build it myself)

1. `21st search "<intent>"` — free, unlimited. Use search + previews as
   **inspiration and reference**, not as a shopping trip.
2. **Decide the taste first** — run the `frontend-design-direction` skill to set
   the visual direction (the UI equivalent of the taste skills' "decide the
   genre before the first render"). One direction, executed coherently, beats a
   mix of borrowed looks.
3. **Build the component myself** in the project's own stack (Tailwind, shadcn
   patterns, GSAP skill for motion). I have the knowledge — treat 21st.dev as
   the design reference, my own code as the implementation.
4. Spend one of the 2/day free code retrievals (`21st get` / `21st add`) ONLY
   when a component is genuinely complex (shaders, intricate animation
   choreography) and adapting it by hand would cost more than the quota slot.
5. Adapt tokens/props to the project's design system; match Tailwind config and
   the `impeccable` skill workflow for visual builds (the video `taste` /
   `taste-distillation` / `taste-application` skills are the same
   decide-first discipline for video edits — use those when the work is reels
   or music videos, not UI).

## Standing rules

- **FREE TIER ONLY (user's standing rule, 2026-09-30):** never purchase or
  unlock premium templates/components, never enable or call 21st AI generation
  (`generate` / `iterate`), never attach a payment method. If a component is
  premium-only, skip it and find a free alternative.
- Check `21st usage` before every retrieval; stop for the day when the free
  quota (2/day) is exhausted — never work around it.
- API key connected 2026-09-30 as `custom.21st` (Secure Vault) — verified live
  via catalog search. Free-tier metering applies: search/previews free, code
  retrieval has a free daily quota.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →