appCN: Skill for Claude Code

.claude/skills/document-component/SKILL.md

document-component is a skill for Claude Code from Salah-XD/appCN. It costs 69 tokens per session (917 once invoked), scanned A, original, MIT.

A documentation task for creating the typed metadata file for an existing appCN component. It records the component’s structure, properties, examples, visual details, and accessibility information.

In plain words
What is it for?
Use it when documenting or updating metadata for a specific existing component in the appCN UI library.
Why use it?
It keeps component documentation accurate and complete without changing the component’s implementation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Salah-XD/appCN's own configuration. It tells Claude Code how to work on appCN itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything appCN configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { ComponentMeta } from "../lib/meta";.

Reuse

Borrowing it

Nothing to install: this file belongs to Salah-XD/appCN. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Salah-XD/appCN/main/.claude/skills/document-component/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Salah-XD/appCN

Made for: Claude Code.

Wrote 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.

agentmods badge for document-component

README.md
[![agentmods](https://agentmods.dev/badge/skills/salah-xd/appcn/document-component/github.svg)](https://agentmods.dev/skills/salah-xd/appcn/document-component)
Your own site
<a href="https://agentmods.dev/skills/salah-xd/appcn/document-component"><img src="https://agentmods.dev/badge/skills/salah-xd/appcn/document-component/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.

agentmods 80×15 button for document-component

Your own site · 80×15
<a href="https://agentmods.dev/skills/salah-xd/appcn/document-component"><img src="https://agentmods.dev/badge/skills/salah-xd/appcn/document-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00917
Opus 5.5 $0.00028 $0.00367
Sonnet 5.5 $0.00014 $0.00183
Haiku 4.5 $0.00007 $0.00092

Measured 2mo ago against content hash eb5a8dde5545, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

document-component 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 2mo 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.

.claude/skills/document-component/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/document-component

This skill writes (or rewrites) a <slug>.meta.ts for a component that already exists in packages/ui/src/. Component code must not change — only the meta file.

Step 0 — Confirm target

Ask which component if not given. Verify:

  • packages/ui/src/{components,ai}/<slug>.tsx exists.
  • Note whether <slug>.meta.ts already exists (you may be rewriting).

Step 1 — Read the source

Read the full component .tsx. Note:

  • Header doc comment (often names the delight detail).
  • The exported <Name>Props interface — every public prop, in order, with its TSDoc.
  • Defaults (look for prop = value in the destructured signature).
  • Animations + useReducedMotion() branches (drives the delight bullet and the a11y bullet about reduced motion).
  • accessibilityRole, accessibilityLabel, accessibilityState, hitSlop — these drive the a11y section.

If ../lib/motion / ../lib/haptics are used, those are themselves shipped as registry deps and worth mentioning in anatomy / a11y where relevant.

Step 2 — Compose the meta

Use the existing metas in packages/ui/src/{components,ai}/*.meta.ts as reference for voice and depth.

import type { ComponentMeta } from "../lib/meta";

export const meta: ComponentMeta = {
  slug: "...",
  title: "...",
  category: "base" | "ai",
  description: "<one line — match the component's header doc comment if it has one>",
  anatomy: "<2–4 sentences: what's it made of, when to reach for it>",
  delight: "<the one non-obvious motion / haptic / behavior>",
  props: [
    /* every public prop, in interface order, with TSDoc mirrored into description */
  ],
  examples: [
    { title: "Basic", description: "...", code: `...` }, // canonical demo
    { title: "<feature>", description: "...", code: `...` },
    // more if the component has clearly distinct modes
  ],
  a11y: [
    /* one bullet per relevant accessibility behavior:
       roles, labels, state, hit slop, reduced-motion, focus/press feedback */
  ],
};

Read the full file on GitHub · 103 lines

Changes

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.

  1. 2mo ago First seen · 103 lines · 69 tokens per session scan A eb5a8dde5545

Subscribe to this mod's changes

document-component is a skill published in the GitHub repository Salah-XD/appCN (3 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 917 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

document-component compared with skills from other repositories

document-component next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
document-componentSalah-XD/appCNSkill35mo agoMITA69Claude Code
shadcn-vueunovue/shadcn-vueSkill11k3d agoMITA97Claude Code
shadcn-ui-flutternank1ro/flutter-shadcn-uiSkill2.8k3d agoMITA58Claude Code, Codex
ui-componentsyonatangross/orchestkitSkill299yesterdayMITA44Claude Code
maquina-ui-standardsmaquina-app/maquina_componentsSkill1409d agoMITA61Claude Code, Codex
creative-tim-uicreativetimofficial/uiSkill12k7mo agoMITA91Claude Code, Codex
spark-uicodeweb-dev/spark-uiSkill993mo agoMITA73Claude Code, Codex