本文へ移動
cccskills
無料GitHub で公開

ios-hig-design-guide

Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data. Use when a task asks for iOS UI/UX rules, Apple design standards, component behavior, accessibility constraints, interaction patterns, or feature-level design-spec writing grounded in official HIG pages.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md2.9 KB
  • references/ios-design-spec-workflow.md3.5 KB
  • scripts/sync_apple_hig_sources.py13.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

iOS HIG Design Guide

Use this skill to produce iOS design recommendations that stay close to official Apple guidance.

Quick start

  1. Sync official sources.
  2. Read only relevant sections.
  3. Produce a feature-specific spec (not a generic style dump).

Run:

python3 scripts/sync_apple_hig_sources.py --skill-dir .

Source of truth

  • Full raw index with links and abstracts: references/apple-hig-ios-raw.md
  • Consolidated text dump of all downloaded pages: references/apple-hig-ios-fulltext.md
  • Curated text dump for iOS spec writing: references/apple-hig-ios-curated.md
  • Workflow for selecting relevant HIG pages: references/ios-design-spec-workflow.md
  • Per-page JSON sources: references/raw/pages/design/human-interface-guidelines/*.json
  • Crawl metadata and fetch status: references/raw/catalog.json

Workflow

1) Sync and verify

  • Run sync script before answering "latest" or "current" requests.
  • Confirm download_error is 0 in references/raw/catalog.json.
  • If errors exist, report failed paths and continue with successfully downloaded pages.

2) Narrow scope

  • Start from /design/human-interface-guidelines/designing-for-ios.
  • Add only sections directly related to the requested feature.
  • Prioritize foundational constraints (accessibility, layout, typography, color, writing, privacy).
  • Prefer references/apple-hig-ios-curated.md for day-to-day use; use full dump only when needed.

3) Extract constraints

For each selected page, pull concrete rules into implementable statements:

  • When to use component/pattern
  • Required states (loading, empty, error, destructive confirmation)
  • Accessibility behavior (labels, hints, touch target, dynamic type)
  • Localization/layout behavior (RTL, truncation, multiline)
  • Platform-specific caveats (iOS-only vs cross-platform)

4) Produce deliverable

Default output structure:

  1. Feature goal and user scenario
  2. Information architecture and screen inventory
  3. Interaction and state model
  4. Component specification
  5. Accessibility and localization checklist
  6. Open questions and tradeoffs

Output style rules

  • Cite source page paths for each major rule.
  • Translate HIG guidance into actionable product decisions.
  • Avoid copying large raw passages.
  • Mark inferred recommendations explicitly as inference.

Maintenance

  • Re-run sync script whenever Apple updates HIG content.
  • Keep generated raw files in references/; do not hand-edit generated outputs.
  • Update this SKILL.md only for workflow or quality improvements.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6302026年10月12日 更新

davepoon のスキルをすべて見る

このスキルの問題を報告する