acceptance-orchestrato…
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human…
Create or update a shared Apple design context document that other HIG skills use to tailor guidance.
$ npx -y skills add sinhoneyy/master-skills --skill hig-project-context --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hig-project-contextContext preview
The summary Claude sees to decide when to auto-load this skill.
Create or update a shared Apple design context document that other HIG skills use to tailor guidance.
name: hig-project-context description: Create or update a shared Apple design context document that other HIG skills use to tailor guidance. risk: unknown source: community date_added: '2026-02-27'
Create and maintain `.claude/apple-design-context.md` so other HIG skills can skip redundant questions.
Check for `.claude/apple-design-context.md` before asking questions. Use existing context and only ask for information not already covered.
Before asking questions, auto-discover context from:
1. **README.md** -- Product description, platform targets 2. **Package.swift / .xcodeproj** -- Supported platforms, minimum OS versions, dependencies 3. **Info.plist** -- App category, required capabilities, supported orientations 4. **Existing code** -- Import statements reveal frameworks (SwiftUI vs UIKit, HealthKit, etc.) 5. **Assets.xcassets** -- Color assets, icon sets, dark mode variants 6. **Accessibility audit** -- Grep for accessibility modifiers/attributes
Present findings and ask the user to confirm or correct. Then gather anything still missing:
Generate `.claude/apple-design-context.md` using this structure:
# Apple Design Context ## Product - **Name**: [App name] - **Description**: [One sentence] - **Category**: [Category] - **Stage**: [Concept / Development / Shipped / Redesign] ## Platforms | Platform | Supported | Min OS | Notes | |----------|-----------|--------|-------| | iOS | Yes/No | | | | iPadOS | Yes/No | | | | macOS | Yes/No | | | | tvOS | Yes/No | | | | watchOS | Yes/No | | | | visionOS | Yes/No | | | ## Technology - **UI Framework**: [SwiftUI / UIKit / AppKit / Mixed] - **Architecture**: [Single-window / Multi-window / Document-based] - **Apple Technologies**: [List any: HealthKit, CloudKit, ARKit, etc.] ## Design System - **Base**: [System defaults / Custom design system] - **Brand Colors**: [List or reference] - **Typography**: [System fonts / Custom fonts] - **Dark Mode**: [Supported / Not yet / N/A] - **Dynamic Type**: [Supported / Not yet / N/A] ## Accessibility - **Target Level**: [Baseline / Enhanced / Comprehensive] - **Key Considerations**: [List any specific needs] ## Users - **Primary Persona**: [Description] - **Key Use Cases**: [List] - **Known Challenges**: [List]
When updating an existing context document:
1. Read the current `.claude/apple-design-context.md` 2. Ask what has changed 3. Update only the changed sections 4. Preserve all unchanged information
---
*Built by [Raintree Technology](https://raintree.technology) · [More developer tools](https://raintree.technology)*
This skill is applicable to execute the workflow or actions described in the overview.
Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains
Repo: sinhoneyy/master-skills
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human…
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix…
Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first…
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author…
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or…
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.