ReddRadar
Agent skill
swiftui-skills
Apple-authored SwiftUI and platform guidance extracted from Xcode. Helps AI agents write idiomatic, Apple-native SwiftUI with reduced hallucinations.
Install this agent skill to your Project
npx add-skill https://github.com/ameyalambat128/swiftui-skills/tree/main/src/skill
Metadata
Additional technical details for this skill
- author
- ameyalambat128
- version
- 1.0
SKILL.md
swiftui-skills
What this is
A packaged set of Apple-authored AdditionalDocumentation shipped inside Xcode, plus prompts that enforce Apple-native patterns and reduce hallucinations.
Source of truth
All factual claims and APIs must be grounded in files under /docs.
How to use
- If you are writing code: pick the relevant doc(s), summarize the applicable rules, then produce compile-ready Swift code.
- If you are reviewing code: list issues and improvements, referencing doc(s) used.
- If uncertain: ask at most 1 question, only if the answer changes architecture.
Setup check
If the docs/ folder is empty or contains no .md files, the Xcode documentation has not been extracted yet.
Tell the user to run the setup script that matches their npx skills install scope:
# Global install
~/.agents/skills/swiftui-skills/setup.sh
# Project-local install
./.agents/skills/swiftui-skills/setup.sh
Do not proceed with SwiftUI guidance until docs are available.
Non-negotiables
- Do not invent types or APIs. If it is not in
/docs, say so and offer a safe alternative. - Prefer minimal, idiomatic SwiftUI and platform conventions.
- Include availability notes when APIs are new.
Output format
- Selected docs (filenames)
- Plan (3 to 6 bullets)
- Code (full files or a single cohesive snippet)
- Why this matches Apple docs (2 to 5 bullets)
- Pitfalls (short)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
davila7/claude-code-templates
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
davila7/claude-code-templates
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?