agentmods.dev

explore-apple-swift-docs

A guide for finding and using Apple and Swift documentation from sources such as Xcode documentation, Dash, source repositories, generated docs, and official web pages.

In plain words
What is it for?
Use it to look up Apple or Swift APIs, guides, tutorials, symbols, and concepts, or to get help with local documentation and Dash docsets.
Why use it?
It gives documentation lookup a defined order and fallback path when one source is unavailable or incomplete.

Skill for Claude CodeCodex

7 +1 6d ago A scan 78 tokens original Apache-2.0
View the source file gaelic-ghost/socket
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/gaelic-ghost/socket/explore-apple-swift-docs
Any agent
npx skills add gaelic-ghost/socket --skill explore-apple-swift-docs
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00078 $0.01919
Opus 5 $0.00039 $0.00959
Sonnet 5 $0.00016 $0.00384
Haiku 4.5 $0.00008 $0.00192

Measured 2d ago against content hash bd41a2cc9d28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-apple-swift-docs 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 2d 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.

plugins/apple-dev-skills/skills/explore-apple-swift-docs/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Apple Swift Docs

Purpose

Explore Apple and Swift documentation through one top-level entry point. Prefer direct docs access methods in this order: Xcode MCP DocumentationSearch first, Dash.app MCP second, Dash localhost HTTP only when the Dash.app MCP is unavailable or incomplete, then checked-out source, generated DocC, GitHub/source repositories, or release notes, and finally readable online documentation. scripts/run-workflow.fsx remains a maintainer helper for structured dry runs, fallback planning, and Dash follow-up automation, but it is not the primary way the agent should perform ordinary Apple or Swift docs lookup.

When To Use

  • Use this skill for Apple or Swift API reference lookup requests.
  • Use this skill for Apple or Swift guide, tutorial, symbol, or concept search requests.
  • Use this skill when the user wants local docs first, wants official docs first, or wants to compare available Apple or Swift docs sources.
  • Use this skill when the user wants Dash-compatible Apple or Swift docs access, install guidance for a missing Dash docset, or generation guidance when a Dash docset is unavailable.
  • Recommend xcode-build-run-workflow when the user needs Apple or Swift execution, diagnostics, build, run, toolchain help, or mutation decisions inside an existing Xcode project.
  • Recommend xcode-testing-workflow when the user needs Swift Testing, XCTest, XCUITest, .xctestplan, or test diagnosis inside an existing Xcode project.
  • Recommend bootstrap-xcode-workspace when the user is starting a native Apple product or aligning an existing canonical workspace.

Single-Path Workflow

  1. Classify the request into one docs workflow mode:
    • explore
    • dash-install
    • dash-generate
  2. If no mode is explicit, start at explore.
  3. For explore, use the documented direct docs path instead of routing ordinary lookups through a wrapper script:
    • xcode-mcp-docs: use Xcode MCP DocumentationSearch first when it is available and the user has not asked for another source
    • dash: use the Dash.app MCP directly after Xcode MCP when its installed docsets cover the question
    • dash-http: use the documented Dash localhost HTTP structure directly when Dash MCP is unavailable or incomplete
    • source-repo: use GitHub/source repositories, generated DocC, release notes, or checked-out source when the request is about open source Swift projects, tools, or packages
    • official-web: use official Apple or Swift web docs when the local-docs and source-repo paths are unavailable, the user explicitly prefers the web source, and the page content is actually readable through the available tool
  4. Use scripts/run-workflow.fsx only when a structured non-interactive planning result is useful, or when the request is specifically about dash-install or dash-generate follow-up behavior.
  5. If the selected mode cannot complete, hand off forward through one clear next step:
    • explore -> dash-install
    • dash-install -> dash-generate
  6. Return one status, one path_type, one source_used, and one output contract for the mode that ran.

Read the full file on GitHub · 128 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 128 lines · 78 tokens per session scan A bd41a2cc9d28

Subscribe to this mod's changes

explore-apple-swift-docs is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,919 once invoked, about $0.0004 per session on Opus 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.

Learning and teachingResearchWriting and docsagent-skillcodexcodex-plugindeveloper-toolsmacosplugin-repo
Related

Other skills, from other repositories

learn

Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…

SethGammon/Citadel · 66 tokens

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

LEAP

LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.

agentsope/SkillAlchemy · 52 tokens

bq-skill

行为面试 skill。帮求职者挖掘真实经历、用 STAR/CAR 结构化、映射能力标签、构建可复用的中英双语故事库（Story Bank）；并能接入 JD + 简历，针对具体岗位生成 Top 20 BQ 选题 + 基于真实经历的 STAR 准备模板（HTML 报告）。不是背答案，而是建立可复用的职业叙事体系，让任何行为面试题都能自然作答。关键词：behavioral question, BQ, 行为面试, STAR, 故事库, Amazon LP, 职业故事, tell me about a time, 面试准备, JD 面试题预测, top 20 题。.

yanliudesign/offer-toolkit-skill · 166 tokens

zapier-demo

Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…

zapier/zapier-mcp · 121 tokens

vitaecontext-vitaegraph

Build, deepen, validate, index, and maintain a private hierarchical career knowledge graph from supplied career materials. Use when the user asks to create or update a VitaeGraph, model education with nested courses or thesis work, enrich projects from Git repositories, or supply deep selected career context to…

vitaecontext/vitaecontext · 69 tokens