opencode-skills-antigravity 1.0.13 → 1.0.14

package/bundled-skills/app-store-changelog/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: app-store-changelog
+description: Generate user-facing App Store release notes from git history since the last tag.
+risk: safe
+source: "Dimillian/Skills (MIT)"
+date_added: "2026-03-25"
+---
+
+# App Store Changelog
+
+## Overview
+Generate a comprehensive, user-facing changelog from git history since the last tag, then translate commits into clear App Store release notes.
+
+## When to Use
+
+- When the user asks for App Store "What's New" text or release notes from git history.
+- When you need to turn raw commits into concise, user-facing release bullets.
+
+## Workflow
+
+### 1) Collect changes
+- Run `scripts/collect_release_changes.sh` from the repo root to gather commits and touched files.
+- If needed, pass a specific tag or ref: `scripts/collect_release_changes.sh v1.2.3 HEAD`.
+- If no tags exist, the script falls back to full history.
+
+### 2) Triage for user impact
+- Scan commits and files to identify user-visible changes.
+- Group changes by theme (New, Improved, Fixed) and deduplicate overlaps.
+- Drop internal-only work (build scripts, refactors, dependency bumps, CI).
+
+### 3) Draft App Store notes
+- Write short, benefit-focused bullets for each user-facing change.
+- Use clear verbs and plain language; avoid internal jargon.
+- Prefer 5 to 10 bullets unless the user requests a different length.
+
+### 4) Validate
+- Ensure every bullet maps back to a real change in the range.
+- Check for duplicates and overly technical wording.
+- Ask for clarification if any change is ambiguous or possibly internal-only.
+
+## Commit-to-Bullet Examples
+
+The following shows how raw commits are translated into App Store bullets:
+
+| Raw commit message | App Store bullet |
+|---|---|
+| `fix(auth): resolve token refresh race condition on iOS 17` | • Fixed a login issue that could leave some users unexpectedly signed out. |
+| `feat(search): add voice input to search bar` | • Search your library hands-free with the new voice input option. |
+| `perf(timeline): lazy-load images to reduce scroll jank` | • Scrolling through your timeline is now smoother and faster. |
+
+Internal-only commits that are **dropped** (no user impact):
+- `chore: upgrade fastlane to 2.219`
+- `refactor(network): extract URLSession wrapper into module`
+- `ci: add nightly build job`
+
+## Example Output
+
+```
+What's New in Version 3.4
+
+• Search your library hands-free with the new voice input option.
+• Scrolling through your timeline is now smoother and faster.
+• Fixed a login issue that could leave some users unexpectedly signed out.
+• Added dark-mode support to the settings screen.
+• Improved load times when opening large photo albums.
+```
+
+## Output Format
+- Title (optional): "What's New" or product name + version.
+- Bullet list only; one sentence per bullet.
+- Stick to storefront limits if the user provides one.
+
+## Resources
+- `scripts/collect_release_changes.sh`: Collect commits and touched files since last tag.
+- `references/release-notes-guidelines.md`: Language, filtering, and QA rules for App Store notes.

package/bundled-skills/app-store-changelog/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "App Store Changelog"
+  short_description: "Generate App Store release notes"
+  default_prompt: "Use $app-store-changelog to draft App Store release notes from the changes since the last tag."

package/bundled-skills/app-store-changelog/references/release-notes-guidelines.md

@@ -0,0 +1,34 @@
+# App Store Release Notes Guidelines
+
+## Goals
+- Produce user-facing release notes that describe visible changes since the last tag.
+- Include all user-impacting changes; omit purely internal or refactor-only work.
+- Keep language plain, short, and benefit-focused.
+
+## Output Shape
+- Prefer 5 to 10 bullets total for most releases.
+- Group by theme if needed: New, Improved, Fixed.
+- Each bullet should be one sentence and start with a verb.
+- Avoid internal codenames, ticket IDs, or file paths.
+
+## Filtering Rules
+- Include: new features, UI changes, behavior changes, bug fixes users would notice, performance improvements with visible impact.
+- Exclude: refactors, dependency bumps, CI changes, developer tooling, internal logging, analytics changes unless they affect user privacy or behavior.
+- If a change is ambiguous, ask for clarification or describe it as a small improvement only if it is user-visible.
+
+## Language Guidance
+- Translate technical terms into user-facing descriptions.
+- Avoid versions of "API", "refactor", "nil", "crash log", or "dependency".
+- Prefer "Improved", "Added", "Fixed", "Updated" or action verbs like "Search", "Upload", "Sync".
+- Keep tense present or past: "Added", "Improved", "Fixed".
+
+## Examples
+- "Added account switching from the profile menu."
+- "Improved timeline loading speed on slow connections."
+- "Fixed media attachments not opening in full screen."
+
+## QA Checklist
+- Every bullet ties to a real change in the range.
+- No duplicate bullets that describe the same change.
+- No internal jargon or file paths.
+- Final list fits App Store text limits for the target storefront if provided.

package/bundled-skills/app-store-changelog/scripts/collect_release_changes.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+since_ref="${1:-}"
+until_ref="${2:-HEAD}"
+
+if [[ -z "${since_ref}" ]]; then
+  if git describe --tags --abbrev=0 >/dev/null 2>&1; then
+    since_ref="$(git describe --tags --abbrev=0)"
+  fi
+fi
+
+range=""
+if [[ -n "${since_ref}" ]]; then
+  range="${since_ref}..${until_ref}"
+else
+  range="${until_ref}"
+fi
+
+repo_root="$(git rev-parse --show-toplevel)"
+
+printf "Repo: %s\n" "${repo_root}"
+if [[ -n "${since_ref}" ]]; then
+  printf "Range: %s..%s\n" "${since_ref}" "${until_ref}"
+else
+  printf "Range: start..%s (no tags found)\n" "${until_ref}"
+fi
+
+printf "\n== Commits ==\n"
+git log --reverse --date=short --pretty=format:'%h|%ad|%s' ${range}
+
+printf "\n\n== Files Touched ==\n"
+git log --reverse --name-only --pretty=format:'--- %h %s' ${range} | sed '/^$/d'

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Come usare antigravity-awesome-skills con Jetski/Cortex evitando l’overflow di contesto con 1.311+ skill."
+description: "Come usare antigravity-awesome-skills con Jetski/Cortex evitando l’overflow di contesto con 1.326+ skill."
 ---
 
-# Jetski/Cortex + Gemini: integrazione sicura con 1.311+ skill
+# Jetski/Cortex + Gemini: integrazione sicura con 1.326+ skill
 
 Questa guida mostra come integrare il repository `antigravity-awesome-skills` con un agente basato su **Jetski/Cortex + Gemini** (o framework simili) **senza superare il context window** del modello.
 
@@ -23,7 +23,7 @@ Non bisogna mai:
 - concatenare il contenuto di tutte le `SKILL.md` in un singolo system prompt;
 - reiniettare l’intera libreria per **ogni** richiesta.
 
-Con oltre 1.311 skill, questo approccio riempie il context window prima ancora di aggiungere i messaggi dell’utente, causando l’errore di truncation.
+Con oltre 1.326 skill, questo approccio riempie il context window prima ancora di aggiungere i messaggi dell’utente, causando l’errore di truncation.
 
 ---
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -20,7 +20,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 1,311+ skills installed.
+This pattern avoids context overflow when you have 1,326+ skills installed.
 
 ---
 

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t
 
 Preferred positioning:
 
-> Installable GitHub library of 1,311+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,326+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
 
 Key framing:
 
@@ -20,7 +20,7 @@ Key framing:
 
 Preferred description:
 
-> Installable GitHub library of 1,311+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
+> Installable GitHub library of 1,326+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
 
 Preferred homepage:
 
@@ -28,7 +28,7 @@ Preferred homepage:
 
 Preferred social preview:
 
-- use a clean preview image that says `1,311+ Agentic Skills`;
+- use a clean preview image that says `1,326+ Agentic Skills`;
 - mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -69,7 +69,7 @@ For manual updates, you need:
 The update process refreshes:
 - Skills index (`skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 1,311+ skills from the skills directory
+- All 1,326+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/sources/sources.md

@@ -80,6 +80,16 @@ The following skills were added from the curated collection at [VoltAgent/awesom
 | `fp-ts-react`     | [whatiskadudoing/fp-ts-skills](https://github.com/whatiskadudoing/fp-ts-skills) | Compatible | fp-ts with React 18/19 and Next.js                       |
 | `fp-ts-errors`    | [whatiskadudoing/fp-ts-skills](https://github.com/whatiskadudoing/fp-ts-skills) | Compatible | Type-safe error handling with Either and TaskEither      |
 
+## Skills from Dimillian/Skills
+
+The following skills were added from [Dimillian/Skills](https://github.com/Dimillian/Skills), a curated Codex skills repository focused on Apple platforms, GitHub workflows, refactoring, and performance work.
+
+| Skill / Group | Original Source | License | Notes |
+| :------------ | :-------------- | :------ | :---- |
+| `app-store-changelog`, `github`, `orchestrate-batch-refactor`, `project-skill-audit`, `react-component-performance`, `simplify-code` | [Dimillian/Skills](https://github.com/Dimillian/Skills) | MIT | Workflow, GitHub, React performance, and code simplification skills. |
+| `ios-debugger-agent`, `macos-menubar-tuist-app`, `macos-spm-app-packaging`, `swift-concurrency-expert` | [Dimillian/Skills](https://github.com/Dimillian/Skills) | MIT | Apple-platform debugging, packaging, and Swift concurrency guidance. |
+| `swiftui-liquid-glass`, `swiftui-performance-audit`, `swiftui-ui-patterns`, `swiftui-view-refactor` | [Dimillian/Skills](https://github.com/Dimillian/Skills) | MIT | SwiftUI-specific implementation, performance, and refactoring patterns. |
+
 ---
 
 ## Recently Added Skills (March 2026)

package/bundled-skills/docs/users/bundles.md

@@ -4,6 +4,8 @@
 
 > These packs are curated starter recommendations for humans. Generated bundle ids in `data/bundles.json` are broader catalog/workflow groupings and do not need to map 1:1 to the editorial packs below.
 
+> **Important:** bundles are not invokable mega-skills such as `@web-wizard` or `/essentials-bundle`. Use the individual skills listed in the pack, or use the activation scripts if you want only that bundle's skills active in your live Antigravity directory.
+
 ## Quick Start
 
 1. **Install the repository:**
@@ -22,6 +24,12 @@
    - Gemini CLI: `Use skill-name...`
    - Codex CLI: `Use skill-name...`
 
+If you want a bundle to behave like a focused active subset instead of a reading list, use:
+
+- macOS/Linux: `./scripts/activate-skills.sh --clear Essentials`
+- macOS/Linux: `./scripts/activate-skills.sh --clear "Web Wizard"`
+- Windows: `.\scripts\activate-skills.bat --clear Essentials`
+
 ---
 
 ## Essentials & Core
@@ -579,4 +587,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: March 2026 | Total Skills: 1,311+ | Total Bundles: 36_
+_Last updated: March 2026 | Total Skills: 1,326+ | Total Bundles: 36_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -6,7 +6,7 @@ Antigravity Awesome Skills gives Claude Code users an installable library of `SK
 
 ## Why use this repo for Claude Code
 
-- It includes 1,311+ skills instead of a narrow single-domain starter pack.
+- It includes 1,326+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.
 - It covers both everyday engineering tasks and specialized work like security reviews, infrastructure, product planning, and documentation.

package/bundled-skills/docs/users/faq.md

@@ -162,6 +162,26 @@ If Antigravity becomes unstable only when the full skills library is active, swi
 
 That guide shows how to run `scripts/activate-skills.sh` from a cloned copy of this repository so only the bundles or skill ids you need stay active in `~/.gemini/antigravity/skills`.
 
+### Gemini CLI hangs after a few turns or says "This is taking a bit longer, we're still on it". What should I do?
+
+Start with a quick isolation check:
+
+1. Start a brand-new Gemini CLI conversation.
+2. Try one prompt with no skills at all.
+3. Try the same task again with only one small skill such as `brainstorming`.
+4. Temporarily reduce your active skill set to 2-5 skills and retry.
+
+How to interpret the result:
+
+- If plain Gemini CLI hangs even without skills, the problem is likely on the Gemini CLI/runtime side rather than this repository.
+- If plain Gemini works, but hangs only when skills are present or after several turns, the likely cause is conversation/context growth.
+
+In that case:
+
+- keep a much smaller active set
+- start fresh conversations more often
+- use the overload guide: [agent-overload-recovery.md](agent-overload-recovery.md)
+
 ### How do I update skills?
 
 Navigate to your skills directory and pull the latest changes:
@@ -185,6 +205,22 @@ Use the `@` symbol followed by the skill name:
 @brainstorming help me design a todo app
 ```
 
+### Can I invoke a whole bundle like `@Essentials` or `/web-wizard`?
+
+No. Bundles are curated lists of skills, not standalone invokable mega-skills.
+
+Use them in one of these two ways:
+
+- pick individual skills from the bundle and invoke those directly
+- use the activation scripts if you want only that bundle's skills active in Antigravity
+
+Examples:
+
+```bash
+./scripts/activate-skills.sh --clear Essentials
+./scripts/activate-skills.sh --clear "Web Wizard"
+```
+
 ### Can I use multiple skills at once?
 
 **Yes!** You can invoke multiple skills:

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -8,7 +8,7 @@ Antigravity Awesome Skills supports Gemini CLI through the `.gemini/skills/` pat
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,311+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,326+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/getting-started.md

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V8.8.0)
+# Getting Started with Antigravity Awesome Skills (V8.9.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 1,311+ specialized areas
+- **Domain expertise** across 1,326+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/usage.md

@@ -12,7 +12,7 @@ Great question! Here's what just happened and what to do next:
 
 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,311+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
+✅ **Downloaded 1,326+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
 ✅ **Made them available** to your AI assistant  
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -32,7 +32,7 @@ Bundles are **recommended lists** of skills grouped by role. They help you decid
 
 **Analogy:**
 
-- You installed a toolbox with 1,311+ tools (✅ done)
+- You installed a toolbox with 1,326+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You don't install bundles—you **pick skills from them**
 
@@ -41,6 +41,7 @@ Bundles are **recommended lists** of skills grouped by role. They help you decid
 ❌ Separate installations  
 ❌ Different download commands  
 ❌ Something most users need to activate during normal install
+❌ Invokable mega-skills like `@essentials` or `/web-wizard`
 
 ### Example: The "Web Wizard" Bundle
 
@@ -53,6 +54,13 @@ When you see the [Web Wizard bundle](bundles.md#-the-web-wizard-pack), it lists:
 
 These are **recommendations** for which skills a web developer should try first. They're already installed—you just need to **use them in your prompts**.
 
+If you want only one bundle active at a time in Antigravity, use the activation scripts instead of trying to invoke the bundle name directly:
+
+```bash
+./scripts/activate-skills.sh --clear Essentials
+./scripts/activate-skills.sh --clear "Web Wizard"
+```
+
 ---
 
 ## Step 2: How to Actually Execute/Use a Skill
@@ -88,6 +96,8 @@ The exact syntax varies by tool, but it's always simple:
 Use the brainstorming skill to help me plan my app
 ```
 
+If Gemini CLI starts hanging after a few turns, try a fresh conversation and temporarily reduce the active set to just 2-5 skills to rule out context growth.
+
 #### Codex CLI
 
 ```bash
@@ -192,7 +202,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Step 5: Picking Your First Skills (Practical Advice)
 
-Don't try to use all 1,311+ skills at once. Here's a sensible approach:
+Don't try to use all 1,326+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -323,7 +333,7 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 1,311+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,326+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 

package/bundled-skills/docs/users/visual-guide.md

@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,311+ skills live here
+├── 📁 skills/                          ← 1,326+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,311+ total)
+│   └── ... (1,326+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,311+ SKILLS          │
+                    │  1,326+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,311+ total)                │
+│   └── ... (1,326+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/github/SKILL.md

@@ -0,0 +1,76 @@
+---
+name: github
+description: "Use the `gh` CLI for issues, pull requests, Actions runs, and GitHub API queries."
+risk: safe
+source: "Dimillian/Skills (MIT)"
+date_added: "2026-03-25"
+---
+
+# GitHub Skill
+
+Use the `gh` CLI to interact with GitHub. Always specify `--repo owner/repo` when not in a git directory, or use URLs directly.
+
+## When to Use
+
+- When the user asks about GitHub issues, pull requests, workflow runs, or CI failures.
+- When you need `gh issue`, `gh pr`, `gh run`, or `gh api` from the command line.
+
+## Pull Requests
+
+Check CI status on a PR:
+```bash
+gh pr checks 55 --repo owner/repo
+```
+
+List recent workflow runs:
+```bash
+gh run list --repo owner/repo --limit 10
+```
+
+View a run and see which steps failed:
+```bash
+gh run view <run-id> --repo owner/repo
+```
+
+View logs for failed steps only:
+```bash
+gh run view <run-id> --repo owner/repo --log-failed
+```
+
+### Debugging a CI Failure
+
+Follow this sequence to investigate a failing CI run:
+
+1. **Check PR status** — identify which checks are failing:
+   ```bash
+   gh pr checks 55 --repo owner/repo
+   ```
+2. **List recent runs** — find the relevant run ID:
+   ```bash
+   gh run list --repo owner/repo --limit 10
+   ```
+3. **View the failed run** — see which jobs and steps failed:
+   ```bash
+   gh run view <run-id> --repo owner/repo
+   ```
+4. **Fetch failure logs** — get the detailed output for failed steps:
+   ```bash
+   gh run view <run-id> --repo owner/repo --log-failed
+   ```
+
+## API for Advanced Queries
+
+The `gh api` command is useful for accessing data not available through other subcommands.
+
+Get PR with specific fields:
+```bash
+gh api repos/owner/repo/pulls/55 --jq '.title, .state, .user.login'
+```
+
+## JSON Output
+
+Most commands support `--json` for structured output.  You can use `--jq` to filter:
+
+```bash
+gh issue list --repo owner/repo --json number,title --jq '.[] | "\(.number): \(.title)"'
+```

package/bundled-skills/github/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "GitHub"
+  short_description: "Use gh for GitHub workflows"
+  default_prompt: "Use $github to inspect this repository's pull requests, issues, runs, or API data."

package/bundled-skills/ios-debugger-agent/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: ios-debugger-agent
+description: Debug the current iOS project on a booted simulator with XcodeBuildMCP.
+risk: safe
+source: "Dimillian/Skills (MIT)"
+date_added: "2026-03-25"
+---
+
+# iOS Debugger Agent
+
+## Overview
+Use XcodeBuildMCP to build and run the current project scheme on a booted iOS simulator, interact with the UI, and capture logs. Prefer the MCP tools for simulator control, logs, and view inspection.
+
+## When to Use
+
+- When the user asks to run, debug, or inspect an iOS app on a simulator.
+- When you need simulator UI interaction, screenshots, or runtime logs via XcodeBuildMCP.
+
+## Core Workflow
+Follow this sequence unless the user asks for a narrower action.
+
+### 1) Discover the booted simulator
+- Call `mcp__XcodeBuildMCP__list_sims` and select the simulator with state `Booted`.
+- If none are booted, ask the user to boot one (do not boot automatically unless asked).
+
+### 2) Set session defaults
+- Call `mcp__XcodeBuildMCP__session-set-defaults` with:
+  - `projectPath` or `workspacePath` (whichever the repo uses)
+  - `scheme` for the current app
+  - `simulatorId` from the booted device
+  - Optional: `configuration: "Debug"`, `useLatestOS: true`
+
+### 3) Build + run (when requested)
+- Call `mcp__XcodeBuildMCP__build_run_sim`.
+- **If the build fails**, check the error output and retry (optionally with `preferXcodebuild: true`) or escalate to the user before attempting any UI interaction.
+- **After a successful build**, verify the app launched by calling `mcp__XcodeBuildMCP__describe_ui` or `mcp__XcodeBuildMCP__screenshot` before proceeding to UI interaction.
+- If the app is already built and only launch is requested, use `mcp__XcodeBuildMCP__launch_app_sim`.
+- If bundle id is unknown:
+  1) `mcp__XcodeBuildMCP__get_sim_app_path`
+  2) `mcp__XcodeBuildMCP__get_app_bundle_id`
+
+## UI Interaction & Debugging
+Use these when asked to inspect or interact with the running app.
+
+- **Describe UI**: `mcp__XcodeBuildMCP__describe_ui` before tapping or swiping.
+- **Tap**: `mcp__XcodeBuildMCP__tap` (prefer `id` or `label`; use coordinates only if needed).
+- **Type**: `mcp__XcodeBuildMCP__type_text` after focusing a field.
+- **Gestures**: `mcp__XcodeBuildMCP__gesture` for common scrolls and edge swipes.
+- **Screenshot**: `mcp__XcodeBuildMCP__screenshot` for visual confirmation.
+
+## Logs & Console Output
+- Start logs: `mcp__XcodeBuildMCP__start_sim_log_cap` with the app bundle id.
+- Stop logs: `mcp__XcodeBuildMCP__stop_sim_log_cap` and summarize important lines.
+- For console output, set `captureConsole: true` and relaunch if required.
+
+## Troubleshooting
+- If build fails, ask whether to retry with `preferXcodebuild: true`.
+- If the wrong app launches, confirm the scheme and bundle id.
+- If UI elements are not hittable, re-run `describe_ui` after layout changes.

package/bundled-skills/ios-debugger-agent/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "iOS Debugger Agent"
+  short_description: "Debug iOS apps on Simulator"
+  default_prompt: "Use $ios-debugger-agent to build, launch, and inspect the current iOS app on the booted simulator."