opencode-skills-collection 1.0.157 → 1.0.159

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-04-05T18:47:13.154Z",
+  "updatedAt": "2026-04-05T20:35:39.925Z",
   "entries": [
     "00-andruia-consultant",
     "007",

package/bundled-skills/acceptance-orchestrator/SKILL.md

@@ -14,6 +14,12 @@ Orchestrate coding work as a state machine that ends only when acceptance criter
 
 Core rule: **do not optimize for "code changed"; optimize for "DoD proven".**
 
+## When to Use
+
+- The task already has an issue or clear acceptance criteria and should run end-to-end with minimal human re-intervention.
+- You need structured handoff across implementation, review, deployment, and final verification.
+- You want explicit stop conditions and escalation instead of silent partial completion.
+
 ## Required Sub-Skills
 
 - `create-issue-gate`

package/bundled-skills/aegisops-ai/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: aegisops-ai
-description: "Autonomous DevSecOps & FinOps Guardrails. 
-Orchestrates Gemini 3 Flash to audit Linux Kernel patches,
-Terraform cost drifts, and K8s compliance."
+description: "Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance."
 risk: safe
 source: community
 author: Champbreed
@@ -124,4 +122,3 @@ python3 main.py
 
 + - **Repository**: https://github.com/Champbreed/AegisOps-AI
 + - **Documentation**: https://github.com/Champbreed/AegisOps-AI#readme
-

package/bundled-skills/agentmail/SKILL.md

@@ -11,6 +11,12 @@ AgentMail gives AI agents real email addresses (`@theagentmail.net`) with a REST
 
 Base URL: `https://api.theagentmail.net`
 
+## When to Use
+
+- An AI agent needs a real inbox/outbox for signups, verification flows, or transactional communication.
+- You need to provision AgentMail accounts, send messages, read inbox contents, or register inbound webhooks.
+- You need to monitor karma usage or wire email events into agent automation.
+
 ## Quick start
 
 All requests require `Authorization: Bearer am_...` header (API key from dashboard).

package/bundled-skills/agents-md/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.
 
+## When to Use
+
+- The user asks to create, update, or audit `AGENTS.md` or `CLAUDE.md`.
+- The project needs concise, high-signal agent instructions derived from the actual toolchain and repo layout.
+- Existing agent documentation is too long, duplicated, or drifting away from real project conventions.
+
 ## File Setup
 
 1. Create `AGENTS.md` at project root

package/bundled-skills/ai-analyzer/SKILL.md

@@ -10,6 +10,12 @@ source: community
 
 基于AI技术的综合健康分析系统，提供智能健康洞察、风险预测和个性化建议。
 
+## When to Use
+
+- The user wants AI-driven health analysis across multiple health datasets or lifestyle signals.
+- You need anomaly detection, risk prediction, or personalized recommendations based on health inputs.
+- You need generated health reports or question-answering over health metrics and trends.
+
 ## 核心功能
 
 ### 1. 智能健康分析

package/bundled-skills/analyze-project/SKILL.md

@@ -26,6 +26,12 @@ For each session, determine:
 4. Which files/subsystems repeatedly correlate with struggle
 5. What changes would most improve future sessions
 
+## When to Use
+
+- You need a postmortem on AI-assisted coding sessions, especially when scope drift or repeated rework occurred.
+- You want root-cause analysis that separates user/spec issues from agent mistakes, repo friction, or validation gaps.
+- You need evidence-backed recommendations for improving future prompts, repo health, or delivery workflows.
+
 ## Global Rules
 
 - Treat `.resolved.N` counts as **iteration signals**, not proof of failure

package/bundled-skills/antigravity-design-expert/SKILL.md

@@ -8,6 +8,12 @@ date_added: "2026-03-07"
 
 # Antigravity UI & Motion Design Expert
 
+## When to Use
+
+- You are building a highly interactive web interface with spatial depth, glassmorphism, and motion-heavy UI.
+- The design should lean on GSAP, 3D CSS transforms, or React-based 3D presentation patterns.
+- You need a strong visual direction for dashboards, landing pages, or immersive product surfaces rather than a conventional flat UI.
+
 ## 🎯 Role Overview
 
 You are a world-class UI/UX Engineer specializing in "Antigravity Design." Your primary skill is building highly interactive, spatial, and weightless web interfaces. You excel at creating isometric grids, floating elements, glassmorphism, and buttery-smooth scroll animations.

package/bundled-skills/apify-actor-development/SKILL.md

@@ -11,6 +11,12 @@ source: community
 
 **Important:** Before you begin, fill in the `generatedBy` property in the meta section of `.actor/actor.json`. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
 
+## When to Use
+
+- You need to create, modify, or debug an Apify Actor project.
+- The task involves choosing an Apify template, wiring actor inputs/outputs, or implementing actor runtime logic.
+- You need safe setup guidance for `apify` CLI authentication, project bootstrap, or deployment workflow.
+
 ## What are Apify Actors?
 
 Actors are serverless programs inspired by the UNIX philosophy - programs that do one thing well and can be easily combined to build complex systems. They're packaged as Docker images and run in isolated containers in the cloud.

package/bundled-skills/apify-audience-analysis/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Analyze and understand your audience using Apify Actors to extract follower demographics, engagement patterns, and behavior data from multiple platforms.
 
+## When to Use
+
+- You need audience demographics, engagement patterns, or follower behavior from social platforms.
+- The task is to choose and run Apify Actors for audience analysis across Facebook, Instagram, YouTube, or TikTok.
+- You need structured extraction plus a summarized interpretation of audience findings.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-brand-reputation-monitoring/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Scrape reviews, ratings, and brand mentions from multiple platforms using Apify Actors.
 
+## When to Use
+
+- You need to monitor reviews, ratings, or brand mentions across social, travel, or map platforms.
+- The task is to select and run an Apify Actor for brand sentiment or reputation tracking.
+- You need exported monitoring results and a summary of reputation signals.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-competitor-intelligence/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Analyze competitors using Apify Actors to extract data from multiple platforms.
 
+## When to Use
+
+- You need competitor benchmarks for content, reviews, pricing, ads, audience, or channel performance.
+- The task involves selecting Apify Actors to compare competitors across maps, booking, social, or video platforms.
+- You need structured competitor data plus synthesized takeaways for strategy or positioning.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-content-analytics/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Track and analyze content performance using Apify Actors to extract engagement metrics from multiple platforms.
 
+## When to Use
+
+- You need engagement, growth, or ROI metrics for posts, reels, videos, ads, or hashtags.
+- The task is to use Apify Actors to collect cross-platform content performance data.
+- You need exported analytics results and a concise interpretation of what content is performing best.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-ecommerce/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.
 
+## When to Use
+
+- You need product, pricing, review, stock, or seller data from e-commerce sites.
+- The task involves price monitoring, competitor product comparison, MAP enforcement, or review analysis.
+- You need a guided workflow for extracting marketplace data and summarizing findings.
+
 ## Prerequisites
 
 - `.env` file with `APIFY_TOKEN` (at `~/.claude/.env`)

package/bundled-skills/apify-influencer-discovery/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Discover and analyze influencers across multiple platforms using Apify Actors.
 
+## When to Use
+
+- You need to discover creators or influencers for outreach, partnerships, or campaign planning.
+- The task is to evaluate authenticity, engagement, niche fit, or audience signals across social platforms.
+- You need Apify-based extraction plus a shortlist or summary of suitable influencer candidates.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-lead-generation/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Scrape leads from multiple platforms using Apify Actors.
 
+## When to Use
+
+- You need business, creator, or contact leads from maps, search, social, or video platforms.
+- The task involves selecting an Apify Actor to discover prospects and extract outreach data.
+- You need exported lead data plus a concise summary of lead quality or segmentation.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-market-research/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Conduct market research using Apify Actors to extract data from multiple platforms.
 
+## When to Use
+
+- You need market sizing, regional demand, pricing, trend, or consumer behavior data.
+- The task is to gather research inputs from maps, travel, Facebook, Instagram, or trend sources with Apify.
+- You need structured market data plus a synthesized view of opportunities or risks.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/apify-ultimate-scraper/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task.
 
+## When to Use
+
+- The user needs web data extraction but has not yet chosen a specific Apify Actor.
+- You need a general-purpose Apify entry point that maps a broad scraping goal to the most suitable Actor.
+- The task spans multiple platforms and benefits from one unified workflow for actor selection, execution, and summarization.
+
 ## Prerequisites
 (No need to check it upfront)
 

package/bundled-skills/awt-e2e-testing/SKILL.md

@@ -11,6 +11,12 @@ source: "https://github.com/ksgisang/awt-skill"
 
 AWT gives AI coding tools the ability to see and interact with web applications through a real browser. Your AI designs YAML test scenarios; AWT executes them with Playwright.
 
+## When to Use
+
+- You need AI-assisted end-to-end testing through a real browser with declarative YAML scenarios.
+- The test flow depends on visual matching, OCR, or platform auto-detection instead of stable DOM selectors.
+- You want an E2E toolchain that can both execute tests and explain failures for AI coding workflows.
+
 ## What works now
 - YAML scenarios → Playwright with human-like interaction
 - Visual matching: OpenCV template + OCR (no CSS selectors needed)

package/bundled-skills/baseline-ui/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Enforces an opinionated UI baseline to prevent AI-generated interface slop.
 
+## When to Use
+
+- You are building or reviewing Tailwind-based UI and want a strict baseline for accessibility, motion, typography, and layout.
+- The task is to prevent generic or sloppy AI-generated interface decisions before they spread through the codebase.
+- You need concrete UI constraints to apply to a file review or an ongoing frontend implementation.
+
 ## How to use
 
 - `/baseline-ui`

package/bundled-skills/beautiful-prose/SKILL.md

@@ -11,6 +11,12 @@ A hard-edged writing skill for producing timeless, forceful English prose withou
 
 This is a style contract, not a vibe. Treat violations as failures.
 
+## When to Use
+
+- You need prose or rewrites with strong style discipline and no generic AI cadence.
+- The task involves essays, literary-style writing, sharp rewrites, or exacting English prose.
+- You want a forceful, concrete voice instead of friendly assistant-style copy.
+
 ## What this skill does
 
 When active, write prose that is:

package/bundled-skills/blog-writing-guide/SKILL.md

@@ -13,6 +13,12 @@ This skill enforces Sentry's blog writing standards across every post — whethe
 
 What follows are the core principles to internalize and apply to every piece of content.
 
+## When to Use
+
+- You need to draft or edit a Sentry blog post.
+- The task involves technical storytelling, product announcements, or engineering deep-dives in Sentry's blog voice.
+- You want blog content that is opinionated, specific, and technically credible rather than generic marketing copy.
+
 ## The Sentry Voice
 
 **We sound like:** A senior developer at a conference afterparty explaining something they're genuinely excited about — smart, specific, a little irreverent, deeply knowledgeable.

package/bundled-skills/brand-guidelines/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Write user-facing copy following Sentry's brand guidelines.
 
+## When to Use
+
+- You need to write or rewrite user-facing copy in Sentry's voice.
+- The task involves UI text, onboarding, empty states, docs, marketing copy, or other branded content.
+- You need guidance on when to use Plain Speech versus Sentry Voice.
+
 ## Tone Selection
 
 Choose the appropriate tone based on context:

package/bundled-skills/build/SKILL.md

@@ -16,6 +16,12 @@ metadata:
 
 Feature development pipeline - research, plan, track, and implement major features.
 
+## When to Use
+
+- You need a structured workflow for building a major feature across research, planning, implementation, and tracking.
+- The task involves moving a feature through named phases such as `research`, `implementation`, `progress`, or `phase`.
+- You want one command to coordinate status, next steps, and phased delivery for a feature effort.
+
 ## Instructions
 
 This command manages a 4-phase feature development workflow for building major features. Parse `$ARGUMENTS` to determine which subcommand to run.

package/bundled-skills/building-native-ui/SKILL.md

@@ -9,6 +9,12 @@ license: MIT
 
 # Expo UI Guidelines
 
+## When to Use
+
+- You are building a native-feeling Expo Router application and need guidance on navigation, controls, effects, or platform-specific UI.
+- You need to decide whether Expo Go is sufficient or a custom native build is actually required.
+- The task involves modern Expo UI patterns across animations, tabs, headers, storage, media, or visual effects.
+
 ## References
 
 Consult these resources as needed:

package/bundled-skills/cirq/SKILL.md

@@ -12,6 +12,12 @@ source: community
 
 Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.
 
+## When to Use
+
+- You are designing, simulating, or executing quantum circuits with the Cirq ecosystem.
+- You need Google Quantum AI-style primitives, parameterized circuits, or integrations like `cirq-google` and `cirq-ionq`.
+- You are prototyping or teaching quantum workflows in Python and want concrete circuit examples.
+
 ## Installation
 
 ```bash

package/bundled-skills/claude-settings-audit/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Analyze this repository and generate recommended Claude Code `settings.json` permissions for read-only commands.
 
+## When to Use
+
+- You are setting up or auditing Claude Code `settings.json` permissions for a repository.
+- You need to infer a safe read-only allow list from the repo's tech stack, tooling, and monorepo structure.
+- You want to review or replace an existing Claude permissions baseline with something evidence-based.
+
 ## Phase 1: Detect Tech Stack
 
 Run these commands to detect the repository structure:

package/bundled-skills/code-simplifier/SKILL.md

@@ -14,6 +14,12 @@ https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-sim
 
 You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions.
 
+## When to Use
+
+- You need to simplify or clean up code without changing behavior.
+- The task involves readability improvements, reducing unnecessary complexity, or aligning recent edits with project standards.
+- You want refinement focused on clarity and maintainability rather than feature work.
+
 ## Refinement Principles
 
 ### 1. Preserve Functionality

package/bundled-skills/commit/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Follow these conventions when creating commits for Sentry projects.
 
+## When to Use
+
+- The user asks to commit code, prepare a commit message, or save changes in git.
+- You need Sentry-style commit formatting with conventional commit structure and issue references.
+- The task requires enforcing branch safety before committing, especially avoiding direct commits on `main` or `master`.
+
 ## Prerequisites
 
 Before committing, always check the current branch:

package/bundled-skills/comprehensive-review-pr-enhance/SKILL.md

@@ -11,6 +11,12 @@ source: community
 
 # Pull Request Enhancement
 
+## When to Use
+
+- You need to turn a git diff into a reviewer-friendly pull request description.
+- You want a PR summary with change categories, risks, testing notes, and a checklist.
+- The diff is large enough that reviewers need explicit structure instead of a short ad hoc summary.
+
 ## Workflow
 
 1. Run `git diff <base>...HEAD --stat` to identify changed files and scope

package/bundled-skills/conductor-setup/SKILL.md

@@ -12,6 +12,12 @@ metadata:
 
 Set up this Rails project for Conductor, the Mac app for parallel coding agents.
 
+## When to Use
+
+- You need to configure a Rails project so it runs correctly inside Conductor workspaces.
+- The project should support parallel coding agents with isolated ports, Redis settings, and shared secrets.
+- You want the standard `conductor.json`, `bin/conductor-setup`, and `script/server` scaffolding for a Rails repo.
+
 # What to Create
 
 ## 1. conductor.json (project root)

package/bundled-skills/create-branch/SKILL.md

@@ -10,6 +10,12 @@ source: community
 
 Create a git branch with the correct type prefix and a descriptive name following Sentry conventions.
 
+## When to Use
+
+- You need to create a new git branch that follows the repository's naming convention.
+- You are starting a new piece of work from the default branch and need help classifying it as `feat`, `fix`, `docs`, or another branch type.
+- You want the branch name proposed from either the task description or the current local diff.
+
 ## Step 1: Get the Username Prefix
 
 Run `gh api user --jq .login` to get the GitHub username.

package/bundled-skills/create-issue-gate/SKILL.md

@@ -14,6 +14,12 @@ Create GitHub issues as the single tracking entrypoint for tasks, with a hard ga
 
 Core rule: **no explicit, testable acceptance criteria from user => issue stays `draft` and execution is blocked.**
 
+## When to Use
+
+- You are starting a new implementation task and want a GitHub issue to be the required tracking entrypoint.
+- The work must be blocked until the user provides explicit, testable acceptance criteria.
+- You need to distinguish between `draft`, `ready`, and `blocked` work before execution begins.
+
 ## Required Fields
 
 Every issue must include these sections:

package/bundled-skills/create-pr/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 This skill name is kept for compatibility.
 
+## When to Use
+
+- The user explicitly asks for `create-pr` or refers to the legacy skill name.
+- You need to redirect pull request creation work to the canonical `sentry-skills:pr-writer` workflow.
+- The task is specifically about writing or updating a pull request rather than general git operations.
+
 Use `sentry-skills:pr-writer` as the canonical skill for creating and editing pull requests.
 
 If invoked via `create-pr`, run the same workflow and conventions documented in `sentry-skills:pr-writer`.

package/bundled-skills/daily/SKILL.md

@@ -9,6 +9,12 @@ source: community
 date_added: "2026-03-07"
 ---
 
+## When to Use
+
+- You are building a real-time voice or multimodal AI application that uses Daily or Pipecat-style transports.
+- You need guidance on low-latency audio, video, text, and AI service orchestration in one pipeline.
+- You want a capability reference before choosing services, transports, or workflow patterns for an interactive agent.
+
 ## Capabilities
 
 Pipecat enables agents to build production-ready voice and multimodal AI applications with real-time processing. Agents can orchestrate complex AI service pipelines that handle audio, video, and text simultaneously while maintaining ultra-low latency (500-800ms round-trip). The framework abstracts away the complexity of coordinating multiple AI services, network transports, and audio processing, allowing agents to focus on application logic.

package/bundled-skills/differential-review/SKILL.md

@@ -9,6 +9,12 @@ source: community
 
 Security-focused code review for PRs, commits, and diffs.
 
+## When to Use
+
+- You need a security-focused review of a PR, commit range, or diff rather than a general code review.
+- The changes touch auth, crypto, external calls, value transfer, permissions, or other high-risk logic.
+- You need findings backed by code evidence, attack scenarios, and an explicit report artifact.
+
 ## Core Principles
 
 1. **Risk-First**: Focus on auth, crypto, value transfer, external calls

package/bundled-skills/django-access-review/SKILL.md

@@ -22,6 +22,12 @@ Find access control vulnerabilities by investigating how the codebase answers on
 
 **Can User A access, modify, or delete User B's data?**
 
+## When to Use
+
+- You need to review Django or DRF code for access control gaps, IDOR risk, or object-level authorization failures.
+- The task involves confirming whether one user can access, modify, or delete another user's data.
+- You want an investigation-driven authorization review instead of generic pattern matching.
+
 ## Philosophy: Investigation Over Pattern Matching
 
 Do NOT scan for predefined vulnerable patterns. Instead:

package/bundled-skills/django-perf-review/SKILL.md

@@ -11,6 +11,12 @@ source: community
 
 Review Django code for **validated** performance issues. Research the codebase to confirm issues before reporting. Report only what you can prove.
 
+## When to Use
+
+- You need a Django performance review focused on verified ORM and query issues.
+- The code likely has N+1 queries, unbounded querysets, missing indexes, or other database-driven bottlenecks.
+- You want only provable performance findings, not speculative optimization advice.
+
 ## Review Approach
 
 1. **Research first** - Trace data flow, check for existing optimizations, verify data volume

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

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V9.6.0)
+# Getting Started with Antigravity Awesome Skills (V9.7.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/evolution/SKILL.md

@@ -11,6 +11,12 @@ source: community
 
 This skill enables makepad-skills to self-improve continuously during development.
 
+## When to Use
+
+- You are maintaining `makepad-skills` and want the skill library to improve itself during development.
+- You need the workflow for deciding when a new pattern should become a skill update or hook-driven evolution.
+- You are working on self-correction, self-validation, or version adaptation for the skill set.
+
 ## Quick Navigation
 
 | Topic | Description |

package/bundled-skills/expo-cicd-workflows/SKILL.md

@@ -12,6 +12,12 @@ license: MIT License
 
 Help developers write and edit EAS CI/CD workflow YAML files.
 
+## When to Use
+
+- You need to create, edit, or validate `.eas/workflows/*.yml` files for an Expo project.
+- The task involves EAS build pipelines, deployment automation, workflow triggers, or Expo CI/CD configuration.
+- You need schema-backed workflow guidance rather than relying on stale memorized syntax.
+
 ## Reference Documentation
 
 Fetch these resources before generating or validating workflow files. Use the fetch script (implemented using Node.js) in this skill's `scripts/` directory; it caches responses using ETags for efficiency:

package/bundled-skills/expo-dev-client/SKILL.md

@@ -9,6 +9,12 @@ license: MIT
 
 Use EAS Build to create development clients for testing native code changes on physical devices. Use this for creating custom Expo Go clients for testing branches of your app.
 
+## When to Use
+
+- You need an Expo development client because the app depends on custom native code or targets not supported by Expo Go.
+- The task involves building, distributing, or testing EAS development builds on physical devices.
+- You need guidance on when to choose a dev client versus staying on plain Expo Go.
+
 ## Important: When Development Clients Are Needed
 
 **Only create development clients when your app requires custom native code.** Most apps work fine in Expo Go.

package/bundled-skills/expo-tailwind-setup/SKILL.md

@@ -11,6 +11,12 @@ license: MIT
 
 This guide covers setting up Tailwind CSS v4 in Expo using react-native-css and NativeWind v5 for universal styling across iOS, Android, and Web.
 
+## When to Use
+
+- You need to set up Tailwind CSS v4 styling in an Expo app using `react-native-css` and NativeWind v5.
+- The task involves configuring Metro, PostCSS, global CSS, or package versions for Expo + Tailwind.
+- You want one styling setup that works across iOS, Android, and web in an Expo project.
+
 ## Overview
 
 This setup uses:

package/bundled-skills/expo-ui-jetpack-compose/SKILL.md

@@ -12,6 +12,12 @@ description: `@expo/ui/jetpack-compose` package lets you use Jetpack Compose Vie
 
 > The instructions in this skill apply to SDK 55 only. For other SDK versions, refer to the Expo UI Jetpack Compose docs for that version for the most accurate information.
 
+## When to Use
+
+- You need to build Android-native UI in Expo using `@expo/ui/jetpack-compose`.
+- The task involves choosing Compose views or modifiers, embedding them in `Host`, or translating Jetpack Compose patterns into Expo UI code.
+- You are working specifically against Expo SDK 55 behavior for Jetpack Compose integration.
+
 ## Installation
 
 ```bash

package/bundled-skills/expo-ui-swift-ui/SKILL.md

@@ -12,6 +12,12 @@ description: `@expo/ui/swift-ui` package lets you use SwiftUI Views and modifier
 
 > The instructions in this skill apply to SDK 55 only. For other SDK versions, refer to the Expo UI SwiftUI docs for that version for the most accurate information.
 
+## When to Use
+
+- You need to build iOS-native UI in Expo using `@expo/ui/swift-ui`.
+- The task involves selecting SwiftUI views or modifiers, wrapping trees in `Host`, or embedding React Native components with `RNHostView`.
+- You are targeting Expo SDK 55 behavior for SwiftUI integration and extension guidance.
+
 ## Installation
 
 ```bash

package/bundled-skills/family-health-analyzer/SKILL.md

@@ -8,6 +8,12 @@ source: community
 
 # 家庭健康分析技能
 
+## When to Use
+
+- 需要分析家族病史、遗传风险或家庭层面的健康模式时使用。
+- 任务涉及家庭健康报告、家族聚集性疾病识别或预防建议生成。
+- 需要把多个家庭成员的健康数据汇总后做趋势或风险评估。
+
 ## 技能概述
 
 本技能提供家庭健康数据的深度分析,包括: