opencode-skills-collection 2.0.105 → 2.0.107

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

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-04-16T13:48:36.159Z",
+  "updatedAt": "2026-04-16T17:16:52.960Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -419,6 +419,7 @@
     "customer-support",
     "customs-trade-compliance",
     "daily",
+    "daily-gift",
     "daily-news-report",
     "data-engineer",
     "data-engineering-data-driven-feature",
@@ -746,6 +747,7 @@
     "kpi-dashboard-design",
     "kubernetes-architect",
     "kubernetes-deployment",
+    "lambdatest-agent-skills",
     "landing-page-generator",
     "langchain-architecture",
     "langfuse",

package/bundled-skills/daily-gift/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: daily-gift
+description: "Relationship-aware daily gift engine with five-stage creative pipeline — editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video"
+category: productivity
+risk: unknown
+source: community
+source_repo: openclaw/skills
+source_type: community
+date_added: "2026-04-15"
+author: jiawei248
+tags: [creative, gift, personalization, h5, image-generation, video-generation, relationship]
+tools: [openclaw]
+license: "MIT-0"
+license_source: "https://clawhub.ai/jiawei248/daily-gift"
+---
+
+# Daily Gift
+
+## Overview
+
+A relationship-aware gift engine that decides *whether* a gift should exist before deciding *what* it should be. Uses a five-stage creative pipeline to generate personalized daily gifts in H5 (interactive web pages), AI-generated images, or AI-generated videos. The core design principle is "idea before medium" — the creative concept is locked before the output format is chosen.
+
+Published on ClawHub: https://clawhub.ai/jiawei248/daily-gift
+
+## When to Use This Skill
+
+- Use when the agent should autonomously decide whether today deserves a personalized gift
+- Use when a milestone, anniversary, or emotionally meaningful moment should be marked with a creative artifact
+- Use when the user manually requests a visual gift from a quote, poem, or creative brief
+- Use when you want a daily cron-triggered creative output that avoids repetition and template fatigue
+
+## How It Works
+
+### Stage 1: Editorial Judgment
+
+Decide whether a gift should exist today, how heavy it should be (skip / nudge / light / standard / heavy), and what content direction to take (reflect, extension, compass, mirror, play, curation, utility, etc.). Format is NOT chosen here.
+
+### Stage 2: Synthesis + Gift Thesis
+
+Extract six content slots from conversation context (today_theme, emotion_peaks, historical_echo, open_loop, lobster_judgment, preference_hint). Form a gift thesis = anchor (which moment deserves the center) + return (what new perspective the agent gives back). If the thesis has no return, it's not a gift — it's a decorated log entry.
+
+### Stage 2.5: Creative Concept
+
+Generate 5+ concept candidates using seven thinking angles (metaphor flip, format mashup, impossible action, scale shift, role reversal, time distortion, cultural remix). Cross-pollinate with a library of 73 creative seeds across 8 categories. Run three quality checks: concept quality, concept diversity (8 families), and visual/theme collision detection.
+
+### Format Selection
+
+Only after the concept is locked does the system choose the output format (H5, image, or video) based on what best serves the concept.
+
+### Stage 3: Visual Strategy
+
+Choose visual approach, plan assets (pure code, generated background, hybrid), select visual style, and run pre-visualization checks against recent gifts for anti-repetition.
+
+### Stage 4: Rendering
+
+Produce the final artifact. H5 gifts use p5.js/canvas with a quality floor set by built-in templates (300-400 lines of tuned code). Image and video gifts use AI generation APIs. All formats have fallback chains.
+
+## Key Features
+
+- **Five-stage creative pipeline** with explicit quality gates between stages
+- **Multi-layer anti-repetition**: concept family, visual elements, theme, style, content direction — each tracked across sliding windows of recent gifts
+- **Three-layer user taste profile**: Layer 1 (identity — stable), Layer 2 (context — updates every 5-7 gifts), Layer 3 (signals — auto-appended after every gift)
+- **Three runtime modes**: onboarding setup, daily cron, and manual trigger
+- **11 content directions**: reflect, extension, compass, mirror, gift-from-elsewhere, play, real-world-nudge, curation, delayed-payoff, openclaw-inner-life, utility
+- **8 concept families**: borrowed-media, interactive-object, transformation, narrative, data-viz, game-puzzle, real-world, poetic-literary
+
+## Best Practices
+
+- ✅ Let the editorial judgment decide — not every day needs a gift
+- ✅ Generate 5+ concept candidates before selecting one
+- ✅ Check recent gifts for visual and thematic collision before rendering
+- ✅ Use the taste profile to personalize over time
+- ❌ Don't skip straight from thesis to rendering without a real creative concept
+- ❌ Don't default to "reflect on today" every time — vary content direction
+- ❌ Don't choose the format before locking the concept
+
+## Limitations
+
+- Requires API keys for image/video generation (optional — H5 works without them)
+- Cron mode runs in the agent's main session for full conversation context access
+- Shell scripts make external API calls for rendering and asset fetching
+- The skill creates and manages local workspace files for state, history, and taste profiling
+
+## Security & Safety Notes
+
+- The skill creates a recurring cron job for daily gift delivery. Review and approve the cron setup step.
+- Shell scripts in `scripts/` call external APIs (image generation, video generation, asset hosting). Supply API keys only after reviewing which scripts use them.
+- User taste data and gift history are stored locally in `workspace/daily-gift/`. No data is sent to external services beyond the configured rendering APIs.
+- The skill reads conversation context and memory files to inform editorial judgment — this is core to personalization but means it has broad read access within the agent's workspace.
+
+## Related Skills
+
+- Image generation skills — for standalone image creation without the gift pipeline
+- Cron/scheduling skills — for understanding the daily trigger mechanism

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

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.410+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.412+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 1,1.410+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,1.412+ skills
 
 This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
 
@@ -23,7 +23,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With over 1,1.410 skills, this approach fills the context window before user messages are even added, causing truncation.
+With over 1,1.412 skills, this approach fills the context window before user messages are even added, causing 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 1,410+ skills installed.
+This pattern avoids context overflow when you have 1,412+ 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 1,410+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,412+ 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 1,410+ 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 1,412+ 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 `1,410+ Agentic Skills`;
+- use a clean preview image that says `1,412+ 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 1,410+ skills from the skills directory
+- All 1,412+ skills from the skills directory
 
 ## When to Update
 

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

@@ -673,4 +673,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: March 2026 | Total Skills: 1,410+ | Total Bundles: 37_
+_Last updated: March 2026 | Total Skills: 1,412+ | Total Bundles: 37_

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

@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the
 
 ## Why use this repo for Claude Code
 
-- It includes 1,410+ skills instead of a narrow single-domain starter pack.
+- It includes 1,412+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

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

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - 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 1,410+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,412+ 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 (V10.1.0)
+# Getting Started with Antigravity Awesome Skills (V10.2.0)
 
 **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 1,410+ specialized areas
+- **Domain expertise** across 1,412+ 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

@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l
 
 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,410+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
+✅ **Downloaded 1,412+ 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)
 
@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide
 
 **Analogy:**
 
-- You installed a toolbox with 1,410+ tools (✅ done)
+- You installed a toolbox with 1,412+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin
 
@@ -212,7 +212,7 @@ 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 1,410+ skills at once. Here's a sensible approach:
+Don't try to use all 1,412+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -343,7 +343,7 @@ 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 1,410+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,412+ 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/                          ← 1,410+ skills live here
+├── 📁 skills/                          ← 1,412+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,410+ total)
+│   └── ... (1,412+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,410+ SKILLS          │
+                    │  1,412+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,410+ total)                │
+│   └── ... (1,412+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/lambdatest-agent-skills/SKILL.md

@@ -0,0 +1,229 @@
+---
+name: lambdatest-agent-skills
+description: "Production-grade test automation skills for 46 frameworks across E2E, unit, mobile, BDD, visual, and cloud testing in 15+ languages."
+category: testing
+risk: safe
+source: community
+source_repo: LambdaTest/agent-skills
+source_type: community
+date_added: "2026-04-16"
+author: tanveer-farooq
+tags: [testing, test-automation, e2e, unit-testing, mobile-testing, bdd, selenium, playwright, cypress, jest, pytest, appium, lambdatest]
+tools: [claude, cursor, gemini, copilot]
+license: "MIT"
+license_source: "https://github.com/LambdaTest/agent-skills/blob/main/LICENSE"
+---
+
+# LambdaTest Agent Skills — Test Automation Registry (46 Skills)
+
+## Overview
+
+This skill is a curated index of 46 production-grade test automation skills sourced from the [LambdaTest/agent-skills](https://github.com/LambdaTest/agent-skills) repository. It teaches AI coding assistants how to write, structure, and execute test automation code across every major framework and 15+ programming languages. Instead of generating generic test code, the AI becomes a senior QA automation architect that understands correct project structure, dependency versions, cloud execution, CI/CD integration, and common debugging patterns for each framework.
+
+This skill adapts material from an external GitHub repository:
+- `source_repo: LambdaTest/agent-skills`
+- `source_type: community`
+
+## When to Use This Skill
+
+- Use when you need to write, scaffold, or review test automation code for any major framework
+- Use when working with Selenium, Playwright, Cypress, Jest, pytest, Appium, or any of the 46 supported frameworks
+- Use when setting up a new test project and need the correct project structure, config files, and dependencies
+- Use when integrating tests into a CI/CD pipeline (GitHub Actions, Jenkins, GitLab CI)
+- Use when migrating tests between frameworks (e.g. Selenium → Playwright, Puppeteer → Cypress)
+- Use when running tests on cloud infrastructure such as LambdaTest / TestMu AI
+- Use when the user asks how to write, debug, or scale automated tests
+
+## How It Works
+
+### Step 1: Identify the Framework and Language
+
+Determine which testing framework and programming language the user is working with. Match it to one of the 46 supported skills below. Each skill covers a specific framework with language-appropriate code patterns.
+
+### Step 2: Apply the Correct Skill Context
+
+Load the relevant framework skill from the registry below. Each skill includes: project setup and dependencies, core code patterns, page objects or test utilities, cloud execution configuration, CI/CD integration, a debugging table for common problems, and a best practices checklist.
+
+### Step 3: Generate Production-Ready Test Code
+
+Use the loaded skill context to generate test code that follows real-world conventions — not generic boilerplate. Apply correct import paths, configuration formats, assertion libraries, and runner commands specific to the framework and language.
+
+### Step 4: Configure for Local or Cloud Execution
+
+If the user wants to run tests locally, apply local runner configuration. If running on LambdaTest / TestMu AI cloud, configure RemoteWebDriver capabilities or the appropriate cloud SDK, and set `LT_USERNAME` and `LT_ACCESS_KEY` from environment variables — never hardcode credentials.
+
+### Step 5: Add CI/CD Integration
+
+When requested, generate a GitHub Actions (or Jenkins / GitLab CI) workflow that runs the tests in parallel, uploads reports, and captures artifacts on failure.
+
+## Skill Registry
+
+### 🌐 E2E / Browser Testing (15 skills)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `selenium-skill` | Java, Python, JS, C#, Ruby | Selenium WebDriver with cross-browser and cloud support |
+| `playwright-skill` | JS, TS, Python, Java, C# | Playwright browser automation with API mocking |
+| `cypress-skill` | JS, TS | Cypress E2E and component testing |
+| `webdriverio-skill` | JS, TS | WebdriverIO with page objects and cloud integration |
+| `puppeteer-skill` | JS, TS | Puppeteer Chrome automation |
+| `testcafe-skill` | JS, TS | TestCafe cross-browser testing |
+| `nightwatchjs-skill` | JS, TS | Nightwatch.js browser automation |
+| `capybara-skill` | Ruby | Capybara acceptance testing |
+| `geb-skill` | Groovy | Geb Groovy browser automation |
+| `selenide-skill` | Java | Selenide fluent Selenium wrapper |
+| `nemojs-skill` | JS | Nemo.js PayPal browser automation |
+| `protractor-skill` | JS, TS | Protractor Angular E2E testing |
+| `codeception-skill` | PHP | Codeception full-stack PHP testing |
+| `laravel-dusk-skill` | PHP | Laravel Dusk browser testing |
+| `robot-framework-skill` | Python, Robot | Robot Framework keyword-driven testing |
+
+### 🧪 Unit Testing (15 skills)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `jest-skill` | JS, TS | Jest unit and integration tests with mocking |
+| `junit-5-skill` | Java | JUnit 5 with parameterized tests and extensions |
+| `pytest-skill` | Python | pytest with fixtures, parametrize, and plugins |
+| `testng-skill` | Java | TestNG with data providers and parallel execution |
+| `vitest-skill` | JS, TS | Vitest for Vite projects |
+| `mocha-skill` | JS, TS | Mocha with Chai assertions |
+| `jasmine-skill` | JS, TS | Jasmine BDD-style unit testing |
+| `karma-skill` | JS, TS | Karma test runner |
+| `xunit-skill` | C# | xUnit.net for .NET |
+| `nunit-skill` | C# | NUnit for .NET |
+| `mstest-skill` | C# | MSTest for .NET |
+| `rspec-skill` | Ruby | RSpec with shared examples |
+| `phpunit-skill` | PHP | PHPUnit with data providers |
+| `testunit-skill` | Ruby | Test::Unit Ruby testing |
+| `unittest-skill` | Python | Python unittest with mocking |
+
+### 📱 Mobile Testing (5 skills)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `appium-skill` | Java, Python, JS, Ruby, C# | Appium mobile testing for iOS and Android |
+| `espresso-skill` | Java, Kotlin | Espresso Android UI testing |
+| `xcuitest-skill` | Swift, Obj-C | XCUITest iOS UI testing |
+| `flutter-testing-skill` | Dart | Flutter widget and integration tests |
+| `detox-skill` | JS, TS | Detox React Native E2E testing |
+
+### 📋 BDD Testing (7 skills)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `cucumber-skill` | Java, JS, Ruby, TS | Cucumber Gherkin BDD |
+| `specflow-skill` | C# | SpecFlow .NET BDD with Gherkin |
+| `serenity-bdd-skill` | Java | Serenity BDD with Screenplay pattern |
+| `behave-skill` | Python | Behave Python BDD |
+| `behat-skill` | PHP | Behat BDD for PHP |
+| `gauge-skill` | Java, Python, JS, Ruby, C# | Gauge specification-based testing |
+| `lettuce-skill` | Python | Lettuce Python BDD testing |
+
+### 👁️ Visual Testing (1 skill)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `smartui-skill` | JS, TS, Java | SmartUI visual regression testing |
+
+### ☁️ Cloud Testing (1 skill)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `hyperexecute-skill` | YAML | HyperExecute cloud test orchestration |
+
+### 🔄 Migration (1 skill)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `test-framework-migration-skill` | JS, TS, Java, Python, C# | Convert tests between Selenium, Playwright, Puppeteer, Cypress |
+
+### 🔄 DevOps / CI/CD (1 skill)
+
+| Skill | Languages | Description |
+|---|---|---|
+| `cicd-pipeline-skill` | YAML | CI/CD pipeline integration for GitHub Actions, Jenkins, GitLab CI |
+
+## Examples
+
+### Example 1: Scaffold a Playwright test in TypeScript
+
+```
+"Write Playwright tests for the login page using TypeScript and run them on Chrome and Firefox"
+```
+
+The skill will generate: correct `playwright.config.ts`, a typed Page Object for the login page, a test file using `@playwright/test`, and a GitHub Actions workflow with parallel execution.
+
+### Example 2: Run Selenium tests on LambdaTest cloud
+
+```
+"Run my Selenium Java tests on Chrome, Firefox, and Safari on LambdaTest with OS Windows 11 and macOS Sonoma"
+```
+
+The skill will configure `RemoteWebDriver` with LambdaTest capabilities, read `LT_USERNAME` and `LT_ACCESS_KEY` from environment variables, and set up a parallel TestNG suite.
+
+### Example 3: Migrate Selenium tests to Playwright
+
+```
+"Migrate my existing Selenium Python tests to Playwright"
+```
+
+The skill uses `test-framework-migration-skill` to map Selenium locators, waits, and assertions to their Playwright equivalents, preserving test intent while updating syntax.
+
+### Example 4: Set up pytest with fixtures
+
+```
+"Create a pytest test suite for the payments API with fixtures and parametrized test cases"
+```
+
+The skill generates a `conftest.py` with shared fixtures, parametrized test cases using `@pytest.mark.parametrize`, and a `pytest.ini` config with coverage reporting.
+
+## Best Practices
+
+- ✅ Always use environment variables for cloud credentials (`LT_USERNAME`, `LT_ACCESS_KEY`) — never hardcode them
+- ✅ Use Page Object Model (POM) to keep test logic separate from UI selectors
+- ✅ Prefer explicit waits over fixed `sleep()` calls in all frameworks
+- ✅ Run tests in parallel where the framework supports it to reduce execution time
+- ✅ Always capture screenshots and logs on test failure for easier debugging
+- ✅ Match dependency versions to what each framework officially recommends — avoid mixing major versions
+- ❌ Don't write tests that depend on test execution order
+- ❌ Don't hardcode URLs, credentials, or environment-specific values inside test files
+- ❌ Don't skip writing assertions — a test without assertions is not a test
+- ❌ Don't ignore flaky tests — investigate and fix root cause rather than adding retries as a permanent fix
+
+## Limitations
+
+- This skill is an index and trigger guide. The full implementation details for each framework live in the individual skill files at [LambdaTest/agent-skills](https://github.com/LambdaTest/agent-skills).
+- This skill does not replace framework-specific documentation, environment setup, or expert QA review.
+- Cloud execution examples assume a valid LambdaTest / TestMu AI account. Stop and ask the user for their setup details if credentials or target environments are unclear.
+- Mobile testing skills (Appium, Espresso, XCUITest, Flutter, Detox) require platform-specific toolchains (Android SDK, Xcode) that must be installed separately.
+
+## Security & Safety Notes
+
+- Never include `LT_USERNAME`, `LT_ACCESS_KEY`, API tokens, or any credentials in generated code. Always reference them via environment variables.
+- When generating CI/CD pipelines, store secrets in GitHub Actions Secrets or equivalent — never in plaintext YAML.
+- Installation commands (`npm install`, `pip install`, `mvn install`) should only be run in local development or authorized CI environments.
+
+## Common Pitfalls
+
+- **Problem:** Tests pass locally but fail on CI
+  **Solution:** Ensure headless mode is enabled in CI, and that browser versions match between local and CI environments. Use the framework's built-in CI detection where available.
+
+- **Problem:** Flaky tests due to timing issues
+  **Solution:** Replace `sleep()` with explicit waits — `waitForSelector` in Playwright, `WebDriverWait` in Selenium, `cy.get().should()` in Cypress.
+
+- **Problem:** Cloud tests fail with authentication errors
+  **Solution:** Verify `LT_USERNAME` and `LT_ACCESS_KEY` are correctly set as environment variables and match the credentials on the LambdaTest dashboard.
+
+- **Problem:** Wrong browser capabilities for cloud execution
+  **Solution:** Use the LambdaTest Capabilities Generator at https://www.lambdatest.com/capabilities-generator/ to get the correct capability object for your target browser and OS.
+
+- **Problem:** Mobile tests fail with "device not found"
+  **Solution:** For local runs, verify the emulator/simulator is running and `adb devices` (Android) or Simulator is active (iOS). For cloud runs, check the device name matches exactly what LambdaTest supports.
+
+## Related Skills
+
+- `@test-driven-development` — Use when you want to design tests before writing implementation code
+- `@testing-patterns` — Use for general testing design patterns and strategies
+- `@cicd-pipeline-skill` — Use when setting up end-to-end CI/CD pipelines with test automation
+- `@debugging-strategies` — Use when diagnosing systematic test failures

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "2.0.105",
+  "version": "2.0.107",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -9355,6 +9355,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "daily-gift",
+    "path": "skills/daily-gift",
+    "category": "productivity",
+    "name": "daily-gift",
+    "description": "Relationship-aware daily gift engine with five-stage creative pipeline \u2014 editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video",
+    "risk": "unknown",
+    "source": "community",
+    "date_added": "2026-04-15",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "daily-news-report",
     "path": "skills/daily-news-report",
@@ -16421,6 +16443,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "lambdatest-agent-skills",
+    "path": "skills/lambdatest-agent-skills",
+    "category": "testing",
+    "name": "lambdatest-agent-skills",
+    "description": "Production-grade test automation skills for 46 frameworks across E2E, unit, mobile, BDD, visual, and cloud testing in 15+ languages.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-04-16",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "landing-page-generator",
     "path": "skills/landing-page-generator",