Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Conducts open-ended Q&A on image content based on computer vision and large language models, supporting any questions to receive natural language responses. | 大模型视觉问答（VQA）技能，基于计算机视觉和大语言模型对图片内容进行开放式问答，…
Prefab management. Use when users want to create, instantiate, apply, or unpack prefabs. Triggers: prefab, instantiate, spawn, apply, unpack, variant, 预制体, 实例化, 生成.
Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main bra…
Use when reviewing, auditing, or improving E2E test specs for Playwright, Cypress, or Puppeteer — static code analysis of existing test files, not diagnosing runtime failures. Triggers on "review my t…
Interactive code review for agent iterations. Captures comments, tracks resolution status, and integrates with git diffs.
Pre-commit and pre-merge validation checks. Use before committing changes or declaring work complete to ensure all quality gates pass.
Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.
Create DTOs and MapStruct converters for Spring Boot layered architecture projects. Covers naming conventions, validation annotations, OpenAPI schemas, and conversion patterns. Use when creating DTOs,…
Aws Cdk Development
Control Android devices via ADB with support for UI layout analysis (uiautomator) and visual feedback (screencap). Use when you need to interact with Android apps, perform UI automation, take screensh…
Debugging specialist for errors, test failures, and unexpected
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Optimize agent instruction files by extracting sections into separate files and referencing them. Reduces context size while preserving information.
Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10 coverage, forensic detection, real-time threat interception, and guided hardening.
Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.
Use this skill when analyzing and optimizing LLM API costs. Activate when the user wants to reduce AI API spending, understand token usage, audit LLM costs, optimize prompts for cost efficiency, or tr…
Convert design specifications from Figma, Sketch, or Penpot to Flutter widgets with proper theming
Typed routes, route state, and redirection using go_router. Use when implementing go_router typed routes, guards, or redirects in Flutter.
Use when the user asks to analyze code for test coverage, list what test cases are needed, or review testing strategy — WITHOUT generating actual test code.
Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to reference files for team discussion and handoff.
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-code-review-comprehensive
Java COLA Architecture Guide - Alibaba's COLA Clean Layered Architecture Framework. It is used for DDD layered architecture design, code structure standards, and application architecture refactoring i…
The Xiaosheng Shopping Guide Digital Human Live Streaming Version, also known as the Dream Video Prompt Word Generation System, is based on the collaboration of four intelligent agents (prompt word ge…