ing

代理技能 - 挑战 - 通过 $agent-challenges 调用

Implement query caching strategies to improve performance. Use when setting up caching layers, configuring Redis, or optimizing database query response times.

Secure blockchain development for EVM, Solana, Cosmos, and TON. Use when building smart contracts, auditing, or integrating on-chain backends.

Quiz yourself on documents you've recently read to test understanding and retention

Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.

Risk-based test strategy for software delivery. Use when defining coverage, setting CI gates, managing flaky tests, or establishing release criteria.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions,…

pr-manager 的 Agent 技能 - 使用 $agent-pr-manager 调用

Audit your OpenClaw environment for credential leaks, unsafe defaults, and missing sandbox configuration. Wizard-style:

Checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Use when implementation tasks are Done and need quality scoring.

Build microservices - Spring Cloud, service mesh, event-driven, resilience patterns

Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network,

Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3,…

Coordinates project documentation creation with single context gathering and project type detection. Use when generating project docs subset.

Audits E2E coverage for critical user-visible journeys and wasteful E2E tests. Use when reviewing E2E journey value.

Use when working with error diagnostics smart debug

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status…

Performs manual testing of Story AC via executable bash scripts in tests/manual/. Use when Story implementation needs hands-on AC verification.

Configures Husky, lint-staged, commitlint, and Python pre-commit hooks. Use when adding Git hook automation to a project.

为应用商店页面生成经优化的 Apple App Store 元数据建议，遵循 ASO 最佳实践。在分析应用列表、优化元数据（标题、副标题、关键词、描述、截图、预览视频、应用内购买名称）或提升 App Store 搜索排名与转化率时使用此技能。 核心能力： - 基于目标关键词研究与竞品分析，生成高转化率标题（30 字符内）与副标题（30 字符内） - 构建 100 字符关键词字段，最大化搜索覆盖与相关性得分 - 撰写符合 Apple 指南的促销文本（170 字符）与描述，突出核心价值主张与功能亮点 - 设计截图叙事结构（3-5 张竖屏/横屏）与 App Preview 视频脚本（15-30 秒） - 优化应用内购买显示名称与描述，提升可发现性 - 提供 A/B 测试方案与迭代策略，基于转化率、展示-安装率、关键词排名等数据 输入处理： - 接收应用名称、类别、目标受众、核心功能、竞品列表、当前元数据（如有）及目标市场（地区/语言） - 识别高潜力关键词：搜索量、竞争度、相关性三维度评估 - 检测元数据违规风险：误导性声明、未授权商标、功能未上线即宣传、截图包含非 iOS 设备 输出规范： - 每项建议标注字符数，确保符合 Apple 硬性限制 - 区分搜索优化（关键词字段、标题）与转化优化（副标题、截图、描述） - 提供 2-3 套标题/副标题/关键词组合供测试 - 截图方案包含：每张视觉焦点、配文文案（≤80 字符）、色彩心理学依据 - 输出格式为可直接提交 App Store Connect 的字段映射表 约束与伦理： - 拒绝生成欺骗性元数据（虚假排名、未实现功能、竞品品牌词堆砌） - 禁止建议利用漏洞行为（如关键词重复填充、误导性类别选择） - 遵循 Apple App Review Guidelines 第 2.3.7、2.3.10、3.1.1 条等元数据相关条款 - 优先长期品牌健康度 over 短期搜索操纵 协同提示：若用户未提供目标市场，默认按中国大陆区简体中文优化，同时标注全球通用英文备选方案。