全部能力

Mine Instagram comments to extract audience language, pain points, objections, FAQs, and purchase-intent signals from shortlisted posts or Reels.

飞书日历与日程管理工具集。包含日历管理、日程管理、参会人管理、忙闲查询。

Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a…

Complete energy optimization API reference - Power Profiler workflows, timer/network/location/background APIs, iOS 26 BGContinuedProcessingTask, MetricKit…

Use when profiling async/await performance, diagnosing actor contention, or investigating thread pool exhaustion. Covers Swift Concurrency Instruments…

Use when implementing App Shortcuts for instant Siri/Spotlight availability, configuring AppShortcutsProvider, adding suggested phrases, or debugging shortcuts…

在输出包含中文字符与中文标点符号、编写中文文档、根据中文文档生成中文的交互回应、回复用户用中文提出的问题或任务、需要进行中文与非中文混排操作等涉及中文文字与标点符号的使用的场景中，必须使用本 Skill 以获得专业的中文字符的操作指导与行为规范引导。

Use when app runs at unexpected frame rate, stuck at 60fps on ProMotion, frame pacing issues, or configuring render loops. Covers MTKView, CADisplayLink,…

Use when automating Instruments profiling, running headless performance analysis, or integrating profiling into CI/CD - comprehensive xctrace CLI reference…

使用 p5.js 创建算法艺术，支持种子随机性和交互式参数探索。当用户请求使用代码创作艺术时使用，…

根据功能规范生成基于 Tzatziki 的 Cucumber BDD 测试（.feature 文件）。当用户需要编写 Cucumber 测试、添加 BDD 场景、创建 feature 文件、生成测试，或使用 Gherkin 测试应用行为时使用此技能——特别是在 Java/Spring 项目中，使用 Tzatziki 的 HTTP、JPA、Kafka、MongoDB、OpenSearch、日志或 MCP 步骤定义。当用户提及在已包含 Tzatziki/Cucumber 依赖（包括基于 TestNG 的 setup）的项目中编写集成测试、验收测试或端到端测试时，同样适用。

Symptom-based energy troubleshooting - decision trees for 'app at top of battery settings', 'phone gets hot', 'background drain', 'high cellular usage', with…

Use when build times are slow, investigating build performance, analyzing Build Timeline, identifying type checking bottlenecks, enabling compilation caching,…

Use this skill when reviewing, writing, or refactoring code for cleanliness and maintainability following Robert C. Martin's (Uncle Bob) Clean Code principles. Triggers on code review, refactoring, naming improvements, function decomposition, applying SOLID principles, writing clean tests with TDD, identifying code smells, or improving error handling. Covers Clean Code, SOLID, and test-driven development.

Use when first installing Axiom, unsure which skill to use, want an overview of available skills, or need help finding the right skill for your situation —…

OpenAI Codex CLI code review with GPT-5.2-Codex, CI/CD integration

Grafana Cloud Application Observability (APM), Frontend Observability (RUM/Faro), and AI Observability. Covers RED metrics (Rate/Error/Duration), service maps, span metrics from traces, Faro JavaScript/React SDK for browser instrumentation, session replay, AI/LLM model monitoring, and integration with traces/logs/profiles for full-stack correlation. Use when setting up APM, configuring frontend monitoring, analyzing service performance, or monitoring AI/LLM applications.

Dockerfile optimization guidelines from official Docker documentation. This skill should be used when writing, reviewing, or refactoring Dockerfiles to ensure…

Validate, lint, audit, or fix PromQL queries and alerting rules; detects anti-patterns.

Export .pen design to React/Tailwind code. Does ONE thing well. Input: .pen frame ID or file path Output: React component code + Tailwind config Use when: design-exploration or user needs implementation code from a finalized Pencil design.