全部能力

实现标准化 API 错误响应，包含恰当的状态码、日志记录和用户友好的提示信息。适用于构建生产环境 API、实现…

Use when implementing haptic feedback, Core Haptics patterns, audio-haptic synchronization, or debugging haptic issues - covers UIFeedbackGenerator,…

当用户要求设计多-agent系统、创建agent架构、定义agent通信模式或构建自主agent工作流时使用。

Use when asked to "strategic narrative", "Andy Raskin", "tell our company story", "write a pitch deck", "explain why customers should care", or "movement…

Expert sales strategy and operations guidance for B2B SaaS companies. Use when designing sales processes, implementing qualification frameworks (MEDDIC, BANT,…

Implements secure session management with JWT tokens, Redis storage, refresh flows, and proper cookie configuration. Use when building authentication systems,…

Application-level React performance optimization covering React Compiler mastery, bundle optimization, rendering performance, data fetching, Core Web Vitals,…

Write React components with minimal state, proper memoization, and type-safe patterns. Use when creating components, managing state, or optimizing renders.

This skill creates or updates a README.md file in the GitHub home directory of the current project. The README.md file it generates will conform to GitHub best…

Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.

Cross-platform operating system automation and screen control toolkit. Use when users need screenshots, mouse/keyboard control, visual recognition, window…

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin…

Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (as_type, score_current_span, should_export_span,…

触发：当你准备下判断、做决策或提出建议，但事实、上下文或一手信息还不充分时优先调用；常见信号包括 unknowns、信息缺口、证据不足、领域陌生、需要先摸清现状。 English: Trigger before making claims or decisions when context is incomplete, evidence is weak, or the domain is unfamiliar. Use this skill to investigate first, gather firsthand facts, and let reality shape the conclusion.

Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia. Use when: creating custom composables, fetching data with useFetch or useAsyncData, managing global state with useState, integrating Pinia, debugging reactive data issues, or implementing SSR-safe state patterns. Keywords: useFetch, useAsyncData, $fetch, useState, composables, Pinia, data fetching, state management, reactive, shallow reactivity, reactive keys, transform, pending, error, refresh, dedupe, caching

Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. This skill should be used when writing,…

Reads Microsoft Word (.docx) files and extracts text content. Use when needing to read .docx documents. Requires python-docx package.

Generate pixel-art self-portrait, profile card (自画像卡), emoji GIFs, and meme stickers. Use when: "生成形象"、"画头像"、"avatar"、"self-portrait"、"表情包"、"梗图"、"贴纸"、"sticker"、"换一个"、"重新生成"、"不喜欢"、"regenerate". Also use when: Cola wakes up — display existing avatar or prompt user to generate. Also use when: repairing sticker behavior — if ~/.cola/avatar/ has sticker files but AGENT.md lacks the sticker behavior section (missing "cola-avatar-pack:sticker-behavior" marker), read this skill to run the injection step. Do NOT use when: discussing third-party platform avatar settings or searching for external stickers.

| Type-safe ORM for Cloudflare D1 databases using Drizzle. Use when: building D1 database schemas, writing type-safe SQL queries, managing migrations with…

Optimize Claude Code permissions by finding safe Bash commands from session history and auto-applying them to settings.json. Can run from any coding agent but…