全部能力

issue 流程的阶段 1——通过对话把用户脑子里的问题落成可复现、可追溯的 {slug}-report.md。AI 在这里只问"看到了什么、怎么复现、应该怎样"，不替用户猜根因（那是阶段 2 的事）。同时这一阶段是判断走快速通道还是标准路径的唯一正式判定点：根据用户描述先读一下相关代码，能一眼定位且改动小就直接告知用…

GitLab issue operations. ALWAYS use this skill when user wants to: (1) list issues, (2) view issue details, (3) create new issues, (4) update/close/reopen…

Full conversion audit for any homepage or landing page. Use when someone asks to "review my homepage," "audit my landing page," "why isn't my page converting,"…

Audio analysis with Tone.js and Web Audio API including FFT, frequency data extraction, amplitude measurement, and waveform analysis. Use when extracting audio…

GitLab CI/CD pipeline operations. ALWAYS use this skill when user wants to: (1) view pipeline status, (2) run/trigger pipelines, (3) view/retry jobs, (4) trace…

This skill should be used when the user wants to optimize Next.js frontend performance using Lighthouse, bundle analysis, and animation best practices. Use…

Expert in deploying backends to EC2 instances using CI/CD pipelines, Docker containers, and GitHub Actions

Advanced Clippy configuration for comprehensive Rust linting with custom rules, categories, and IDE integration. Use when configuring linting rules, enforcing code standards, setting up CI linting, or customizing clippy behavior. Trigger terms: clippy, linting, code quality, clippy.toml, pedantic, nursery, restriction, lint configuration, code standards.

Expert in error handling patterns, exception management, error responses, logging, and error recovery strategies for React, Next.js, and NestJS applications

Use when you need to review, improve, or write Java unit tests — including migrating from JUnit 4 to JUnit 5, adopting AssertJ for fluent assertions,…

Write high-quality bug reports that get fixed quickly. Use when reporting bugs, training teams on bug reporting, or establishing bug report standards.

Validate and test Doppler secrets. TRIGGERS - add to Doppler, store secret, validate token, test credentials.

Design and maintain TypeScript packages in a monorepo, including exports and build configuration.

Design high-converting ad creative across Google, Meta, LinkedIn, Twitter/X, and TikTok. Includes platform-specific format specs, A/B testing frameworks, headline formulas, creative iteration methodology, and compliance validation. Use when writing ad copy, generating headline variations, creating ad sets, iterating on winning ads, validating creative against platform specs, or when user mentions ad copy, RSA headlines, Meta ad copy, LinkedIn ads, creative testing, ad variations, or bulk creative production.

Advanced exploratory testing techniques with Session-Based Test Management (SBTM), RST heuristics, and test tours. Use when planning exploration sessions,…

Comprehensive Flutter development patterns covering widgets, testing, performance, security, and animations. Use when you need quick reference for Flutter best…

当用户明确要求"评审国自然标书"、"模拟专家评审"、"审阅 NSFC 申请书"时使用。模拟领域专家视角对 NSFC 标书进行多维度评审，输出分级问题与可执行修改建议。⚠️ 不适用：用户只是想写/改标书某个章节（应使用 nsfc-*-writer 系列技能）、只是想了解评审标准（应直接回答）、没有明确"评审/审阅"意图。

Generate custom Claude Code slash commands via guided question flow. TRIGGERS - create slash command, generate command, custom command.

Step through versioning, tagging, and verification

Bitcoin rune operations — check rune balances, list rune-bearing UTXOs, and transfer runes between addresses with Runestone OP_RETURN encoding. Uses the Unisat…