security-integration-tests
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.
voice-changer
音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换，支持视频直接输入
audiocut-keyword
音频关键字过滤工具 - 根据关键字配置自动识别并删除音频中的指定内容
vps-security-hardening
|
wespy-fetcher
获取并转换微信公众号/网页文章为 Markdown 的封装 Skill，完整支持 WeSpy 的单篇抓取、微信专辑批量下载、专辑列表获取、HTML/JSON/Markdown 多格式输出。Use when user asks to 抓取微信公众号文章、公众号专辑批量下载、URL 转 Markdown、保存微信文章、mp.weixin.qq.com to markdown.
x-fetcher
抓取 X (Twitter) 推文和长文章的命令行工具。支持普通推文（文字、图片、视频链接）和 X Article 长文章（完整正文，Markdown 格式），自动保存为 Markdown 文件。基于 Jane-xiaoer/x-fetcher 项目。Use when user mentions "抓取推文", "下载推文", "保存 X 文章", "fetch tweet", or provides x.com/twitter.com URLs.
youtube-publisher
Upload and publish videos to YouTube with title, description, tags, thumbnail and subtitles. Use for: youtube upload, publish video, share on youtube.
youtube-to-blog-post
Convert YouTube videos to SEO-optimized blog posts. Extract video title, description, and content, then generate a search-engine-friendly blog post with embedded video, cover images, and optimized metadata. Auto-generates English filenames and saves to the configured Hexo blog posts directory.
youtube-tracker
Track YouTube channels for new uploads. Supports both RSS mode (no API key needed, unlimited quota) and API mode. Use when: add/remove/list tracked YouTube channels, check for new videos, or run scheduled YouTube channel monitoring.
code-roaster
🔥 用 Gordon Ramsay 风格毒舌吐槽代码质量，生成搞笑且实用的代码审查报告
image-generator
通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用
invoice-scanner
扫描目录识别所有类型发票（交通、住宿、餐饮等），提取关键信息并生成分类统计报告
quark-mswnlz-publisher
Automate the full QuarkPanTool → mswnlz GitHub content publishing pipeline. Use when the user provides Quark share URLs and wants: (1) create a batch folder in Quark Drive, (2) save/copy resources into that folder, (3) copy promotional files INTO each shared resource folder, (4) generate permanent encrypted share links with random passcodes, (5) auto-classify items into mswnlz repos (book/movies/etc.) by repo descriptions, (6) append/update the target repo's YYYYMM.md and README month index, (7) git commit+push, (8) send unified Telegram notifications, and (9) force-trigger mswnlz.github.io site rebuild and return the final site URLs.
text-to-speech
文本转语音工具 - 支持脚本解析、情绪标记和后处理，基于 Edge TTS
youtube-downloader
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
cookie-sync
Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.
browserbase-cli
Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, or search the web through the Browserbase Search API. Prefer the Browser skill for interactive browsing; use `bb browse` only when the user explicitly wants the Browserbase CLI path.
search
Use this skill when the user wants to search the web without a full browser session: find URLs, titles, and metadata for a query. Prefer it over a browser when you just need search results, not page content. Returns structured results with titles, URLs, authors, and dates.
functions
Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.
fetch
Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with automatic CAPTCHA solving, anti-bot stealth mode, and residential proxies — ideal for scraping protected websites, bypassing bot detection, and interacting with JavaScript-heavy pages.
ui-test
AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites).
commit-messages
Generate clear, conventional commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or preparing releases.
security-audit
Audit code and dependencies for security vulnerabilities. Use when reviewing PRs, checking dependencies, preparing for deployment, or when user mentions security, vulnerabilities, or audit.
weekly-report
帮助用户梳理周报，按照完整逻辑展示工作价值和边界。当用户说"写周报"、"周报"、"梳理周报"、"整理工作"时触发。
prd-doc-writer
Write and iteratively refine PRD/需求文档 with a story-driven structure and strict staged confirmations (journey map alignment, per-story single-point confirmation, final generation gate). Use when the user asks to 梳理/撰写/完善 PRD、需求文档、用户故事、验收标准，并希望用 ASCII 线框图与 Mermaid（流程图/状态图/时序图）来减少歧义、共同完成文档。
priority-judge
优先级判断助手 - 帮用户从混沌的待办事项中判断优先级，确定现在该做什么。当用户说"我有很多事要做"、"帮我理一下"、"排个优先级"、"今天该做什么"时触发。
product-naming
产品命名协作流程。当用户想给产品/项目/模块起名字时使用。通过"灵魂挖掘 → 约束提取 → 路线发散 → 方向选择 → 竞品验证 → 最终确认"的结构化流程，从模糊想法产出有品牌生命力的名字，避免拍脑袋起名。
backlog-manager
需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
writing-assistant
写作助手 - 当用户说"我想写XX"、"帮我梳理选题"、"怎么形成框架"、"给我组织思路"时触发。根据观点清晰度自动选择最优路线：清晰观点走"框架→内容"，模糊观点走"挖掘→选题→框架→内容"。
project-map-builder
生成或更新用户指定文件夹的 PROJECT_MAP.md。适用于用户要求目录地图/项目地图/代码仓概览/文件夹级说明/更新已有 PROJECT_MAP.md 的场景。必须先询问要扫描的文件夹范围，禁止默认全仓库扫描；支持单目录或多目录（合并或分别生成）。
req-change-workflow
>
thinking-partner
思考拍档 - 陪你从混沌中理清局面，锁定核心问题，拆解卡点，共创解法，落地行动
issue-triage
GitHub Issue 处理协作流程。当用户收到 issue 需要分析和回复时使用。通过"诊断 → 定性 → 决策 → 回复"四步法，从一个 issue 产出准确的根因分析和得体的用户回复，避免误判问题类型或回复不专业。
lesson-builder
帮助用户通过讨论完成课程大纲和课件。当用户说"备课"、"做课件"、"准备课程"时触发。
thought-mining
思维挖掘助手 - 通过对话帮助用户把脑子里的零散想法倒出来、记录下来、整理成文章。覆盖从思维挖掘到成稿的完整流程。
memory-init
在当前目录下初始化记忆系统，生成 CLAUDE.md（可选 AGENT.md 给 Cursor 用）、MEMORY.md 和 memory/ 目录。当用户说"初始化记忆"、"搭建记忆"、"memory init"、"/memory-init"时触发。
multi-perspective-analysis
多视角深度分析。用多个 Sub-agent 分别扮演不同思维框架的顾问，对同一份素材做独立分析，然后交叉汇总共识与分歧，产出结构化诊断报告。当用户说"帮我多视角分析"、"多维分析"、"用多个视角看看"、"帮我诊断一下"时触发。
design-exploration
新功能设计探索流程。当用户有模糊想法要做新功能/新模块时使用。通过"需求收敛 → 技术调研 → ASCII 批量探索 → HTML 设计稿 → 全状态覆盖 → 需求总结"的结构化流程，从模糊想法产出可交付的设计参考文档，作为 PRD 阶段的输入。
git-push
一键推送项目到 GitHub。自动扫描大文件、生成 .gitignore、初始化 Git、创建仓库并推送。支持首次推送、日常更新、版本发布三种模式。当用户说"推到GitHub"、"推送到GitHub"、"git push"、"上传到GitHub"、"发版本"、"打release"、"/git-push"时触发。
github-repo-search
帮助用户搜索和筛选 GitHub 开源项目，输出结构化推荐报告。当用户说"帮我找开源项目"、"搜一下GitHub上有什么"、"找找XX方向的仓库"、"开源项目推荐"、"github搜索"、"/github-search"时触发。
ui-design
UI 样式修改协作流程。当用户要求修改页面样式、调整布局、改 UI 细节时使用。通过"截图定位 → 现状描述 → 方案选择 → 改代码 → 微调"的结构化流程，减少沟通偏差，避免浪费 token。
version-planner
帮助用户把产品需求拆解成渐进式版本规划。当用户说"拆版本"、"版本规划"、"MVP怎么做"、"分阶段实现"时触发。
image-assistant
配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词；先定“需要几张图+每张讲什么”，再压缩文案与隐喻，最后输出可直接复制的生图提示词并迭代。
vision-exploration
终局愿景探索。用户抛出一个模糊 idea，AI 主导引导，通过"追问价值 → 挖掘动机 → 推导演化 → 画终局"的链路，帮用户看到未来最远的可能性。不设限，不收敛，纯发散。
skills-discovery
Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention skills. Skills encode best practices, tools, and techniques you wouldn't otherwise have. Also use when users explicitly ask to find, install, or manage skills.
config-setup
Set up or tune .codemap/config.json so Codemap focuses on code-relevant parts of the repo. Use when config is missing, boilerplate, noisy, or mismatched to the stack.
codemap
Analyze codebase structure, dependencies, changes, cross-agent handoffs, and get code-aware intelligence. Use when user asks about project structure, where code is located, how files connect, what changed, how to resume work, before starting any coding task, when you need risk analysis and skill guidance, or when Codemap should tune project config before analysis.
agent-council
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.
clarify
This skill should be used when the user asks to "clarify requirements", "refine requirements", "specify requirements", "what do I mean", "make this clearer", or when the user's request is ambiguous and needs iterative questioning to become actionable. Also trigger when user says "clarify", "/clarify", or mentions unclear/vague requirements.
Page 281 of 1486 · 74265 results
