niannian-workspace

Unit, integration, and E2E testing patterns with framework-specific guidance. Use when asked to "write tests", "add test coverage", "testing strategy", "test this function", "create test suite", "fix flaky tests", or "improve test quality".

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

抖音视频下载工具 - 解析抖音链接，下载视频并发送

根据用户提供的内容方向自动生成提示词并创作爽文小说。适用场景：(1) 用户提供小说方向/题材/关键词，(2) 需要生成章节连贯的长篇爽文，(3) 需要维护角色、地点、情节的连续性，(4) 需要为关键情节生成图解，(5) 需要记录生成失败场景以优化后续创作。支持都市、修仙、玄幻、重生、系统流等多种题材。Use when user asks to write a novel, generate fiction, create stories, or mentions 爽文/小说/写作。

Imported specialist agent skill for architecture designer. Use when requests match this domain or role.

Builds automation workflows from repetitive tasks. Use when user mentions "automate", "save time", "reduce manual work", or has repeated tasks.

工作流任务拆解与模型编排技能。使用场景：(1) 收到复杂工作任务需要拆解为可执行步骤，(2) 需要为不同步骤选择最合适的模型，(3) 需要跟踪工作流进度和模型使用情况，(4) 长时间任务卡住需要问题诊断和解决方案。

Raincloud Plot 可视化工具 — 替代 Dynamite Plot（柱状图 + 误差线），诚实展示数据分布。三合一结构（半小提琴 + 箱线图 + 抖动散点），支持 Plotly/Seaborn/Matplotlib 三种后端。

从源代码自动生成 API 文档、技术文档，支持输出到飞书云文档。包含代码注释提取、 中文文档模板、OpenAPI 规范生成等功能。 **触发场景**： - 用户要求"生成文档"、"写 API 文档"、"自动生成文档" - 需要从代码提取注释生成文档 - 需要输出文档到飞书 - 用户提到"API 文档"、"接口文档"、"技术文档"

PR 审查技能 — 完整的 Pull Request 审查流程，集成 GitHub CLI，支持安全分析、测试覆盖、性能评估、代码质量检查，并可推送飞书通知。Use when: (1) 审查 PR，(2) 检查 PR 安全性，(3) 分析测试覆盖，(4) 评估代码质量，(5) 生成审查报告。触发词：'review PR', '审查PR', '代码审查', 'pr review', '检查PR'。

DuckDB数据分析工具集 — 内存管理/ClickBench基准/结果导出。$700 MacBook也能跑大数据。

Write and run tests using Node.js 25's built-in test runner (node:test). Zero dependencies — includes describe/it, mocking, coverage, expectFailure, rerun-failures, and TypeScript type stripping. Use when: writing unit/integration tests, running test suites, checking coverage, mocking functions, or testing .ts files directly.

Enhanced browser DOM manipulation using PageAgent's page-controller. Injects into any web page to provide precise DOM extraction, interactive element detection (cursor:pointer heuristic), and robust interaction (full event chain simulation, React-compatible input). Use when you need to operate on web pages with precision — clicking, typing, scrolling, form filling, or reading page structure. Combines with frontend-design skill for full design→code→browser-operate workflow.

Python生产级工具集 — logging/异常处理/性能分析。告别print调试，所有新脚本import即用。

年年自我进化引擎 — 自我监控、Agent匹配、任务分解、决策追踪。让年年持续变强的元技能。

Extract article content from any URL as clean Markdown. Uses Scrapling script as primary method (with auto fast→stealth fallback), Jina Reader as alternative for simple pages. Preserves headings, links, images, lists, and code blocks. Use this skill whenever the user wants to fetch, read, extract, scrape, or summarize content from a URL — including blog posts, news articles, WeChat articles (微信公众号), documentation pages, or any web page. Also trigger when the user says things like "帮我读一下这篇文章", "抓取这个网页", "提取正文", or "read this page for me".

Test API endpoints and document responses. Define tests in plain English, run them, get formatted results. Agent-driven Postman alternative.

Search the web using Perplexity's Search API for ranked, real-time web results with advanced filtering. Use when you need to search for current information, market research, trending topics, or when Brave Search is unavailable. Supports recency filtering (day/week/month/year) and returns structured results with titles, URLs, and snippets.

咨询级智能分析系统。将碎片化信息通过结构化思考转化为可执行洞察。 使用场景：(1) 深度行业/市场/竞品分析 (2) 战略规划与决策支持 (3) 复杂问题根因诊断 (4) 创新方案设计 (5) 用户说"分析一下"、"深度研究"、"帮我调研"、"做个报告"时触发。 包含12大分析框架（诊断/战略/创新/决策/系统/理解六大类），支持自适应复杂度分级和多框架组合。

Analyzes codebases and generates comprehensive test suites. Unit tests, integration tests, edge cases, mocking strategies. Supports JavaScript/TypeScript (Jest, Vitest), Python (pytest), Go, and Rust.

年年的第一个学习技能 - 向用户问好

快速摘要技能 - 将长文本/URL 内容精简为要点摘要