hwj123hwj
- 83 skills
- 0 followers
- 5 hours ago last updated
- ▌
- ▌ Wizard · hwj123hwj bundleGenerate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state transition — opening URLs, capturing values, confirming each step, and writing .env files and GitHub Actions secrets.
- ▌ Loop Me · hwj123hwj bundleGrill me about specs for the workflows I want to build, within this workspace.
- ▌ Ask Matt · hwj123hwj bundleAsk which skill or flow fits your situation. A router over the skills in this repo.
- ▌ Grilling · hwj123hwj bundleInterview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
- ▌ Code Review · hwj123hwj bundleReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
- ▌ Huashu Nuwa · hwj123hwj bundle女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。 两种入口：(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。 触发词：「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」。 模糊需求也触发：「我想提升决策质量」「有没有一种思维方式能帮我...」「我需要一个思维顾问」。
- ▌ Taste Skill · hwj123hwjAnti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
- ▌ Edit Article · hwj123hwj bundleEdit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
- ▌ Brainstorming · hwj123hwj bundleYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌
- ▌ Writing Shape · hwj123hwj bundleWriting, exploit — shape raw material into an article, paragraph by paragraph.
- ▌ Obsidian Vault · hwj123hwj bundleSearch, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
- ▌ Emil Design Eng · hwj123hwjThis skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
- ▌ Decision Mapping · hwj123hwjTurn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
- ▌
- ▌ Scaffold Exercises · hwj123hwj bundleCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
- ▌
- ▌ Migrate To Shoehorn · hwj123hwj bundleMigrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
- ▌
- ▌
- ▌
- ▌ Research · hwj123hwj对外部项目进行深度调研分析，产出结构化报告。当用户提到'调研 XXX 项目'、'分析 XXX'、'对比 XXX 和我们的项目'、'研究一下 XXX 的架构/设计'等意图时加载此 skill。
- ▌
- ▌ Diagnosing Bugs · hwj123hwj bundleDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
- ▌ Domain Modeling · hwj123hwj bundleBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
- ▌ Knowledge Skill · hwj123hwj bundle个人知识流水线技能。将网页、B站、微信公众号、小红书、Markdown 等内容先入库到 PostgreSQL 原料池，再编译为 Agent 友好的 Markdown / LLM Wiki 知识网络。 支持 URL 入库、摘要与向量、Markdown 检索、Wiki 编译、飞书知识库发布、记忆层整理和夜间自动收割。
- ▌ Xiaohongshu CLI · hwj123hwj bundleUse xiaohongshu-cli for ALL Xiaohongshu (Little Red Book, 小红书) operations — searching notes, reading content, browsing users, liking, collecting, commenting, following, and posting. Invoke whenever the user requests any Xiaohongshu interaction.
- ▌ Memory Organizer · hwj123hwj长期记忆整理指南。使用当需要清理、组织或重构 MEMORY.md 文件时，或决策哪些信息应该/不应该存储在长期记忆中。提供区分静态知识（长期价值）vs 动态信息（可自动获取）的原则。
- ▌ Setup Pre Commit · hwj123hwj bundleSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
- ▌ Storage Analyzer · hwj123hwj bundlemacOS / Windows 只读存储分析助手（自动识别系统）。扫描整机磁盘占用，找出 占空间大户，把每一项分成 🟢可自动清理 / 🟡需人工判断 / 🔴谨慎清理 三级并给出 可执行处置方案，生成排版精美、可折叠、命令可一键复制的交互式 HTML 报告，并可 起本地服务在网页上一键删除（移废纸篓/直接删）。扫描全程只读。务必在以下场景 使用：用户说"存储分析""磁盘满了""C盘/硬盘满了""空间不够""清理空间" "清理磁盘""占空间""哪些东西占地方""帮我看看存储""看一下电脑存储/空间" "存储空间""电脑空间不够""内存满了/不够/不足""看下内存/存储"（中文口语里 "内存"常指存储空间）"storage analysis""disk cleanup""清缓存""磁盘清理"； 或用户抱怨电脑没空间、想知道什么东西吃硬盘、想要清理建议时。注意：若用户明确 指运行内存/RAM（如"哪个进程吃内存""内存占用高"想看活动监视器），那是 RAM 不是存储，不属于本 skill。
- ▌ Guizang Ppt Skill · hwj123hwj bundle生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。
- ▌ LLM Price Tracker · hwj123hwj bundleTrack and compare LLM API pricing across 147+ providers. Uses models.dev JSON API as primary source + manual scraping for uncatalogued Chinese providers. Triggers: 查模型价格, 价格对比, model pricing, 降价, 新模型, 供应商查询.
- ▌ Content Repurposer · hwj123hwj bundleMarkdown 提示工程驱动的内容复用技能，含 7 个子技能（LinkedIn/Twitter/Medium/Substack/Newsletter/GitHub Pages + 编排器）。支持语音配置系统、emoji 控制系统、正则黑名单。零依赖零修改即可用。
- ▌ Feishu Md Exporter · hwj123hwj bundleExport Feishu/Lark docs or entire Drive folders to local Markdown using the official Open Platform APIs. Use this skill whenever the user asks to export a Feishu/Lark document, docx link, wiki/doc link, Drive folder, folder tree, or batch of Feishu docs to md/Markdown, especially for personal backups of documents that are viewable but not copy/export enabled.
- ▌ Skill Scout · hwj123hwjSearch existing skills before creating a new one. Checks for naming conflicts, tag overlap, and functional duplication. Use BEFORE creating any new skill to prevent wasted effort and registry bloat.
- ▌ Vertex Video Reader · hwj123hwj bundleUse this skill to read, analyze, and understand video files using Google Cloud Vertex AI's lightweight video model (gemini-3.1-flash-lite-preview). Use it whenever the user asks to summarize a video, extract text/actions from a video, describe what happens in an mp4/mov file, or ask questions about a specific video clip.
- ▌ Short Drama Pipeline · hwj123hwj bundleAI 短剧/短视频全链路生产技能。从选题调研、脚本撰写、视频生成到成片输出的完整工作流。 触发词：做一条短视频、做个短剧、AI短剧、帮我选题、生成视频、短视频制作、短剧制作、帮我创作。 复用 tavily（调研）、xiaohongshu-cli/bilibili-cli（平台数据）、libtv-skill（视频生成）。 所有子功能内置于 skills/ 子目录，无需单独安装。
- ▌ Writing Great Skills · hwj123hwj bundleReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
- ▌ Skill Creator · hwj123hwj bundleCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
- ▌ Paddleocr Doc Parsing · hwj123hwj bundleUse this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
- ▌ Short Video Replicator · hwj123hwj bundle短视频爆款复刻一站式工具。输入抖音/B站/YouTube链接或本地视频路径，自动完成： 视频下载与语音转录 → 结构化文字稿 → 三维度爆款分析 → 文案二创 → 口播脚本×3 + 小剧情脚本×3 → Viral-5D评分 → PDF报告导出（可选飞书推送）。 使用场景：拆解爆款视频、学习短视频文案技巧、生成可直接拍摄的二创脚本。 关键词：短视频复刻、爆款分析、口播脚本、小剧情、文案二创、视频转录、PDF报告、抖音、B站
- ▌ Docs Maintainer · hwj123hwj维护 custom-skills 项目文档结构与一致性。当用户提到'维护一下文档'、'更新文档'、'文档整理一下'、'docs 该整理了'、'同步文档和代码'、'整理 docs 目录'等意图时加载此 skill。
- ▌ Setup Matt Pocock Skills · hwj123hwj bundleConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
- ▌ Resolving Merge Conflicts · hwj123hwj bundleUse when you need to resolve an in-progress git merge/rebase conflict.
- ▌ Git Guardrails Claude Code · hwj123hwj bundleSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
- ▌ Paddleocr Text Recognition · hwj123hwj bundleUse this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.
- ▌ React Native Best Practices · hwj123hwj bundleProvides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.
- ▌ Medium Write · hwj123hwj bundleWrite a Medium article in Anuj's voice — measured engineer register, opinionated but evidence-first, 1500-3000 words,
- ▌ Repurpose All · hwj123hwj bundleOrchestrator — one topic, drafts across every format in one pass. Default produces LinkedIn, Twitter, Newsletter, GitHub Pages, Medium, Substack. Skips per-skill clarifying questions using sensible defaults. Use when a topic is worth posting in multiple places and you don't want to invoke each skill separately.
- ▌ Twitter Write · hwj123hwj bundleWrite a Twitter/X post in Anuj's voice. Five modes — quote (aphoristic single line), opinion (sharp contrarian take), share (working-on/reading note with optional link), wow (surprising number plus implication), thread (3-7 tweet structured argument). Asks mode before drafting.
- ▌ Linkedin Write · hwj123hwj bundleWrite a LinkedIn post in Anuj's voice — sharp, contrarian-but-grounded, first-person, no engagement-bait. Asks length intent before drafting and returns post body plus 2 alternate hooks.
- ▌ Substack Write · hwj123hwj bundleWrite a Substack post in Anuj's voice — sharp/contrarian edge, 600-1200 words, email-first cadence, subject line and dek, no engagement-bait. Outputs Markdown ready to paste into Substack.
- ▌ Newsletter Write · hwj123hwj bundleWrite a newsletter issue in Anuj's voice — register between LinkedIn-sharp and Medium-measured, 300-600 words, subject line plus preheader plus scannable body, plain-text-readable, no engagement-bait.
- ▌ Github Page Write · hwj123hwj bundleWrite a long-form post for Anuj's hand-rolled blog at asadani.github.io. Outputs a complete topic-slug/index.html from the single light+dark template (one design, reader toggles light/dark), with inline CSS, ready to commit. Use when Anuj wants to publish on his own site.
- ▌ Asr · hwj123hwj bundleUnified ASR (Speech Recognition) skill with pluggable providers (strategy pattern). Supports: SiliconFlow (TeleAI/TeleSpeechASR). Use for transcribing audio/video files to text. Trigger: "转录", "识别语音", "语音转文字", "ASR", "transcribe", "语音识别". Auto-extracts audio from video files via ffmpeg.
- ▌ Tts · hwj123hwj bundleUnified TTS (Text-to-Speech) skill with pluggable providers (strategy pattern). Supports: Edge TTS (free, no API key), Vertex AI Gemini TTS (Google). Use for generating voiceovers, narration, dubbing. Trigger: "配音", "生成语音", "TTS", "text-to-speech", "合成语音", "语音合成".
- ▌
- ▌ Tavily · hwj123hwjUnified Tavily CLI skill — web search, URL extraction, and deep research via `tvly`. Use this skill when the user wants to search the web, extract content from URLs, conduct research, find articles, look up information, or needs current information from the internet. Routes to the appropriate sub-command based on user intent.
- ▌ To Prd · hwj123hwjTurn the current conversation context into a PRD (Product Requirements Document). Use when user wants to create a PRD, write product requirements, or formalize a feature specification.
- ▌ Triage · hwj123hwj bundleMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
- ▌ Archify · hwj123hwj bundleCreate polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.
- ▌ Handoff · hwj123hwj bundleCompact the current conversation into a handoff document for another agent to pick up. Use when switching sessions, handing off work, or transitioning between agents.
- ▌ Boss CLI · hwj123hwj bundleUse boss-cli for ALL BOSS 直聘 operations — searching jobs, viewing recommendations, managing applications, chatting with recruiters, and batch greeting. Invoke whenever the user requests any job search or recruitment platform interaction on BOSS 直聘.
- ▌ Videocut · hwj123hwj bundle口播视频一站式剪辑 Skill。覆盖转录、口误识别、字幕生成、高清导出的完整工作流。触发词：剪口播、处理视频、帮我剪辑、生成字幕、导出高清。从视频到成片，一步到位。
- ▌
- ▌ Impeccable · hwj123hwj bundleDesigns and iterates production-grade frontend interfaces. Real working code, committed design choices, exceptional craft. Covers websites, landing pages, dashboards, product UI, components, forms, and design systems.
- ▌ Twitter CLI · hwj123hwj bundleUse twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, and user lookups. Invoke whenever the user requests any Twitter/X interaction.
- ▌ Weibo Skill · hwj123hwj微博内容搜索、热搜查看、用户动态及评论读取。使用 m.weibo.cn 移动端接口，无需账号和 API Key。触发场景：(1) 用户要求搜索微博内容或话题，(2) 查看实时微博热搜榜，(3) 获取指定用户的微博动态，(4) 查看某条微博的评论，(5) 用户粘贴了 weibo.com 或 m.weibo.cn 的链接。
- ▌ Bilibili CLI · hwj123hwj bundleCLI skill for Bilibili (哔哩哔哩, B站) with token-efficient YAML output for AI agents to browse videos, users, search, trending, dynamics, favorites, and interactions from the terminal
- ▌ Darwin Skill · hwj123hwj bundleDarwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-climbing with git version control, validates improvements through test prompts, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".
- ▌ Drawio Skill · hwj123hwj bundleUse when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI.
- ▌
- ▌ Douyin Upload · hwj123hwj bundle当你需要登录抖音账号、检查 Cookie、上传视频或发布图文时使用本技能。基于 `uv run douyin` 执行，无需额外自定义脚本。
- ▌ Mp Weixin Ops · hwj123hwj bundle微信公众号一站式运营 Skill。覆盖从热点调研、选题策划、文章写作、配图生成、封面制作、排版转换到推送草稿箱的完整工作流。触发词：写公众号文章、帮我写一篇、公众号运营、从选题到发布、推送草稿箱、帮我配图、生成封面、公众号排版、content planning、publish to WeChat。所有子功能内置于 skills/ 子目录，无需单独安装。
- ▌ Open Kimi Ppt · hwj123hwjCreate, edit, replicate, read, and export presentations. For every PPT task, the default deliverables are BOTH (1) a self-contained PPTD project folder containing the .pptd manifest plus pages/media dependencies and (2) a locally generated .pptx with embedded fonts and fade slide transitions. Use for any presentation, PowerPoint, PPT/PPTX, slide deck, PPTD, infographic, or poster task unless the user explicitly requests another format. Deliver with normal local file/folder links using absolute paths.
- ▌ Video Analyze · hwj123hwj bundle当你需要分析视频内容（抽取关键帧、识别语音）时使用本技能。输出结构化素材，供 Agent 理解视频内容，并可与 content-adapt 配合生成发布文案。
- ▌
- ▌ Writing Beats · hwj123hwj bundleWriting, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.
- ▌ Image Provider · hwj123hwj bundleUnified image generation skill with pluggable providers (strategy pattern). Supports: Vertex AI Imagen (Google), dvcode (company tool). Use for any image generation need: article inline images, cover images, general purpose. Trigger: "生成图片", "配图", "封面图", "generate image", "create cover".
- ▌ Officecli DOCX · hwj123hwjUse this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.
- ▌ Stock Analysis · hwj123hwj bundle股票智能分析技能。输入股票代码（A股/港股/美股），自动完成： 1. 获取实时行情 + 历史K线数据 2. 计算技术指标（MA/MACD/RSI/量能/乖离率） 3. 综合评分（100分制）+ 买卖信号 4. 搜索最新新闻消息面 5. AI综合分析，输出决策看板 触发场景：用户提供股票代码要求分析、问某只股票怎么样、要求看盘分析等。 示例输入：「分析下 TSLA PLTR」「600519怎么样」「帮我看看HK00700」
- ▌ Codebase Design · hwj123hwj bundleShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.