All authors
Claude Skills by majiayu000
github.com/majiayu00015,497 skills879 installs33,563 views
- Group Commits MsgGroup files and write a conventional commit message for each group, when the user enter the prompt "group commits messages" or "group commit messages" or "group commits message".Votes: 0GitHub stars: 666
- Gzh Ai FeedAI公众号信息源 — Daily scan of AI WeChat public accounts, finding the hottest articles by read count, auto-clustering into topics, and generating a styled HTML report with cover images, metrics, search, and subscription support. Use when the user wants AI daily reports, 公众号爆款, AI content curation, 每日AI热点, or 公众号日报.Votes: 0GitHub stars: 666
- Hallucination DetectionAI 回答中幻觉问题的检测方法(无依据陈述、编造引用、事实错误)。当需要检测大模型应用输出是否存在幻觉时使用。Votes: 0GitHub stars: 666
- HeartmulaHeartMuLa: Suno-like song generation from lyrics + tags.Votes: 0GitHub stars: 666
- Helm Liang 2022 Curiositech Windags SkillsHolistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairnessVotes: 0GitHub stars: 666
- Hermes History IngestIngest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their ~/.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest ~/.hermes", or "what have I worked on in Hermes". Also triggers when the user mentions Hermes memories, Hermes sessions, ~/.hermes/memories, or Hermes skill logs.Votes: 0GitHub stars: 666
- Humanize Ai TextПрименять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеческий стиль. Триггеры - пользователь пишет 'убери AI-стиль', 'перепиши по-человечески', 'сделай естественно', 'убери воду', 'не как ChatGPT', 'убери LLM-штампы'; либо на входе текст с явными маркерами генерации: H2/H3 на каждый абзац, буллеты вместо прозы, штампы 'в современном мире', 'давайте погрузимся', избыток длинных тире, эмодзи-заголовки, обязательные 'надеюсь, это по...Votes: 0GitHub stars: 666
- Humanizer Jdrhyne Agent SkillsRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.Votes: 0GitHub stars: 666
- Humanizer Marysatasselshaped66 Skills Collection 1Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.Votes: 0GitHub stars: 666
- Hypogenic Huang Sh DeepscienceAutomated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.Votes: 0GitHub stars: 666
- Ian Xiaohei Scenes生成“小黑 + 真实物件 + 物理动作 + 留白叙事”的中文配图。默认输出 16:9 正文配图，用于互联网打工人共鸣图、AI 时代职场焦虑、程序员/产品/创作者处境和正文观点隐喻图；遇到“彩蛋模式 / 长卷故事图 / 超横版 / 个人经历 / 项目复盘 / 产品演化 / 成长路径”时，输出小黑长卷故事图。标准模式默认 #FFFFFF 纯白背景；彩蛋长卷模式使用高级近白背景和一条真实物件人生线。样例是高质量模板母版和出图质量标尺；必须对齐其比例、留白、动作清晰度和叙事关系，但不能复刻其物件组合、空间拓扑、小黑姿态或标签位置。Votes: 0GitHub stars: 666
- Idea GenerationGenerate 5–10 business idea candidates from a blank page or a founder's domain context — using pain mining, jobs-to-be-done, trend × capability mapping, constraint relaxation, adjacency search, and founder-market-fit prompts. Each candidate is a structured idea card (segment, JTBD, current alternative, why-now, distribution wedge, monetisation, "feels like"). Load when the user asks to generate business ideas, brainstorm startup ideas, find ideas to work on, says "what business should I start...Votes: 0GitHub stars: 666
- IdeateGenerate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.Votes: 0GitHub stars: 666
- IdeogramUse to write great prompts for Ideogram (Ideogram 4.0) to generate design-grade images for social media — the image-prompt-craft mini-skill for typography + layout, sibling to nano-banana under the image-prompt router. Run when the user wants an Ideogram / AI image prompt where TEXT and LAYOUT matter: quote cards, carousel covers, posters, logos/wordmark concepts, signage, ads with headlines, or any image that must say words correctly. Reads brand-profile for style/palette. Ideogram's standou...Votes: 0GitHub stars: 666
- Image Creation Hub3 visual and image creation skills for Claude Code: cinematic AI image direction, brand identity guidelines, and advanced prompt mastery for image generation models.Votes: 0GitHub stars: 666
- Image GenAI 图片生成器 — 基于 gpt-image-2 模型，支持文生图与图生图，开箱即用。Votes: 0GitHub stars: 666
- Imagine Hero Diwad Code Rsj1SaaS · 개인 사이드 프로젝트의 **랜딩 페이지 히어로 이미지**를 3:2(1536×1024) 전용 프리셋으로 생성한다. 이미지 내부에 텍스트를 넣지 않고(모든 copy는 HTML이 담당), 한쪽 40%를 세이프존으로 비워 CTA·헤드라인을 얹을 수 있게 한다. `--transparent-bg` 플래그 지정 시 `scripts/lib/bg-remove.js`로 배경을 잘라낸 PNG도 함께 저장한다. 사용자가 \"히어로 이미지\", \"랜딩 히어로\", \"imagine-hero\", \"landing page hero\" 등을 말하면 이 스킬이 담당한다.Votes: 0GitHub stars: 666
- Imagine HeroSaaS · 개인 사이드 프로젝트의 **랜딩 페이지 히어로 이미지**를 3:2(1536×1024) 전용 프리셋으로 생성한다. 이미지 내부에 텍스트를 넣지 않고(모든 copy는 HTML이 담당), 한쪽 40%를 세이프존으로 비워 CTA·헤드라인을 얹을 수 있게 한다. `--transparent-bg` 플래그 지정 시 `scripts/lib/bg-remove.js`로 배경을 잘라낸 PNG도 함께 저장한다. 사용자가 "히어로 이미지", "랜딩 히어로", "imagine-hero", "landing page hero" 등을 말하면 이 스킬이 담당한다.Votes: 0GitHub stars: 666
- Imagine Logo Diwad Code Rsj1회사·개인 프로젝트·팀의 **로고 시안 탐색기**. 마크(심볼)만 Codex 이미지 모델로 생성하고 워드마크(회사명 글자)는 `scripts/lib/compose-text.js`로 합성한다. 회사명 텍스트는 AI 프롬프트에 **절대** 포함하지 않으며, 이미지 생성 후 OCR로 글자 검출 시 1회 자동 재생성한다. 3~6개의 서로 다른 방향성 시안을 한 번에 뽑아 \"나쁘지 않은 출발점\"을 빠르게 고르도록 돕는다. `scripts/lib/vectorize.js`로 선택된 1장을 SVG로 벡터화하는 옵션도 제공한다. 사용자가 \"로고 만들어줘\", \"imagine-logo\", \"회사 로고\", \"팀 로고\" 등을 말하면 이 스킬이 담당한다.Votes: 0GitHub stars: 666
- Imagine Logo회사·개인 프로젝트·팀의 **로고 시안 탐색기**. 마크(심볼)만 Codex 이미지 모델로 생성하고 워드마크(회사명 글자)는 `scripts/lib/compose-text.js`로 합성한다. 회사명 텍스트는 AI 프롬프트에 **절대** 포함하지 않으며, 이미지 생성 후 OCR로 글자 검출 시 1회 자동 재생성한다. 3~6개의 서로 다른 방향성 시안을 한 번에 뽑아 "나쁘지 않은 출발점"을 빠르게 고르도록 돕는다. `scripts/lib/vectorize.js`로 선택된 1장을 SVG로 벡터화하는 옵션도 제공한다. 사용자가 "로고 만들어줘", "imagine-logo", "회사 로고", "팀 로고" 등을 말하면 이 스킬이 담당한다.Votes: 0GitHub stars: 666
- Imagine Og Diwad Code Rsj1블로그·랜딩 글의 **OG 이미지 / 소셜 카드**(Twitter / Instagram / LinkedIn)를 플랫폼 프리셋에 맞춰 자동 생성한다. 배경 일러스트만 Codex 이미지 모델로 뽑고, 제목·태그 같은 글자는 AI에 맡기지 않고 공용 후처리 모듈(`scripts/lib/compose-text.js`)로 합성한다. 사용자가 \"OG 이미지\", \"소셜 카드\", \"imagine-og\", \"Twitter 카드\" 등을 말하면 이 스킬이 담당한다. 블로그 수백 편을 일괄 렌더하는 `--bulk` 모드도 지원한다.Votes: 0GitHub stars: 666
- Imagine Og블로그·랜딩 글의 **OG 이미지 / 소셜 카드**(Twitter / Instagram / LinkedIn)를 플랫폼 프리셋에 맞춰 자동 생성한다. 배경 일러스트만 Codex 이미지 모델로 뽑고, 제목·태그 같은 글자는 AI에 맡기지 않고 공용 후처리 모듈(`scripts/lib/compose-text.js`)로 합성한다. 사용자가 "OG 이미지", "소셜 카드", "imagine-og", "Twitter 카드" 등을 말하면 이 스킬이 담당한다. 블로그 수백 편을 일괄 렌더하는 `--bulk` 모드도 지원한다.Votes: 0GitHub stars: 666
- Imagine ThumbYouTube 썸네일 전용 생성기. 배경/인물 일러스트는 Codex 이미지 모델로 뽑고, 제목 텍스트는 **AI가 아니라 Node 후처리**(`scripts/lib/compose-text.js`)로 합성한다. 한국어 글자 깨짐을 원천 차단한다. 사용자가 "썸네일 만들어줘", "imagine-thumb <제목>", "유튜브 썸네일" 등을 말하면 이 스킬이 담당한다. 기본 A/B용 2장을 같은 제목 텍스트로 합성해 저장한다.Votes: 0GitHub stars: 666
- Implement StepImplement a step of a feature, based on the feature notes and issue notes for that step, and any other relevant context. The step to implement is the one mentioned in the prompt, for example "implement step 2 of the CDC gap feature".Votes: 0GitHub stars: 666
- Improve Aiหา AI/LLM improvements ใน scope — prompts, token cost, guardrails, evals — แก้หลัง user confirmVotes: 0GitHub stars: 666
- Improve Nando65 Orathon Second BrainTurn one recurring pain point into one measurable, bounded workflow improvement.Votes: 0GitHub stars: 666
- Improve Prompt Henrygoldsmith07 Wq Claude CodeSingle-pass rewrite of an LLM prompt — paste a prompt or point at a file (system prompt, prompt template, agent definition, SKILL.md) and get an improved version with a rationale for each change. Use when the user wants a prompt improved, optimized, tightened, or reviewed against prompt-engineering best practices.Votes: 0GitHub stars: 666
- Ink Karanmrn KaranagentskillsInk terminal renderer for json-render that turns JSON specs into interactive terminal UIs. Use when working with @json-render/ink, building terminal UIs from JSON, creating terminal component catalogs, or rendering AI-generated specs in the terminal.Votes: 0GitHub stars: 666
- Interview Prep Bliss Fox Rag Knowledge Assist针对 Modular RAG MCP Server 项目的模拟技术面试 Agent。读取用户简历（可选），围绕三个方向进行最多 3 轮深度追问，结束后生成并持久化面试报告（含参考答案、包装识别点评、评分）。Use when user says '模拟面试', '面试练习', '帮我面试', 'mock interview', 'interview practice', '面试', '考我', '开始面试', or wants to practice interviewing about this project.Votes: 0GitHub stars: 666
- Isolate LogosSplit one AI-generated logo sheet (a uniform grid of logos on a near-white background) into individual PNG assets. Each kept cell is auto-cropped to its content, centered on a square canvas, and written twice: an opaque version on white and a -transparent version where the background is flood-filled to alpha 0 from the borders, preserving white areas inside the artwork. Cells are named in reading order, a dash skips a duplicate cell, and name=basename overrides the output base for the project...Votes: 0GitHub stars: 666
- Iter 0SkillX library management — cluster near-duplicate skills, LLM-merge each cluster into one canonical SKILL.md, then LLM-quality-filter every skill. Use to compress a noisy skill library while preserving findability of the skills tasks actually need.Votes: 0GitHub stars: 666
- Jarvisgit 변경량을 self-paced로 폴링하다 직전 리뷰 이후 새 변경이 쌓이거나·위험 경로가 바뀌거나·새 커밋이 생기면 jarvis-once 단발 리뷰를 자동 실행하는 워치 루프. 반복은 /loop의 self-paced 모드 위에서 도므로 반드시 /loop /jarvis로 띄운다. 고정 라인/파일 임계값은 없다. args(key=value)로 강도 프리셋(strength)·폴링 간격·경로·위험 경로를 설정한다. args 없이 부르면 최초 1회 강도를 물어본다(이전 설정은 .jarvis/args에서 자동 복원). 첫 로드 직후엔 잠깐 빠르게 폴링한다(warmup). "jarvis", "변경 감지 리뷰 루프", "jarvis 워치" 요청 시 사용.Votes: 0GitHub stars: 666
- JevTypeSafe AI's Jev System One model for typed software decisions: Choice/Score/Noul question primitives, state design, confidence gating, the direct api.typesafe.ai /v1/systemone API, typesafe-sdk (Python) and @typesafe-ai/sdk (JS), Cloudflare Workers AI typesafe/jev (binding, REST, AI Gateway), Vercel AI Gateway/OpenRouter/LiteLLM routes, errors incl. 401-vs-403, limits, pricing, Jev 1.13 weaknesses, prompt-injection risk. WHEN: \"jev\", \"Jev 1.13\", \"TypeSafe\", \"typesafe.ai\", \"typesafe...Votes: 0GitHub stars: 666
- Job Hunting Ai AgentSearch and filter AI Agent / LLM internship positions in Shanghai for a 2024-cohort AI undergraduate. Covers company lists (955.WLB, 996.ICU), known job links, search strategy, and pitfalls.Votes: 0GitHub stars: 666
- JunieReference system prompt and tool schemas for Junie. Use when imitating, comparing, or analyzing Junie's prompting style; designing prompts inspired by Junie; or answering questions about how Junie is prompted.Votes: 0GitHub stars: 666
- Kanso PromptingUse when rewriting, sharpening, or producing a prompt for Claude or another current frontier model. Sets standing rules for getting better LLM output through better prompts. Loaded by /kanso-task; not directly invoked by the user.Votes: 0GitHub stars: 666
- Karpathy GuidelinesBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.Votes: 0GitHub stars: 666
- Khazix Writer Xfs96192 Claude Config数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。Votes: 0GitHub stars: 666
- Kimi Ask Wonecosystem 2300 SkillsDeliberative consultation with Kimi API. Ask, evaluate, critique, iterate until workable agreement.Votes: 0GitHub stars: 666
- KiroReference system prompt and tool schemas for Kiro. Use when imitating, comparing, or analyzing Kiro's prompting style; designing prompts inspired by Kiro; or answering questions about how Kiro is prompted.Votes: 0GitHub stars: 666
- Kling Prompter生成符合 Kling 3.0（可灵 3.0，快手）规则的视频提示词。三种写法自适应：4 部分基础公式（短视频）/ 5 层进阶公式（剧情+音频）/ 图生视频专用（只描述运动）。Kling 是 2026 年中文理解最强、原生音画同步、最长 2 分钟、支持角色定向发声、Motion Brush 的电影级模型。用于"用 Kling 生成视频"、"可灵 AI 提示词"、"中文视频生成"、"带原生音频的剧情视频"、"图生视频"、"角色对话视频"等触发场景。Votes: 0GitHub stars: 666
- rust-best-practicesHelps write high-quality, idiomatic Rust code following Microsoft Pragmatic Rust Guidelines. Use when writing, reviewing, optimizing Rust code, or dealing with lifetimes, borrow checker, memory safety, cargo, and async Rust.Votes: 0GitHub stars: 286
- Ask OpencliAsk Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.Votes: 0GitHub stars: 286
- Clash DoctorClash Verge 诊断与配置管理。网络诊断、配置 AI 工具路由规则（Claude/Codex/Cursor/Warp）、查看/克隆订阅配置、切换配置文件。当用户遇到网络问题、要配置代理规则、切换订阅、查看 Clash 配置时使用Votes: 0GitHub stars: 286
- Clash Routes查看指定进程的代理线路。通过 Mihomo API 查询当前活跃连接，显示进程匹配的规则和代理链路。用于确认某个进程（如 claude、chrome）走的是哪条订阅线路Votes: 0GitHub stars: 286
- Cliproxy Newapi Stack在已经过独立验证的 CLIProxyAPI upstream 之上部署 NewAPI 计费层，把 Codex/Claude/Gemini/Qwen 等订阅账号包装成可计费的 OpenAI 兼容 API。本 Skill 不负责新建裸 CLIProxyAPI；负责 NewAPI Docker 部署、容器到宿主桥接、模型计费倍率、参数化额度修正、多账号 OAuth 凭据热加载和双路径验证。当用户说“给现有 cliproxy 加 NewAPI”“配置 NewAPI 渠道接已运行的 cliproxy”“NewAPI 价格不对”“给现有部署加账号”“172.17.0.1 容器网络”或“408 冷却放大故障”时触发。Votes: 0GitHub stars: 286
- Codex FluentUse when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.Votes: 0GitHub stars: 286
- Comprehensive TestingComplete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest, Vitest, pytest), mock strategies, and CI integration. Use when writing tests, reviewing test quality, or establishing testing standards.Votes: 0GitHub stars: 286
- ContributorEnd-to-end open source contribution workflow: from scanning issues to submitting PRs. Use this skill whenever the user wants to contribute to an open source project, find issues to fix, submit a pull request, fork a repo to contribute, fix a GitHub issue, or mentions 'open source contribution'. Also trigger when they provide a GitHub repo URL and ask about contributing, say things like 'help me submit a PR', 'find good first issues', 'I want to contribute to X', or mention fixing bugs in some...Votes: 0GitHub stars: 286
- Css DebugUse this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.Votes: 0GitHub stars: 286