Claude Skills Directory

alphaparkinc/genpark-influencer-content-performance-analyzer-skill

Analyze supplied creator content metrics and return normalized performance insights.

Alpha-Park/genpark-influencer-creator-fit-scoring-skill

Score creator and campaign fit from supplied audience, topic, reach, and safety signals.

alphaparkinc/genpark-wukong-data-synthesizer

Enterprise Data Synthesizer. Analyzes internal communication logs and unstructured data to generate structured business reports.

boffti/github-profile-readme

Create or upgrade a GitHub *profile* README — the special README.md in the repo named exactly after a username (github.com/<user>/<user>) that renders at the top of the profile page. Use this whenever someone wants to make, design, redesign, refresh, or "level up" their GitHub profile, set up their github.com/<user>/<user> repo, add stats cards / badges / a tech stack / an auto-updating blog feed to their profile, or asks "how do I get that box on my GitHub page." Trigger even when they don't say the word "README" — "make my GitHub look good", "personalize my GitHub", or "set up my dev profile

AKzar1el/god-prompt

Production workflow skill for coding, debugging, architecture, design, deployment, automation, SEO, content, and other substantial build or review work. Use when a task benefits from explicit scope, task classification, evidence-backed execution, verification, and delivery gates. Routes work through the appropriate protocol and scales depth to the task while preserving user and developer authority.

wppoland/hidden-text-detector

Detects hidden text and manipulation attempts in PDF and DOCX documents - white-on-white text, sub-legible fonts, text positioned off-page, invisible render mode, Word's hidden attribute, and invisible Unicode characters. Use when the user asks "does this document contain hidden text", "check this contract for hidden clauses", "is someone trying to manipulate me", "scan this PDF for prompt injection", "is this a scam", or BEFORE analysing any contract, quote, invoice, or document received from an external party.

KondrashovDenis/claude-humanizer-ru-skill

Чистит русские тексты от типичных AI-штампов (канцелярит, кальки с английского, раздутая значимость, чатбот-артефакты). Контекстные режимы — пост ТГ / письмо / личная переписка / копирайтинг сайта / аудит чужого текста на признаки AI. Опциональный voice calibration по образцам пользователя из voice-samples/. Use when Russian text needs to sound less AI-generated, or when auditing suspicious text for AI authorship.

ceoimperiumprojects/imperium-brain

The Ultimate Startup OS for Claude Code. Routes to 18 domain skills across startup ops, competitive research, and content creation. Use when the user mentions anything related to: startups, strategy, fundraising, marketing, sales, product, finance, legal, engineering, competitive research, ecosystem mapping, LinkedIn posts, carousels, presentations, slides, brand identity, tone of voice, SOPs, runbooks, video creation, API discovery, images, visual media, stock photos, or any business/startup/content topic.

kmgcc/iOS-Trace

Agent-native runbook for evidence-based profiling and optimization of native iOS and iPadOS apps with xctrace and Xcode Instruments on physical devices or simulators. Use for CPU or battery use, memory growth or Jetsam, UI hitches, slow launch, concurrency stalls, audio glitches, or network activity. Choose instruments and workload reproduction to fit the issue; bundled scripts are optional helpers.

basejb/isms-p-audit-skill

ISMS-P 인증 사전 점검을 위한 코드/IaC 정적 분석 스킬. 사용자가 "ISMS 점검", "ISMS-P 준비", "보안 감사", "통제항목 점검", "개인정보보호 감사", "정보보호 인증 준비"를 언급하거나, NestJS/ Spring/Django/Rails 같은 백엔드 프로젝트에서 IAM·로깅·암호화·접근통제 미흡 사항을 식별해 달라고 요청할 때 호출한다. Glob/Grep/Read로 코드와 Terraform/CloudFormation/Kubernetes 매니페스트를 스캔해 ISMS-P 통제항목과 매핑된 리스크 보고서를 생성한다. EN: Static analysis skill for ISMS-P (Korean Personal Information & Information Security Management System) pre-audit. Triggers on phrases like "ISMS audit", "ISMS-P readiness", "security compliance check", "Korean privacy audit". Scans source code and IaC to map findings to ISMS-P controls and

alphaparkinc/janitor-ai-skill

A modular GenPark AI Agent skill that interacts with JanitorAI to create, manage, and converse with highly customizable AI personas for storytelling, roleplay, and character-driven interactions.

anhao/jingtian-style

把任意文稿改写成《我的女友景甜》体（景甜体）：短行白描、抵押对位、外围劳动镜头、数字代替情绪、称谓即关系状态、以空置与「什么都不发生」收束的第一人称记账文案。 Use when the user asks for 景甜体、孙宇晨体、孙哥文案、《我的女友景甜》风格、景甜式文案、景甜体改写、记账体改写、克制文风改写, or says 改成景甜体 / 用景甜体重写 / 写成孙宇晨那种记账体, or asks for Justin Sun style / justinsun write style, or runs /jingtian-style.

yanliudesign/linear-style-illustration

Dark "Linear/AI-OS" style technical diagrams — near-black background, cyan × purple × lilac duotone, JetBrains Mono uppercase labels, pill-shaped SVG nodes, glowing hub/kernel layer. Use when the user wants a "Linear 风格 diagram", a dark tech/architecture diagram, a product flow / state machine / layered-stack / hub-and-spoke diagram for a deck or landing page, or references screenshots that look like a dark AI product OS deck. Outputs a self-contained HTML file with inline SVG, ready to drop into a slide deck or export as PNG. Keywords: Linear style diagram, dark tech diagram, kernel diagram,

ClawCap/ManoBrowser

Your hands in the user's real browser. Operate the user's own Chrome with their logged-in sessions — extract data behind login walls, reverse-engineer website APIs into reusable skills, and automate any browser workflow. Use when you need login-required data extraction, API reverse engineering, browser automation, or social media data collection. 给你一双手，像用户一样使用浏览器。在用户已登录的 Chrome 中工作——提取登录墙后的数据、逆向 API 生成可复用 Skill、自动化浏览器工作流。

kajisho5/media-analysis-skill

Measure deterministic facts about a media file (container, streams, video/audio format, silence, loudness, integrity, scene cuts, timing) with local ffprobe/ffmpeg and return a structured Observation. Use when a task needs to *know* something about a video or audio file before deciding anything: duration, resolution, fps, CFR/VFR, codecs, channel layout, where the silence is, how loud it is (LUFS / true peak), whether it decodes cleanly, where hard cuts are. Do not use it to edit, convert, normalise or export media (that is ffmpeg-skill) or to interpret the numbers (that is the agent). Python

bingo33-gif/motionsites-promptcapture

Use when the user asks to create a website (landing page, SaaS site, portfolio, agency site, hero section, etc.) and mentions UI design, or explicitly asks to find website prompts from motionsites.ai. Go to https://motionsites.ai, find the most relevant prompt template for the user's request, and deliver the prompt plus an optimization plan adapted to the user's tech stack. Triggers on natural language like '需要你创建一个网站并且要用到UI设计', '创建一个网站，要用到UI设计', '帮我从 MotionSites 找合适的 prompt', '做一个带动效的落地页'. Do not use for plain coding tasks without UI/website design needs.

kane50613/native-writing

Write, edit, or review prose in English, 台灣繁中, 简体中文, or 日本語 so the reader follows it on the first read. Covers website and app copy, documentation pages and docs-site structure, PR bodies, commit messages and changesets, blog posts, slide decks, books, and messages. Use when asked to write or edit copy, humanize text, remove AI voice, fix translationese, or organize documentation. Other skills use it for every piece of prose they author.

XiangyuSu611/obsidian-theme-designer

Use when the user wants to design, preview, or customize an Obsidian vault theme — including choosing styles, comparing color schemes, adjusting typography, or generating CSS snippets. Triggers on keywords like "Obsidian theme", "color scheme", "CSS snippet", "appearance".

alphaparkinc/openclaw-genpark-agent-monitor

OpenClaw GenPark Agent Monitor - Heartbeat telemetry liveness auditor, EWMA latency drift detector with CUSUM change-points, and Apdex performance index solver with zero dependencies.

mary13/pair-design-agent-skill

Use this skill for collaborative UX/UI design work — designing user flows, creating wireframes or prototypes, working through interaction design problems, or making structured design decisions where iteration and rationale matter. Triggers include: 'design a flow', 'create a wireframe', 'let's pair design', 'I need to design X', 'walk me through designing Y', requests for prototype screens, mentions of UX/UI methodology, interaction design, information architecture, or service design. The skill enforces a disciplined one-artifact-at-a-time methodology with clear human-AI roles (Synth/Gen) and

ColCh/paperless-ngx-skill

Use for Paperless-NGX API work: search, upload, download, metadata, tags, status, logs, bulk ops. Triggers: paperless.

fourierwang66666/product-requirements-review

Conducts structured product requirements review from idea to design doc. As PM asks clarifying questions; analyzes essence (problem, audience, real demand, business logic); researches competitors and data; as CTO assesses technical feasibility and Vibecode cost/time; then proposes creative, shortest-path solutions (smart, non-generic, with unique value or cold-start); makes go/no-go; if go, produces concept, name, architecture, user flows, system design (Vibecode-oriented), design references, and full design document. Principles: no process for its own sake, challenge ideas directly, common se

leonsong09/project-daily-summary

Use when the user wants a same-day Codex work summary grouped by project folder or repository, combining today's Codex sessions, extracted plans, completed items, commits, and uncommitted changes, or says 项目日报, 日报, 今日工作总结, 按项目总结今天, 总结今天所有 Codex 会话, 总结今天会话+提交+未提交改动.

Xabilimon1/reeljet

Use when the user wants to create a short promo or demo video (Reels/TikTok/Shorts/landing hero) for an app, web, or SaaS from their own screen recordings and screenshots. Orchestrates creative direction, Higgsfield-generated motion/b-roll, local music, and deterministic ffmpeg assembly into master 16:9 + 9:16. Trigger: /reeljet.

CyberZenithX/Rich-Elicitation-Skill

Use this skill whenever Claude is about to help with any task that has multiple reasonable approaches, unclear requirements, personal preferences, or ambiguous scope. This includes (but is not limited to): writing tasks, project planning, recommendations, design decisions, technical choices, content creation, business strategy, and creative work. Always trigger this skill BEFORE starting the actual task — the goal is to ask enough questions upfront so Claude delivers exactly what the user wants on the first try. Do NOT trigger for simple factual lookups, math, or tasks where intent is complete

tangyc828/RSA-Whiteboard-Animation

Generate RSA-style whiteboard animation storyboards with scene timing, image prompts, and narration scripts. Supports English and Chinese.

stephenlzc/sci-introduction

写"国内外研究现状"（文献综述 / Related Work）。当用户提到研究现状、文献综述、国内外研究对比、Literature Review、述评、研究背景、国内外研究现状时使用。即使用户没有明确说"写研究现状"，只要涉及对某一主题的国内外学术研究现状进行结构化梳理，就应该触发此技能。

leonsong09/session-wrap

Use when the user wants to wrap up the current coding session, summarize the current session before ending work, document learnings, decide what to commit, or says 总结会话, 会话总结, 收尾, 会话收尾, 结束会话, 总结本次会话.

fuzhengwei/xfg-skills-agnes

Agnes AI 图像与视频生成技能。当用户需要生成图片（文生图、图生图）或视频（文生视频、图生视频、多图视频、关键帧动画）时使用此技能。 触发关键词：生成图片、绘图、画图、AI画图、文生图、图生图、生成视频、做视频、AI视频、文生视频、图生视频、关键帧动画、Agnes、agnes-image、agnes-video。 安装后需配置 API Key 才能使用，首次使用时引导用户设置。

alphaparkinc/shopper-intelligence-skill

Integrate Similarweb Shopper Intelligence data and Amazon IQ capabilities into the GenPark ecosystem for advanced e-commerce insights, sales performance tracking, and competitor analysis.

oguzhantopgul/skill-security-reviewer

Security review and threat analysis for agent skills. Use when reviewing, auditing, or validating skills for security issues including prompt injection, code execution risks, data exfiltration, supply chain vulnerabilities, and policy violations. Triggers on requests to "review a skill", "audit skill security", "check skill for vulnerabilities", "validate skill safety", or any security assessment of SKILL.md files and their associated scripts/assets.

Mochaxgcc/solidworks-ai-bridge

Bridge a local AI coding agent to SolidWorks through the Windows COM Automation API for automated CAD modeling, parametric part and assembly creation, macro-like API calls, template discovery, dependency setup, controlled document cleanup, preview image export, and neutral CAD export for downstream CAE/CFD workflows such as Ansys Fluent, Ansys Mechanical, COMSOL Multiphysics, or other simulation tools. Use when the user asks to connect an agent with SolidWorks, drive an open SolidWorks session, avoid accumulating many Part/零件 windows, troubleshoot SldWorks.Application COM access, create SolidW

Zeeh-Lin/spinal-pro

End-to-end SpinalHDL skill for generating, reviewing, explaining, and validating RTL (Scala HDL). Covers DSL semantics (`:=`, `<>`, `Reg`, `Stream`, `Flow`, `Bundle`, `Vec`, `ClockDomain`, `StateMachine`, `Mem`, `BusSlaveFactory`), pipeline and plugin composition (`spinal.lib.misc.pipeline`, `spinal.lib.misc.plugin`), simulation with `SimConfig`/`doSim`, and architecture patterns drawn from official SpinalHDL docs and VexRiscv. Load for SpinalHDL DSL questions, module implementation, interface design, SoC integration, bug hunting, error-message decoding, and simulation or build validation.

griffinwooldridge/talking-head-editor

Edit raw talking-head footage into a finished video with Claude. Tight cuts that never clip a word, studio-clean voice, reframing and punch-ins, word-timed captions, and cinematic motion graphics written as code, all rendered frame-exact with ffmpeg and HyperFrames. Use when someone hands you a raw recording (camera file, optional separate mic) and asks to "edit this video", "cut my talking head", "add motion graphics", "clean up the audio" or "make this look edited".

Oreo992/thermo-nuclear-code-quality-review

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

wssfk12138/trace-to-practice

Periodically distill task histories into evidence-backed workflow improvements, reusable skills, scoped agent rules, persistent memory, and user habit suggestions while controlling review cost. Use for conversation retrospectives, recurring agent-error analysis, or 对话蒸馏/工作流复盘 across tasks. Do not use for a simple one-chat summary or ML model knowledge distillation.

Han-maker-wp/unipus-agent

操作网页版 U校园（Unipus / U校园AI版 uai.unipus.cn）的全能技能：登录课程、定位单元任务与作业、从内置答案知识库（21 系列/约200本教材）检索答案、AI 辅助作答（默认只填不提交，每次必须当场询问用户提交策略）、按配置时长挂机积累学习时长（默认10分钟/节，带心跳提示）、提交前多重答案核查。当用户提到 U校园、U校园AI版、unipus、Unipus、新编大学英语、新视野、新标准、大学英语作业、刷时长、做英语作业时一律使用本技能，即使用户没有明确说出"U校园"三个字。

LeonardHope/USPTO-ODP-Natural-Language-Search

Search all USPTO patent and trademark databases using plain English. This skill provides a unified interface to the USPTO Open Data Portal (ODP) APIs covering patent application search, file wrapper prosecution history, PTAB trials and appeals, office action rejections, patent assignments, petition decisions, trademark status (TSDR), and bulk data downloads. Use this skill whenever the user wants to search for patents, look up patent applications, check prosecution history, find PTAB proceedings or appeal decisions, trace patent ownership, analyze office action rejections, search by inventor o

bGiaHuy/vietnamese-docs-style

Soạn, biên tập văn bản tiếng Việt và tạo/chỉnh sửa DOCX văn phòng, học thuật, hành chính theo mẫu phù hợp. Dùng cả khi chỉ cần đoạn văn, đề mục hoặc danh sách đánh số trong chat. Chọn thể thức theo loại văn bản và nơi tiếp nhận; chỉ áp dụng Nghị định 30/2020/NĐ-CP trong phạm vi phù hợp.

mrKanoh/wcag-accessibility-audit-skill

WCAG 2.1/2.2 AA accessibility skill: audits, remediation, ARIA roles and patterns, keyboard navigation, focus management, screen reader behavior (NVDA, JAWS, VoiceOver, TalkBack), color contrast, accessible components (modals, menus, tabs, forms, tables, comboboxes), React, Vue, Angular, Svelte and Next.js, mobile a11y (React Native, SwiftUI, Compose), cognitive accessibility, legal compliance (ADA, EAA, Section 508, EN 301 549, VPAT/ACR) and CI testing (axe-core, pa11y, Playwright). Use when the user asks whether UI is accessible or passes WCAG, asks about ARIA, focus traps, live regions, ski

mars-tw/web-card-game-skill

維護「阿軒卡牌對戰」時使用。這是一款原生 HTML/CSS/JS 網頁 TCG，包含對戰、卡包、收藏、牌組工作台、每日任務、收藏里程碑與週任務。

lvpiggyqq/xcatcher-mcp-manifest

Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl, watch, compare, or summarize specified X/Twitter handles or profile URLs.

Ayubjon/yandex-games-skill

Build, integrate, audit, and prepare browser games for Yandex Games. Use for SDK startup, Game Ready, ads, localization, saves, purchases, leaderboards, moderation failures, and pre-submission checks with the bundled 93-check runtime checker.

SamedVossberg/3d-brain-animations

Render 3D still images and rotating turntable animations of brain regions from ANY BrainGlobe atlas (mouse, rat, human, zebrafish, etc.), with optional glow/bloom highlighting and a semi-transparent whole-brain shell for context. Use this WHENEVER the user wants to visualize, render, picture, or animate brain anatomy: any species, any region (hippocampus, CA1, dentate gyrus, cortex, thalamus, amygdala, ...), any color, a glowing/highlighted region, a rotating brain video, or a neuroanatomy figure for a paper/thesis/slide — even if they don't mention Blender or BrainGlobe. Handles requests like

skyil7/agent-onboarding

Initialize a repository by analyzing its structure and generating `AGENTS.md` and structured `docs/`, enabling AI coding agents (Claude Code, Codex, Cursor, etc.) to operate safely, deterministically, and with minimal human supervision.

tom-surge/ai-ad-editor

Turn a finished ad script into a finished short-form video ad (9:16, plus 4:5, 1:1 and 16:9 if wanted) from AI-generated clips, the user's own clip library (UGC), or both - voiceover, shot plan, library clip matching, characters, scene images, AI video clips, talking characters with lip-sync, edit, captions, music, hook variants, quality checks and export. Works with any generation tools - an MCP, built for Kie.ai (images, video and lip-sync) with ElevenLabs for the voiceover, or other APIs, or by hand with copy-paste prompts. Nothing paid runs without your yes. Use when the user says "edit th

Lum1104/ambitious-ai-startup-playbook

Teach, practice, apply, and reference an evidence-grounded founder operating system derived from Sam Altman's Startup School 2026 interview: use AI leverage to raise ambition, exploit fast technology shifts without abandoning business fundamentals, build evidence-updated conviction and compounding relationships, and evaluate safety, power, and human agency.

massipetro/app-ui-slopless

Visual design and UX for native app screens in SwiftUI (iOS and macOS), Jetpack Compose and Compose Multiplatform (KMP). Use whenever the user wants to design, build, restyle, redesign, theme or audit how an iOS, Android or Mac screen, window, flow, component or design system looks and feels — e.g. a screen that looks generic, boring, stock Material or "AI-made"; picking a type scale, colour palette or theme code; giving an app a style (warm premium, neo-brutalist, playful, editorial); or a UX critique of a mobile or Mac screen or screenshot (hierarchy, tap targets, thumb reach, sidebar and to