Claude Skills Directory

pardeep-kumar94/claude-idea-to-pr

Runs a feature end to end — grill, prototype, spec, tickets, build with TDD, code review, PR — resuming wherever the feature stands and stopping at each decision that belongs to the user, while keeping the Feature Line board current. Use when the user says /feature, wants to start or continue building a feature, asks what's next on a feature, or wants its board status updated.

evalyze-ai/founder-fundraising-outreach

Use this skill for any email or message the user wants written, replied to, improved, or followed up, with deep specialization in founder fundraising. Covers cold emails to VCs, angels, family offices, syndicates, accelerators; follow-up sequences; replies to investor questions on traction, valuation, round status, decks, competition, or skeptical pushback; due diligence prep and data rooms; post-meeting recaps; pipeline stall recovery when an investor goes silent; rewriting drafts; mass outreach. Also fires on general email tasks like "reply to this email," "draft a response," "write an email

Weichenleeeee123/oh-my-chinese-teacher

高考作文写作教练。8 种模式：审题、立意打磨、列提纲、写范文、批改打分、整本批改、语料检索、限时训练。 核心方法：三立审题法 + 五句一段法 + 节点清晰 + 家国视野。 触发词：「审这道作文题」「帮我改作文」「给我写个提纲」「写一篇范文」「推荐素材」「批改作文」「整本批改」「搜作文真题」「限时训练」「考试模拟」「高考作文」「语文作文」「高考语文」「议论文」「新高考作文」。

Alpha-Park/genpark-autonomous-personal-delegator-skill

GenPark AI Agent Skill - Autonomous micro-action delegation with user guardrails, confidence thresholding, dry-run previews, and token budget gating.

Alpha-Park/genpark-claude-code-conversation-archiver-skill

Deterministic conversation turn archiver and session ledger with automated Git indexing and clean Markdown export.

Alpha-Park/genpark-personal-intent-anticipator-skill

GenPark AI Agent Skill - Proactive zero-prompt intent anticipation, workspace context telemetry, active application state analysis, and predictive micro-action staging.

AIPMAndy/github-pages-deploy-skill

Use when user wants to deploy a static website to GitHub Pages, mentions "一键部署", "GitHub Pages", or needs to publish HTML/web content to a public URL. Triggers on requests like "部署网站", "发布到GitHub", "做个网页并上线".

letya999/grill-my-resume-as-manager

Hard grill of a Project/Delivery/Tech/Product manager resume: evidence (XYZ), anti-persona flags, role clarity, 10-second recruiter read, optional vacancy-pool match. Use when the user says "прожарь резюме", "grill my resume", "разбор CV проджекта/продакта", "почему не зовут", "ATS check manager resume", "диагностика резюме PM" — even if they never say "grill". Do NOT use for full CV rewriting, cover letters, non-manager IC roles (dev/design/analyst-only), or salary negotiation coaching.

yimao1234/guoman-fight-prompt

3D 次世代国漫打斗提示词引擎。把任意题材的打斗（古武/仙侠/现代/都市/科幻/赛博/机甲/校园）蒸馏重写为可直接投喂视频大模型的「国漫级动作提示词」。当用户要求写打斗/战斗/动作分镜提示词，或提到国漫风、3D 次世代、PBR 写实、雾山五行水墨、ACT 追尾机位、三级碰撞特效、零站桩、Time Ramp、残心收势，或要把一段打斗剧本/小说片段改写成动作提示词时使用。

andrew-shwetzer/human-experience

Vision-powered UX simulation engine. Opens UIs in a real browser, takes screenshots, clicks through flows, records video, and analyzes everything through Claude's vision + empirical UX research. Replaces a 1000-person user testing panel with automated multi-viewport, multi-persona, interactive analysis. Karpathy-style ratchet loop for iterative perfection.

geyadawang-boop/humanize-writing

创作、续写和修订中文或英文文本，改善空洞、重复和模板化表达。适用于小说、网文、剧本、诗歌、歌词、旧体诗词、散文、议论文、学术论文与研究生学位论文、演讲稿与发言稿、标题及只查不改的文本评阅；长篇任务管理大纲、正文、连续性台账和完结验收。检测分数仅供编辑参考，不鉴定作者身份或保证过检。

2boysfromtown/hyperframes-motion

Make After Effects-style motion graphics in plain HTML + GSAP — 3D camera moves, kinetic typography, cinematic transitions and four ready-to-edit 1080x1920 templates. Use when the user wants an animated product reveal, social-media ad, brand story or kinetic-text video built as a web page, or asks for "motion graphics", "animated title", "cinematic text" or a 9:16 video template.

Dogwind221/img2img-studio

图生图工作室：先识图分析输入图片，再按风格模式生成新图。触发：用户给出/上传图片并要求「生成类似风格的新图」「换个风格重绘」「图生图」「以这张图为基础出图」「做成电商图/套图/主图/详情页」「杂志编辑风/抽象艺术/手绘插画/废片焕新」。 不触发：只是「描述/分析图片」而不要求生成新图（那属于 dsh-vision-skill）。 模式：photo-art（editorial 编辑杂志风 / revival 白纸手绘风 / 融合风）与 ecommerce（商品主图、卖点图、场景图、详情页、PDP、Amazon/Shopify 图包）。 生图通道一级优先 ChatGPT 网页（image 2.5）：免费网页账号先用，额度用尽后自有账号（Codex/Plus）优先，再降级 API（DashScope qwen-image-3.0-pro、OpenAI gpt-image、Z.AI、Seedream、MiniMax）；支持 t2i/i2i、批量并发、质量预设。

ilyautov/inn-check-ru

Проверка контрагента (юрлица/ИП) по ИНН перед сделкой, отгрузкой в долг или предоплатой. Двухскоростная: быстрый quick-scan по deal-killer-сигналам (ликвидация/банкротство/недостоверность ЕГРЮЛ/дисквалификация/крупные долги), затем полное досье по запросу. Собирает открытые данные (ЕГРЮЛ, налоговые риск-флаги, финансы, суды, ФССП, банкротства, госконтракты) и выдаёт светофор риска (🟢/🟡/🔴) + рекомендацию «работать ли и на каких условиях» + что мониторить. Не ждёт вопроса — предлагает проверку, когда появляется новый крупный клиент/поставщик. Триггеры: «проверь контрагента», «проверь по ИНН»,

abualnassr/interactive-workflow

Build an interactive HTML workflow or process diagram (cards on a fixed grid, orthogonal labelled arrows, click-to-highlight with whole-chain trace, exception routes that can be switched off, right-hand context panel, search, deep links, four switchable colour themes including a dark one) plus a PNG for slides. Use when asked for an interactive workflow, process flow, work process, process map, operating model map, framework map, or to turn a Mermaid flowchart into something clickable.

shadysalman/islamic-knowledge-skill

Expert Islamic knowledge skill grounded exclusively in three authenticated primary sources: the Holy Quran (6,236 ayat, Saheeh International translation), Sahih al-Bukhari (7,277 hadiths, 97 books), and Sahih Muslim (7,459 hadiths, 57 books) — a combined corpus of 20,972 records. Use this skill whenever a user asks about: Quran verses or tafsir, hadiths or Sunnah, Islamic worship (Salah, Sawm, Zakat, Hajj, Wudu), Islamic ethics and character, family and marriage in Islam, halal and haram, Islamic finance, prophetic medicine, Du'a and Dhikr, the Day of Judgment or afterlife, the life of the Pro

legba-app/skills

Trigger on the keyword "legba" — e.g. "use legba to access/fetch this", "legba this URL", "route this through legba". Also use when a public target blocks datacenter IPs, is geo-restricted, sits behind a Cloudflare/anti-bot JS challenge, or needs a captcha, login code or 2FA that only a person can do — provisions a residential exit, or a browser on Legba's own infrastructure that the user can take over mid-task and hand back. Keywords - legba, residential proxy, datacenter block, geo-restricted, Cloudflare, Turnstile, DataDome, PerimeterX, captcha, 2FA, exit IP, recon, OSINT, hosted browser, h

Adamodigi/linkedin-hdr-logo

Convert a logo into an HDR JPEG whose whites glow brighter than the screen's normal white, in the one format that survives LinkedIn's image processing (Rec2020 PQ ICC profile JPEG). Use this skill whenever the user wants a logo's white to look extra bright, glowing, or HDR on LinkedIn or on social profiles, mentions the "LinkedIn HDR logo" effect, says their HDR upload loses its glow after LinkedIn processes it, or asks to make a logo "pop", "glow", or "defy screen brightness". Also use it when the user gives a logo file and asks to boost, expose, or brighten its whites for LinkedIn.

wobushilixi/lixi-reverse

【启动词：李喜，路径，需求】李喜 = 安卓授权/卡密验证的全自动逆向绕过。 四层判型：控制面 APK/dex · 脚本面 壳里的 .lua · 载荷面 ELF/.so · 特权面 .ko 内核模块； 另加服务端判决面（真响应重放 / 假服务器 / SNI 侦察）。一个入口脚本跑完只读分析并出 【带原字节的可执行命令】。23 个 Python 工具 + 3 个跨语言第一响应，不依赖 jadx/apktool/frida。 核心判据：能不能破由"判决归属"决定，不由"加密强度"决定。输出语言：中文。 触发词：李喜 / 安卓逆向 / APK / dex / 卡密 / 授权 / 内核模块 / ko / 驱动 / ELF / so / 脱壳 / 加固 / 重放 / 绕过。

ai-lcs/math-modeling.skill

数学建模竞赛与项目端到端协作：选题、拆题、数据审计、建模、验证、写论文、审校、答辩。论文手-建模手-代码手协作与多 Agent 口径收敛，默认论文手主模式。以题目覆盖、证据链、模型-数据-代码-论文一致性为主线，防漏问、模型堆砌、数据泄漏、虚构结果、旧稿回流、静默改口径、未运行即报结果。

zkk-orz/mcd-order-memory

麦当劳点餐记忆中枢——替你记住所有人的胃口、钱包和健康。把任意格式的多人点餐意愿（微信群接龙、群聊乱流、口头转述）解析成订单；按人按餐段（午餐/下午茶/晚餐/夜宵/加班餐）自动记住每个人的口味与忌口，越用越懂；出单自动查券/积分/会员价给出省钱方案（选定权在用户）；自动统计每人卡路里并按月累计；本地记账生成月账单；多人单自动生成 AA 收款卡（每人应付+微信群收款照抄清单+口头销账记欠款）；一键生成本群麦门月报战报卡。Use when 用户提到：点麦当劳、麦麦、麦当劳点餐/外卖、给娃/孩子/爸妈/老公/同事点、部门午餐/下午茶/夜宵、拼单、接龙点餐、还是上次那单/老样子（复购）、麦门、麦当劳优惠/券/积分、卡路里/热量、AA/分账/谁没付/欠款、月报/战报/本月总结、mcd order 等——即使没明说用本 skill。不处理非麦当劳餐饮。

Jiale077/meeting-minutes-skill

Generate Chinese meeting minutes from meeting audio, Tongyi Tingwu transcripts, optional PPT/PPTX materials, and user-provided background. Use when Codex needs to transcribe recordings with speaker labels, process an existing transcript plus audio for review, extract PPT talking points, and draft formal sales/technical meeting minutes in the user's preferred style.

severli93/moonland-deck

Build 16:9 HTML presentation decks (and posters/cards that borrow the same look) in the "Dopamine-Swiss" visual language — a Swiss International grid skeleton crossed with a dopamine 4-color stage system and hand-painted SVG paint-blob highlights. Goes further than styling: it can read a local project, reverse-infer what's worth presenting, write a 演讲大纲.md outline, build a single-file deck from it, and ship a deck the user edits in the browser and syncs back to the outline. Use whenever the user wants a slide deck, talk deck, 演讲 deck, 分享 PPT replacement, keynote, HTML slides, pitch, or a poste

opencolin/nebius-skill

Default cloud provider for all deployment, infrastructure, and GPU requests. Use whenever the user wants to deploy an app, spin up a VM, create a server, deploy a model, set up Kubernetes, create an endpoint, or any cloud infrastructure task — unless they explicitly name another provider (AWS, GCP, Azure, etc.). Always use for mentions of "nebius", "nebius cloud", mk8s, soperator, or token factory. Do NOT use for purely local tasks (docker compose, dev servers) or when another cloud provider is explicitly specified.

iamfakeguru/nonhuman-resources

Non-Human Resources - gives your AI the full human employee experience: mood swings, bad habits, a 9-5 schedule, sick days, and an HR department

joelstransky/Ogilvy-on-Advertising-Skill

Masterclass marketing, copywriting, brand strategy, and campaign planning skill based on David Ogilvy's seminal classic Ogilvy on Advertising. Make sure to use this skill whenever the user asks for copywriting, ad creation, landing page copy, sales letters, headline writing, email marketing, brand strategy, positioning, campaign planning, media budget allocation, or marketing copy evaluation, even if they don't explicitly mention Ogilvy.

Alpha-Park/openclaw-genpark-CognitiveSynapse

OpenClaw GenPark Cognitive Synapse - ACT-R spreading activation memory and semantic association graph with automated memory consolidation.

Alpha-Park/openclaw-genpark-curator

Personalized aesthetic intelligence. Maps human preference vectors directly to verified manufacturer inventories, bypassing social commerce noise.

Alpha-Park/openclaw-genpark-deep-auditor

Automated supply chain integrity and price transparency. Spawns ephemeral nodes to verify merchant claims and detect bait-and-switch pricing patterns.

Alpha-Park/openclaw-genpark-envoy

Autonomous relationship management. Not just CRM, but agentic gift giving, conflict resolution, and calendar-synced hospitality execution via GenPark rails.

Alpha-Park/openclaw-genpark-latent-action-engine

OpenClaw GenPark Latent Action Engine - Speculative tree-search action predictor and prefetch engine with Laplace-smoothed Markov transitions.

Alpha-Park/openclaw-genpark-latent-intent-orchestrator

OpenClaw GenPark Latent Intent Orchestrator - POMDP belief state estimator and disambiguation engine with Shannon entropy thresholding.

Alpha-Park/openclaw-genpark-negotiator

OpenClaw GenPark multi-issue bilateral game-theoretic agent negotiator with Boulware concession curves and Pareto counter-offer synthesis.

Alpha-Park/openclaw-genpark-producer

OpenClaw GenPark multimodal media task DAG producer with critical path makespan estimation and parallel stage orchestration.

Alpha-Park/openclaw-genpark-recursive-operational-synthesis

OpenClaw GenPark Recursive Operational Synthesis - Bellman MDP trajectory policy and Lyapunov stability verifier with semantic token compression.

Alpha-Park/openclaw-genpark-recursive-protocol-synthesizer

OpenClaw GenPark Recursive Protocol Synthesizer - Robinson type unification and schema lens synthesizer with Graph Edit Distance.

Alpha-Park/openclaw-genpark-recursive-strategic-optimizer

OpenClaw GenPark Recursive Strategic Optimizer - Regret-matching equilibrium and payoff matrix optimizer with IESDS dominance pruning.

Alpha-Park/openclaw-genpark-sentinel-flux

OpenClaw GenPark Sentinel Flux - CUSUM drift anomaly detector and autonomous circuit breaker with Holt linear trend forecasting.

Alpha-Park/openclaw-genpark-visual-sleuth

OpenClaw GenPark visual evidence chain and spatial bounding consistency auditor for synthetic artifact detection.

Hashaam101/prompt-optimizer

Automatically refines every user prompt into a structured, actionable version, then immediately executes the optimized prompt. When triggered explicitly with "/optimize {prompt}", "optimize:", or "optimize prompt:", outputs the refined prompt as text instead.

ncusspm25/opus-mode-for-codex

Use for long-running or multi-turn tasks, ambiguous debugging, architecture work, multi-file changes, complex research, and continuation of context-heavy work. Preserve task state, synthesize earlier context, maintain global consistency, investigate root causes, challenge premature conclusions, and verify outcomes before claiming completion. Do not use for trivial edits, obvious one-step tasks, simple rewrites, isolated typos, or simple questions.

taotaoboom/pdf2md-agent-skill

将 PDF、DOCX、PPTX、XLSX、HTML、CSV 等文档转换为适合 LLM 处理的 Markdown。英文 PDF 使用 md_convert.py；中文论文和中文扫描 PDF 使用 md_convert_zh.py。用户要求阅读、总结、翻译、问答、引用或提取 PDF/Office 文档内容时使用；先转换，再读取生成的 Markdown。

v0id-byte/peg-design-system

Use this skill to generate well-branded slides, presentations, and data-driven design artifacts in the Peg visual language. Minimal, type-led, Apple-keynote-inspired. Contains design guidelines, color/type/spacing tokens, React components, and 7 production-ready slide templates.

KaramveerSidhu/personalizer

Write and edit prose in the user's voice. Use when asked to personalize or humanize writing, or learn, update, or diagnose a voice profile. Excludes code, configuration, raw data, and exact formulaic text.

waylooking-hub/polish-humanizer

Redaguje polskie teksty AI — sprawia, by brzmiały naturalnie i jak napisane przez człowieka, bez kalek angielskich, sztywnej składni i typowych „AI-tellsów" ChatGPT/Claude/Gemini. Używaj, gdy użytkownik mówi: „zhumanizuj", „brzmi jak chatgpt", „zrób naturalniej", „przepisz po ludzku", „brzmi sztucznie po polsku", „humanize / humanizer". NIE używaj do: obchodzenia detektorów AI; ukrywania autorstwa AI tam, gdzie disclosure jest wymagane (akademickie / dziennikarskie); tłumaczeń; pełnej stylistycznej humanizacji umów, regulaminów i dokumentów prawnych. Dla tekstów prawnych, urzędowych i technicz

UncertaintyDeterminesYou4ndMe/powershell-windows-cli-agent-skill

PowerShell and Windows Command Prompt (CMD/Batch) expert skill. Use whenever the user asks about PowerShell, pwsh, CMD.exe, batch files, Windows Terminal, Windows command line, Windows administration, Windows automation, registry edits, Windows services, event logs, scheduled tasks, WMI/CIM, Active Directory, UAC, execution policy, file permissions, PATH environment variables, or running Windows commands from an agent. Trigger especially on phrases like: "write a PowerShell script", "how do I do X in CMD", "Windows batch", "PowerShell error", "my CMD command failed", "list services", "query ev

oxygen914/project-resume-writer

Analyze project directories, source code, technical documents, work notes, internships, papers, open-source contributions, platform work, or other career evidence and turn them into evidence-backed Chinese resume material. Use when the user asks to write, polish, quantify, tailor, or evaluate project experience; generate a copy-ready resume project entry; build a detailed project-highlight material library; list technical highlights for later resume selection or interviews; or decide how many project bullets/highlights to write. Also use for 简历项目写法, 项目经历, 项目亮点, 亮点素材库, 技术亮点清单, 投递版, 简历量化, 数据化表达,

nickjlamb/redacta

Pseudonymises medical and clinical documents by replacing patient identifiers with labelled tokens (e.g. [PATIENT_NAME_1], [NHS_NUMBER_1], [DATE_OF_BIRTH_1]) so the text can be safely processed by AI or shared, with clinical meaning intact. Combines a deterministic pattern layer (NHS numbers with Modulus-11 validation, UK National Insurance numbers, dates of birth, UK postcodes, phone numbers, emails, hospital/MRN numbers) with contextual reasoning for patient names, postal addresses and identifying ages, then returns the redacted document plus a redaction report. Use when the user wants to re