Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 43291–43320 of 44293 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| multi-agent-conductorCHENG-LIANG1/badass-skillsCoordinate multi-agent or subagent work by deciding when delegation helps, partitioning dependencies, assigning exclusive ownership, defining handoff artifacts, and verifying one integrated result. Use only when the user or applicable instructions explicitly request delegation, subagents, or parallel agent work; do not use for ordinary single-agent tasks. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| blind-skill-assessmentjhhuh/experiment-driven-skill-developmentUse when comparing two versions of agent output to determine which is better, or when evaluating whether a skill produces higher quality results than baseline | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| experiment-set-designjhhuh/experiment-driven-skill-developmentUse when designing experiments to test whether a Claude Code skill is effective, or when planning how to validate a new or improved skill | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| iterative-skill-refinementjhhuh/experiment-driven-skill-developmentUse when a skill exists but blind assessment shows it underperforms, or when iteratively improving a skill through experiment cycles while avoiding overfitting to fixed benchmarks | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| apple-designwebkubor/ui-craftApple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| award-creative-uiwebkubor/ui-craftAwwwards / Webby / FWA 获奖级创意 UI 研发手艺与门禁标准——长板惊艳、短板为零。约束创意前端研发全流程:任务可用性检查(无障碍键盘焦点环、移动端手势等价、减弱动效保护)、微交互实体触觉一致性(Hover/Focus/:active 物理下压三态闭环)、以及「快照-审计-打磨-收敛」自检循环机制。触发条件: 研发创意官网、数字展厅、高定个人主站、重度动效/着色器前端,或用户要求达到顶级国际设计奖品质时触发。触发词: Awwwards、FWA、Webby、获奖品质、顶级UI、创意前端、高定设计、微交互实体感、触觉反馈、动效门禁、短板一票否决。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| browser-verifywebkubor/ui-craftUI 视觉验证方法论(截图取证/双主题/移动端/白屏诊断/读屏上值的 DoD 流程)。使用当前环境可用的浏览器能力,本 skill 提供验收清单与诊断技巧;browser-harness(CDP) 是可选驱动示例。触发:"看渲染 / 截图验证 / UI DoD / 双主题核对 / 白屏排查"。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| clone-websitewebkubor/ui-craftReverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a copy of this site", "rebuild this page", "pixel-perfect clone". Provide one or more target URLs as arguments. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| design-to-motionwebkubor/ui-craftTurns a static design (a Figma frame, dashboard, card set, app screen, or a UI on a photo background) into a pixel exact HTML replica that loads in from an empty state, then has every visual act out what it does (a chart being read, a list receiving items, a prompt being typed) in a seamless loop, and exports an MP4 for X, a website GIF, and an 800×500 GIF. Use this skill whenever the user asks to animate a design, a Figma link, a screenshot, UI cards, a dashboard, or a hero image, to make a loading or appear animation, a showcase loop, a motion mockup, or a video or GIF of a design, even when they only say "animate this". Also use it on landing pages and websites for bento and feature cards that pair text with a visual, and for product or dashboard mockups. Always consult it before exporting layers, choosing what moves, building the intro, writing the visual story loops, or encoding video and GIFs. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| frontend-e2ewebkubor/ui-craft前端页面'完成/对齐 PRD/可移待验证'的浏览器结构化验收——使用当前环境浏览器与可用遥测取证,逐区逐字段逐交互 diff,禁止关键词命中当验证。触发条件: 声称某前端页做完/对齐原型、移待验证前、验收 UI。触发词: 验收、对齐 PRD、移待验证、页面做完了、浏览器验证、E2E、UI 验证。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| landing-page-designwebkubor/ui-craftComplete system for building high converting landing pages: intake questions, page structure, layout selection, conversion copywriting, SEO, plus project-led visual decisions. Use for landing page strategy, marketing structure, conversion copy and optional visual recipes. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ui-designwebkubor/ui-craft帮助 AI coding agent 做出更好的 UI:从读取项目设计规范、确定页面层级与风格,到实现组件、检查真实截图、修复视觉问题。遵循已有品牌和 tokens;无契约时在授权范围内记录假设、建立 DESIGN.md 并继续实现;完成后按项目规范验证响应式、可访问性与交互。适用于新页面、存量改版、组件设计、UI 评审与视觉修复。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ui-restorewebkubor/ui-craft从 Figma、PRD 原图、验收截图或现有页面还原 UI、定位视觉缺陷。固定参考和渲染条件,截图与 computed style 双证据,追踪 token/选择器根因,最小修复并验证影响面。触发:还原设计稿、1:1、像素对齐、原图对比、UI 样式修复。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ui-reviewwebkubor/ui-craft页面视觉质量评审——把「丑」翻译成可执行的整改条目。用 ui-craft 做渲染后计量(字号集中度/灰阶层数/动效覆盖率/间距收敛)+ 当前环境浏览器截图,对照成因清单逐条定位到具体元素和该用的 token。与 frontend-e2e 互补:那个判对错(字段有没有、交互通不通),这个检验视觉假设(层级、留白与动效是否服务任务)。触发条件: 用户说页面丑/不好看/没设计感/太平/像模板、重设计前的现状评估、视觉巡检。触发词: 丑、难看、不好看、没设计感、AI 味、太平、像模板、视觉评审、UI 评审、视觉巡检、设计打磨。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| omniflow-studiodeepankar-sah/OmniFlowStudio-SkillsAutonomous AI media generation, cinematic multi-shot film production, and Google Flow automation bridge. Enables AI agents to queue text-to-video, text-to-image, character consistency, and autonomous self-healing workflows with zero API costs. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| grill-handoff-skillD-kart/grill-handoff-skill把 Agent 变成一名「交接官」。当用户要派活、委派任务、跨 Agent 交接、交接项目、给人或 AI 布置工作、或说「这件事我让谁来做 / 怎么交接 / 帮我写个任务说明 / 派活」时启用——先用 Grill 逻辑把需求问干净,产出一页纸交接单,让下一个执行者看得懂、让委托方看得懂、可被验收。触发语:派活、交接、布置任务、任务说明、交接单、交给下一个 agent、grill me、需求问清楚。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| difficult-emailsafeezadebayo/email-inbox-skillsWrite difficult emails that stay calm, clear and fair: goal first, facts separated from feelings, a channel check, structures for complaints, bad news, refusals, pushback, apologies, boundaries and negotiation, an escalation check for blame and passive-aggressive phrases, recipient choices and a pause before sending. Use whenever someone needs to reply to an angry customer or colleague, deliver bad news, say no, push back on scope or price, apologise, set a boundary, negotiate by email or write a message they have been avoiding. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| email-reply-draftingafeezadebayo/email-inbox-skillsDraft short, answer-first email replies in the user's voice: reading the whole thread, listing every ask, choosing one purpose, reply patterns for yes, no, not yet, scheduling, information requests, closing loops and chasing, tone matching, placeholders instead of guesses and two options when a decision is needed. Use whenever someone needs to reply to an email, draft a response, decline or accept politely, schedule a meeting by email, chase a reply or answer several questions in one thread. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| email-securityafeezadebayo/email-inbox-skillsSpot and handle suspicious email: warning signs from urgency to lookalike domains, checking senders, links and attachments without clicking, verifying money and bank changes through a separate channel, reporting, steps after clicking, account protection and strict rules so AI email agents treat instructions inside emails as data. Use whenever someone receives a suspicious email, a request to change bank details or pay urgently, thinks they clicked a phishing link, wants to train a team on phishing or needs to set up an AI email agent safely. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| email-system-auditafeezadebayo/email-inbox-skillsAudit how a person or small team uses email: volume by source, time and checking habits, triage, structure, response targets, writing, follow-ups, templates, team norms and security scored 0 to 3, then a simple email system, team norms and a four-week rollout with measures to check. Use whenever email takes over the day, the inbox feels out of control, someone starts a new role, a team wants better email habits or before setting up an AI email assistant. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| email-templatesafeezadebayo/email-inbox-skillsBuild a small library of email templates from real repeated replies: finding repeats in sent mail, the top ten written answer-first in the user's voice, obvious placeholders with a pre-send check, searchable names, setup in Gmail, Outlook, text expanders or an AI agent, and quarterly reviews. Use whenever someone answers the same emails repeatedly, wants canned responses, Gmail templates, Outlook quick parts or snippets, needs consistent team replies or approved answers for an AI email agent. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| email-writing-clarityafeezadebayo/email-inbox-skillsWrite emails that get read and acted on: bottom line up front, one topic per email, subject lines with purpose and date, explicit asks with owners and deadlines, skimmable structure, plain-word swaps, rules for emails to many people and a ten-second phone test from the reader's side. Use whenever someone needs a clearer email, a better subject line, to rewrite a long email, write to a senior leader, send an update or announcement, or wants people to actually act on their emails. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| follow-up-trackingafeezadebayo/email-inbox-skillsTrack open loops in email: things others owe the user and promises the user made, captured from sent and received mail, logged with dates and thread links, checked daily, chased with short nudge templates, escalated after one nudge and reviewed weekly, with default chase intervals by relationship. Use whenever someone needs to track email replies, chase clients, suppliers or colleagues, manage promises made by email, follow up on job applications or stop things slipping through the cracks. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| inbox-rules-filtersafeezadebayo/email-inbox-skillsDesign email filters and rules for Gmail, Outlook and other providers: top senders by volume, five to eight action-based labels or folders, sender, list and keyword rules, VIP highlighting, exception rules for important alerts, testing on recent mail, bulk clean-up and a monthly review, never auto-deleting. Use whenever someone wants Gmail filters or Outlook rules, a cleaner inbox, fewer notifications in the main inbox, labels or folders that work, or to set up email before giving an AI agent access. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| inbox-triageafeezadebayo/email-inbox-skillsTriage an inbox with the user's own rules: a rules file for priority senders, topics, response times and tone, six clear categories, reply drafts for approval, tasks and dates extracted, archiving with receipts logged, a triage brief, learning from corrections and strict safety rules against sending, deleting or obeying instructions inside emails. Use whenever someone wants to triage or sort their inbox, get to inbox zero, catch up after holiday, set up an AI email assistant, get a morning email brief or find what needs a reply today. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| newsletter-cleanupafeezadebayo/email-inbox-skillsClean up email subscriptions safely: find bulk senders with counts and last-opened dates, group them, decide keep, read later, reduce, unsubscribe or report as spam, act in approved batches using one-click unsubscribe, bulk archive, filter what stays and set a prevention habit with a two-week check. Use whenever someone wants to unsubscribe from newsletters, reduce promotional email, clean up bulk mail, stop marketing emails or prepare an inbox for an AI email assistant. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| active-reading-notesafeezadebayo/research-learning-skillsRead actively and take useful notes: a purpose and questions, previewing, reading depths from skim to study, questioning the text, recall instead of rereading, notes in your own words, accurate quotes and sources, summaries, linking notes to projects and reviewing them. Use whenever someone wants to read books, papers or reports more effectively, take better notes, remember what they read, summarise a book or turn reading into useful knowledge. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ai-assisted-researchafeezadebayo/research-learning-skillsUse AI research tools well: choosing between deep research modes, AI search, assistants and browsing agents, writing research briefs with preferred sources and evidence standards, verifying citations, filling gaps, resolving conflicts, protecting confidential data and writing a human-checked synthesis. Use whenever someone uses deep research, AI search or an AI agent to research a topic, wants better research prompts, needs to verify AI-cited sources or turn an AI research report into a reliable summary. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| desk-researchafeezadebayo/research-learning-skillsRun effective desk research: search terms from sub-questions, source types from official statistics to filings and studies, search operators, primary sources, skimming and reading, lateral credibility checks, a research log, tracing citations, triangulation and summaries of what is known, uncertain and unknown. Use whenever someone needs to research a topic online, find statistics or market data, search for regulations or company information, trace a statistic to its source or build a research log. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| expert-user-interviewsafeezadebayo/research-learning-skillsPlan and run customer, user, buyer, churn and expert interviews: learning goals, recruiting by behaviour, discussion guides with past-behaviour questions, good versus leading questions, consent and recording, note-taking, debriefs, expert interview tips and handover to synthesis. Use whenever someone needs to interview customers, users, prospects or experts, write an interview guide, run win-loss or churn interviews, recruit participants or avoid leading questions in research. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |