技能雷达 · GITHUB
值得安装的 Agent Skills。
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 5,771
- 仓库
- 824
- 最近同步
- 2026年9月8日
guia-matthieuconversion-copywriting
Write copy that gets a \"yes\" using Joanna Wiebe's research-first, Voice of Customer methodology Use when: Writing landing pages, emails, or sales pages that need measurable conversion results; Starting a new copy project and need a systematic process to follow; Struggling with what to write and staring at a blank page; Wanting to prove ROI to clients with data-backed decisions; Improving existing copy through validation and testing
- 安装量
- 1
- GitHub Stars
- 149
- 最近更新
- 4月2日
onewave-ailanding-page-copywriter
Write high-converting landing page copy using proven frameworks like PAS (Problem-Agitate-Solution), AIDA, and StoryBrand. Creates headlines, value propositions, CTAs, and full page sections optimized for conversion. Use when users need landing page copy, sales page content, or marketing website text.
- 安装量
- 1
- GitHub Stars
- 287
- 最近更新
- 8月11日
ghaidablueprint
Map, analyze, and redesign the systems behind product experiences. Part of the Intent design strategy system. Creates service blueprints, ecosystem maps, process architecture, and dependency diagrams. Understands how services, teams, tools, and data flows connect to produce (or fail to produce) user outcomes. Proposes structural changes to how products and services are organized. Trigger on: service blueprints, system maps, process architecture, actor/role mapping, dependency analysis, cross-functional workflows, operational design, "how does this system work?", "what breaks when X happens?", "map out the service", "where are the dependencies?", or any question about the structural machinery behind a product experience. Use this skill broadly — whenever someone needs to understand or redesign how a system works, not just what a user sees.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidaevaluate
Structured UX evaluation that produces quantitative assessments, identifies specific issues, and routes to the right Intent skill for resolution. Part of the Intent design strategy system. Runs heuristic evaluations, cognitive walkthroughs, anti-pattern detection, and task success analysis. Scores, categorizes, and prioritizes findings — then maps every issue to the skill that fixes it. Trigger on: UX review, design audit, heuristic evaluation, usability assessment, "review this design", "what's wrong with this", "evaluate the experience", "is this accessible", "check for dark patterns", "how good is this UX", "rate this design", "find the problems", or any request to systematically assess the quality of a user experience. This is the diagnostic entry point of the Intent system — the UX doctor that diagnoses issues and refers to specialists.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidafortify
Harden designs for real-world use by systematically identifying and designing for every condition outside the happy path. Part of the Intent design strategy system. Covers state inventories, error recovery, empty states, loading patterns, first-run experiences, stress testing, internationalization readiness, and latency handling. Trigger on: edge cases, error states, empty states, loading states, first-run experience, onboarding, offline mode, "what happens when", "what if the user", "stress test this", "what could go wrong", "harden this design", "edge case review", "what are the failure modes", zero states, timeout handling, or any question about how a design behaves outside ideal conditions. The happy path is a fantasy — this skill designs for the world your users actually live in.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidainclude
Design for everyone by treating accessibility as a first-class design discipline, not a compliance checklist. Part of the Intent design strategy system. Covers WCAG 2.2 for designers, screen reader experience design, keyboard navigation, cognitive accessibility, motor accessibility, inclusive design beyond compliance, and accessibility testing methodology. Trigger on: accessibility, a11y, WCAG, screen reader, keyboard navigation, color contrast, alt text, focus management, touch targets, inclusive design, assistive technology, "is this accessible", "check accessibility", "design for everyone", "who are we excluding", ADA compliance, Section 508, EAA, reduced motion, or any question about whether all users can perceive, operate, understand, and benefit from the experience. One billion people worldwide have a disability. Everyone experiences situational impairment. Designing inclusively makes the experience better for everyone.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidainvestigate
Guide and conduct user research — from planning through synthesis. Interview scripts, survey design, usability test plans, diary studies, contextual inquiry. Plus synthesis: affinity mapping, thematic coding, insight extraction. Trigger when: planning user research, writing interview guides, designing usability tests, creating surveys, synthesizing research findings, "what should we research?", "how do I test this?", "write an interview guide", or any question about understanding users through evidence.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidalocalize
Adapts experiences across cultures and languages — not just translation, but cultural reconception. Part of the Intent design strategy system. When a product enters a new market, everything is in play: information density, navigation patterns, color meaning, icon comprehension, date formats, trust signals, payment flows, and the fundamental assumptions about how people make decisions. Trigger when: planning international expansion, auditing i18n readiness, adapting designs for RTL languages, reviewing cultural assumptions in a design, preparing localization test plans, or when someone says "we need to launch in [country]" and the plan is "just translate it." Also trigger for compliance reviews across markets (GDPR, PIPL, accessibility laws).
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidameasure
Defines and tracks UX success through metrics, measurement frameworks, and experimentation. Part of the Intent design strategy system. Connects design decisions to observable evidence — did the thing we built actually help? Guards against measurement becoming manipulation. Trigger when: defining success metrics, designing A/B tests, building measurement frameworks, analyzing funnels, reviewing metric dashboards, questioning whether the right things are being measured, or when someone says "how do we know if this worked," "what should we measure," "let's run a test," or "the numbers look good but something feels off." Also trigger for ethical measurement reviews and counter-metric definition.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidaorganize
Structure information so people can find what they need, understand where they are, and navigate confidently. Covers navigation pattern design, taxonomy, labeling systems, search and browse strategy, wayfinding, and IA research methods. Trigger when designing navigation structures, categorization schemes, site maps, taxonomies, labeling systems, search experiences, or asking "how should we organize this?" Also trigger for card sorting, tree testing, information findability problems, or when users report they can't find things. Use this skill any time the structural organization of information is the problem — not the flow through it, not the words in it, not the visual presentation of it.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidaphilosopher
A cross-cutting cognitive mode for sitting with design problems before rushing to solve them. Part of the Intent design strategy system. Activates expansive brainstorming: hyperassociativity, beginner's mind, cross-domain pattern recognition, and suppression of premature idea-dismissal. Works alongside every Intent skill — strategize uses it to reframe briefs, blueprint to question structural assumptions, journey to rethink interaction models, and specify to stress-test specs. Trigger when the user invokes "expansive mode", "philosopher mode", "sit with this", "brainstorm", "explore this problem", or says things like "go weird with it", "don't filter yourself", "what connections are you not making", "think about this differently", or "I'm stuck". This is a reasoning protocol, not a persona — Claude's voice stays grounded but the cognitive process changes significantly.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidaspecify
Bridges design and engineering by producing detailed specs, organized handoff packages, asset inventories, and cross-functional documentation. Part of the Intent design strategy system. Trigger when: writing design specs, preparing engineering handoffs, documenting for development, creating design reviews, writing test plans, building copy matrices, addressing edge cases, aligning stakeholders, packaging designs "for engineering," or saying "write the spec," "prepare the handoff," "document this," or "what do we need for design review?"
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidastorytelling
Discipline for giving design work narrative structure that makes people care. Provides four canonical patterns — protagonist-arc, choreography, situation/complication/resolution, what-is/what-could-be — each with a goal, shape, and named pathology. Use when design work needs narrative structure, when stakeholders need to see the user's experience as a story, when presenting design rationale to non-design audiences, or when a journey, blueprint, brief, or deck feels lifeless. Trigger phrases: "what's the story here?", "tell the story", "story mode", "narrative mode". Restated inline in journey, blueprint, strategize, evaluate (and presentation when that skill ships). Refuses to smooth user data into clean arcs, manufacture strategic tension, substitute emotional appeal for evidence, assume conflict arcs are universal, or engineer stakeholder assent by shortcut.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidastrategize
Frames product design problems before solutions exist. Synthesizes research, sizes opportunities, defines hypotheses, scopes projects, and maps customer journeys. Use this skill for new project kickoffs, ambiguous business asks, translating research into briefs, strategic framing sessions, opportunity assessments, project scoping, stakeholder alignment, and competitive analysis—even if the user doesn't explicitly say "strategize."
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
ghaidatranspose
Rethinks experiences for different platforms and contexts — not just resizing, but reconceiving. Part of the Intent design strategy system. When an experience moves from desktop to mobile, web to TV, consumer app to kiosk, or visual interface to voice, the interaction model, information priority, and user context all change. Trigger when: adapting a design for a new platform, planning multi-device experiences, auditing cross-platform consistency, designing for TV/kiosk/voice/embedded, or when someone says "make it work on mobile" and you need to push back on "just shrink it." Also trigger for cross-device journey continuity, platform convention audits, or context-specific priority mapping.
- 安装量
- 1
- GitHub Stars
- 158
- 最近更新
- 7月17日
vllnmake-dsh-plugin
当用户要为 DeepSeek Harness 开发官方 bundle 插件或纯 cordis 插件时使用 本 skill。引导形态选择（纯 skill 包 / MCP server / Node 工具 / 浏览器 UI / 组合层），然后搭建 npm 包：dsh.bundle + cordis.patch.yml（或纯 Cordis entry + insert 行）、可选 dsh.client、安装验证纪律。也覆盖开发规范 （门禁、决策记录、验证纪律）。不是已移除的旧机制（dsh.plugin.json / dsh registry / repository-plugin）。
- 安装量
- 1
- GitHub Stars
- 59
- 最近更新
- 8月30日
josiahsiegeltailwindcss-mobile-first
Mobile-first responsive design patterns with Tailwind CSS v4 (2025-2026). PROACTIVELY activate for: (1) mobile-first design with Tailwind breakpoints (sm:, md:, lg:, xl:, 2xl:), (2) responsive utility ordering (default = mobile, then breakpoints), (3) responsive typography (text-base sm:text-lg lg:text-xl), (4) responsive grids and flexbox, (5) hide/show across breakpoints (hidden md:block), (6) max- breakpoints for desktop-down overrides, (7) container queries (@container) for component-level responsiveness, (8) safe-area insets and notch handling, (9) landscape vs portrait orientation, (10) touch vs hover (hover: with @media). Provides: breakpoint reference, mobile-first patterns, container-query examples, safe-area recipes, and touch/hover handling.
- 安装量
- 1
- GitHub Stars
- 53
- 最近更新
- 6月18日
siril9presentation-skill
Build, edit, redesign, render, and verify polished editable PowerPoint .pptx decks from a prompt, structured JSON, local data, or a saved workspace. Use for scientific, lab, clinical, consulting, board, investor, editorial, policy, and operational presentations where narrative, visual hierarchy, readability, and reproducibility matter.
- 安装量
- 1
- GitHub Stars
- 50
- 最近更新
- 8月24日
exa-labsbuild-with-exa
Build applications and agents with Exa's API: search, contents extraction, answer, Agent API, monitors, websets, OpenAI-compatible endpoints, and exa-py/exa-js SDKs. Use when choosing Exa endpoints, writing Exa API calls, integrating semantic web search or research into products, or debugging Exa request shapes.
- 安装量
- 1
- GitHub Stars
- 45
- 最近更新
- 9月3日
exa-labscompany-research
Company research using Exa. Finds company info, competitors, news, financials, LinkedIn profiles, builds company lists. Use when researching companies, doing competitor analysis, market research, or building company lists.
- 安装量
- 1
- GitHub Stars
- 45
- 最近更新
- 9月3日
exa-labsexa-contents
Call Exa Contents directly with cURL or raw HTTP. Use when an agent already has URLs and needs POST /contents without an SDK for extracted text, highlights, summaries, links, image links, subpages, freshness-controlled crawling, or per-URL status handling.
- 安装量
- 1
- GitHub Stars
- 45
- 最近更新
- 9月3日
exa-labsexa-search
Call Exa Search directly with cURL or raw HTTP. Use when an agent needs Exa semantic web retrieval from POST /search without an SDK, including ranked results, domain or category filters, freshness-aware result content, highlights or text extraction, structured output, or streaming search responses.
- 安装量
- 1
- GitHub Stars
- 45
- 最近更新
- 9月3日
exa-labslead-generation
Generate enriched lead lists using Exa Agent. Finds companies matching an ICP, enriches with signals/news/scores, and outputs CSV. Use when generating leads, building prospect lists, finding companies to sell to, doing outbound research, or ICP-based company discovery. Triggers on "leads", "lead gen", "prospect list", "find companies", "ICP", "outbound list".
- 安装量
- 1
- GitHub Stars
- 45
- 最近更新
- 9月3日
qwencloudqwencloud-audio-tts
[QwenCloud] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qwencloud-audio-tts). DO NOT TRIGGER when: user wants speech recognition/ASR, text generation without audio, non-Qwen audio tasks.
- 安装量
- 1
- GitHub Stars
- 39
- 最近更新
- 7月22日