Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
49.456 de skill-uri din 2.407 depozite · actualizat acum 24 de minute
18.061 de skill-uri
- prd-generatorrshankras/claude-code-apple-skillsGenerates comprehensive Product Requirements Document from product plan. Creates PRD.md with features, user stories, acceptance criteria, and success metrics. Use when creating product requirements.PlanificareFără avertismente★ 863↓ —
- 46-brand-guideline-globalminhnv0807/ai-business-skillsUse when brand VISUAL rules have to be created or updated — brand personality, color system, typography, logo usage, imagery and visual tone, component rules, accessibility contrast, standard asset sizes, and file naming. It is the source document every design skill and the Brand Hub reads. Trigger on 'brand guideline', 'brand book', 'style guide', 'brand standards', 'our designs all look different', 'update the brand palette'. Also use when the user has a logo and nothing written down. Not for — how the brand SOUNDS in writing, see `35-brand-voice-global`; positioning and the message, see `58-positioning-global`; briefing one asset, see `42-image-brief-global`; scoring a design, see `47-design-review-global`.DesignFără avertismente★ 641↓ —
- research-deepWeizhena/Deep-Research-skillsRead research outline, launch independent agent for each item for deep research. Disable task output.ȘtiințăFără avertismente★ 2,5 K↓ —Apare și în 1 alt depozit
- debug-menurshankras/claude-code-apple-skillsGenerates a developer debug menu with feature flag toggles, environment switching, network log viewer, cache clearing, crash trigger, and diagnostic info export. Only included in DEBUG builds. Use when user wants a debug panel, dev tools menu, or shake-to-debug functionality.InginerieFără avertismente★ 863↓ —
- 75-hop-tac-koc-affiliateminhnv0807/ai-business-skillsDung khi thiet ke CHUONG TRINH hop tac voi KOC / creator o cap chuong trinh — chon muc tieu va co cau KOC theo vai tro phieu, tim va tham dinh KOC, neo gia theo chi phi tren moi ket qua dat chuan, chon mo hinh tra phi (phi co dinh, phi + hoa hong, affiliate thuan, tang san pham), co che affiliate, dieu khoan hop dong gom quyen su dung va whitelisting, bang cham diem tung creator va quy tac re-book. Kich hoat khi user nhac 'hop tac KOC', 'tim KOC o dau', 'tham dinh KOC', 'bao gia KOC', 'chuong trinh affiliate TikTok Shop', 'KOC co dang tin khong', 'creator bao so GMV khung'. Khong dung cho — viet brief quay video cho mot creator da chot thi dung skill 06-brief-ugc-egc; khach cu hoac CTV gioi thieu thi dung skill 18-referral-program; rai binh luan cong dong thi dung skill 38-seeding-plan; van hanh gian hang hoac livestream ban hang tren san thi dung skill 76-van-hanh-san-tmdt.MediaFără avertismente★ 641↓ —
- CTF•挑战调度器asdfgh1445/ctf-super-hub用于在 CTF 挑战开始时做首轮分类、轻量 triage 与 skill 路由，识别主导类别后转到对应 ctf-* skill，类别已明确时也可直接作为入口;触发名:solve-challengeAlteleFără avertismente★ 845↓ —
- legal-risk-assessment-anthropiclawve-ai/awesome-legal-skillsAssess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.JuridicFără avertismente★ 931↓ —
- beta-testingrshankras/claude-code-apple-skillsBeta testing strategy for iOS/macOS apps. Covers TestFlight program setup, beta tester recruitment, feedback collection methodology, user interviews, signal-vs-noise interpretation, and go/no-go launch readiness decisions. Use when planning a beta, setting up TestFlight, collecting user feedback, or deciding if ready to launch.TestareFără avertismente★ 863↓ —
- 16-marketing-psychologyminhnv0807/ai-business-skillsDung khi can hieu VI SAO nguoi ta mua va ap dung nguyen tac tam ly vao marketing — khan hiem, bang chung xa hoi, cam ket nhat quan, uy tin, co lai, neo gia, ac cam mat mat — kem cach dua vao copy, landing page, email, ads va dieu chinh theo van hoa Viet Nam. Kich hoat khi user nhac 'tam ly khach hang', 'marketing psychology', 'FOMO', 'social proof', 'khan hiem', 'Cialdini', 'lam sao thuyet phuc khach', 'trigger cam xuc', 'khach doc xong van khong hanh dong'. Khong dung cho — viet copy thanh pham thi dung skill 05-copy-quang-cao; dong goi goi ban va bonus thi dung skill 31-offer-design; chan doan mot trang cu the khong ra don thi dung skill 68-cro-audit-trang.MarketingFără avertismente★ 641↓ —
- code-sizershankras/claude-code-apple-skillsEnforce complexity and size limits on Swift code with SwiftLint threshold rules — cyclomatic complexity, function/type/file length, parameter count — adopted via a violations baseline so existing code never blocks. Use when agent-written code needs deterministic size constraints.InginerieFără avertismente★ 863↓ —
- 39-content-audit-globalminhnv0807/ai-business-skillsUse when published content has to be audited — pull channel data, classify winners and losers by percentile across pillar, format, and hook, find the pattern behind performance, and decide what to keep, kill, or scale. Trigger on 'content audit', 'which posts are working', 'content performance review', 'why did that one go viral', 'our reach is dropping', 'evaluate what we posted last month'. Also use when the user only says content does not seem to work anymore. Not for — the plan for next period built on these findings, see `40-next-content-plan-global`; paid ad account review, see `21-ads-audit-global`; the stakeholder report, see `07-marketing-report-global`.MarketingFără avertismente★ 641↓ —
- story-mineindranilbanerjee/digital-marketing-proMine a real story like a client win into 3-5 content angles with draft openings. "is there a post in this"AlteleFără avertismente★ 925↓ —
- dark-funnelindranilbanerjee/digital-marketing-proMap the dark funnel attribution misses: communities, AI citations, podcasts, word of mouth. "map our dark funnel"AlteleFără avertismente★ 925↓ —
- assistive-accessrshankras/claude-code-apple-skillsAssistive Access implementation for cognitive accessibility including simplified scenes, navigation icons, runtime detection, and design principles. Use when optimizing apps for Assistive Access mode.DesignFără avertismente★ 863↓ —
- 30-design-master-globalminhnv0807/ai-business-skillsUse when the user wants a marketing image GENERATED or an image prompt written — personal brand portraits, logos and monograms, campaign key visuals, day-to-day social graphics, editorial art, infographics, web hero mockups, and quote graphics. Reads brand identity from project context, composes an on-brand prompt, generates via gpt-image-2 when an API key exists, otherwise outputs paste-ready prompts for DALL-E 3, MidJourney, Leonardo, or Ideogram. Trigger on 'design an image', 'make me a logo', 'MidJourney prompt', 'key visual for the campaign', 'generate a graphic for this post', 'I need a visual and have no designer'. Not for — briefing a human designer on a static, see `42-image-brief-global`; a slide sequence, see `43-carousel-brief-global`; the brand rules themselves, see `46-brand-guideline-global`; scoring a finished design, see `47-design-review-global`.DesignFără avertismente★ 641↓ —
- cra-vulnerability-obligationslawve-ai/awesome-legal-skillsUse when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they must report a vulnerability or incident, or what a specific CVE triggers legally. Maps a product with digital elements to CRA scope, product classification, Annex I vulnerability-handling duties, and Article 14 reporting obligations — every legal claim cited from official regulation text fetched live through the Ansvar Gateway MCP connector, joined with live CVE / CISA-KEV / EPSS vulnerability intelligence from the same connector.SecuritateFără avertismente★ 931↓ —
- 19-ab-test-setup-globalminhnv0807/ai-business-skillsUse when the user wants a VALID experiment instead of a guess — hypothesis, one variable, sample size and runtime math, statistical significance, primary versus secondary metrics, multi-arm designs, and a results template, across Optimizely, VWO, and native Meta and Google tests. Trigger on 'A/B test', 'split test', 'how long should I run the test', 'is this result significant', 'test two versions', 'which creative is actually better'. Also use when a winner was declared after two days on tiny numbers. Not for — scaling the proven winner, see `55-scaling-ads-global`; analyzing data already collected, see `13-data-analysis-global`; auditing the account, see `21-ads-audit-global`.TestareFără avertismente★ 641↓ —
- gtrk-vlog-docuGitruck/cliVlog 纪实类一站式成片图纸——纪实 Vlog 是散文的载体：用有限的素材，把一个故事、或一个几个思想，串联起来（形散神不散）。表达形态上是「现场同期声 × 后期旁白」双声道交替，区别于纯口播链（单一对镜说）与纯配音链（全片旁白配 B-roll）：同期声片段是内容本体不是配画，旁白只做定调层。当用户想「做一条纪实 vlog / 我拍了一堆素材想做成有深度的 vlog / 探店探险探厂记录 / 日常生活流做成片 / 旅途记录 / 野采野钓记录 / 城市漫游 citywalk / 圣地巡礼 / 取景地探访 / 挑战企划记录」时使用本 skill。凡涉及把带同期声的现场素材做成纪实成片，优先用本 skill 编排 gtrk CLI 全链，不要手搓单命令、别让用户逐步驱动。InginerieFără avertismente★ 962↓ —
- liquid-glassrshankras/claude-code-apple-skillsImplement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and WidgetKit. Use when creating modern glass-based UI effects.DesignFără avertismente★ 863↓ —
- stakeholder-comms-planner-scott-margettslawve-ai/awesome-legal-skillsStakeholder mapping, communication plan design, reporting hierarchy, and mid-matter comms updates. Use when setting up a new matter and needing to identify who needs what information, designing the communication rhythm, building reporting structures for multi-jurisdiction programmes, or updating the comms plan when the stakeholder landscape changes. Trigger on: 'stakeholder map', 'who needs to be kept informed', 'communication plan', 'reporting structure', 'who do we report to', 'how often do we meet', 'client wants more updates', 'new contact on the client side', 'build the comms plan', 'reporting hierarchy', 'HQ vs regions', 'who is the decision maker', 'comms rhythm', 'meeting cadence', 'status call schedule'.PlanificareFără avertismente★ 931↓ —
- data-flowrshankras/claude-code-apple-skillsSwiftUI's actual mental model — view identity, lifetime, and dependencies (the Demystify canon), state ownership decision rules, Observation's per-property tracking, body-performance discipline, and the main-actor concurrency contract. Use when state resets mysteriously, views re-render too often, animations glitch between branches, choosing @State vs @Bindable vs plain property, or debugging "why did body run."MediaFără avertismente★ 863↓ —
- jev-question-translatorlawve-ai/awesome-legal-skillsTurns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that TypeSafe's Jev, a fast classifier that returns probabilities rather than prose, can answer reliably across many documents. The skill breaks conclusions such as negligence, felony murder, or standing into element-level questions, writes the governing rule into each question, and delivers the questions alone, in Jev's request format or in plain English. Built for legal work that asks the same questions of many texts: coding statutes across jurisdictions, coding opinions or case files for empirical research, checking contracts against a review checklist, screening intake narratives, and grading student work against a rubric. Use when asked to write Jev questions, build a classifier for legal documents, or turn a legal test into yes-or-no questions. Running the questions requires Jev access; writing them does not.TestareFără avertismente★ 931↓ —
- compliance-anthropiclawve-ai/awesome-legal-skillsNavigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests. Use when reviewing data processing agreements, responding to data subject access or deletion requests, assessing cross-border data transfer requirements, or evaluating privacy compliance.JuridicFără avertismente★ 931↓ —
- 11-channel-setup-globalminhnv0807/ai-business-skillsUse when the user needs to choose and stand up marketing channels and the tech behind them — channel selection scoring, platform-by-platform setup checklists, business account and verification steps, and integrations, with region priorities: US Meta plus Google plus LinkedIn, EU adding Xing, SEA adding TikTok, Shopee, Lazada and LINE, LATAM adding WhatsApp Business and Mercado Libre. Trigger on 'channel setup', 'which platforms should we be on', 'set up Google Business Profile', 'marketing tech stack', 'we are starting from zero on social', 'connect our accounts'. Not for — conversion tracking and pixels, see `53-tracking-setup-global`; ad account hierarchy, see `52-account-structure-global`; the posting plan once channels exist, see `01-content-calendar-global`.MarketingFără avertismente★ 641↓ —