Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Cialdini 7 principles applied to global marketing — reciprocity, scarcity, authority, social proof, liking, commitment, unity. Universal psychology with international examples (Apple, Tesla, Patagonia, Spotify). Trigger: 'marketing psychology', 'Cialdini', 'persuasion principles', 'consumer psychology', 'behavioral marketing'.
Setup marketing channels for global businesses — channel selection, platform-specific setup checklists, integration guides. Has 4 region variants (US/EU/SEA/LATAM) with region-specific platform priorities. US: Meta+Google+LinkedIn. EU: + LinkedIn/Xing. SEA: TikTok+Shopee/Lazada+LINE. LATAM: WhatsApp Business+Mercado Libre. Trigger: 'channel setup', 'platform setup', 'marketing tech stack', 'multi-channel marketing', 'platform selection'.
Pricing strategy for global markets — value-based, anchor pricing, charm pricing, decoy effect. Has 4 region variants for currency psychology (US/EU/SEA/LATAM). INCLUDES Dropshipping Markup Math section (3-5x markup, BE-ROAS, profit margin). Trigger: 'pricing strategy', 'price positioning', 'charm pricing', 'pricing psychology', 'dropshipping markup'.
Generic client intake brief for international marketing agencies — 11-section template covering business overview, target audience, current marketing, goals, budget, timeline, brand assets, success criteria. Generic version (no industry variants for v2.5 — coming in v2.6+ if demand). Trigger: 'client intake', 'agency brief', 'new client onboarding', 'project kickoff brief', 'discovery call template'.
Comprehensive ads audit for Meta/Google/TikTok with Health Score 0-100. 84 checkpoints across 6 dimensions (Account/Campaign/AdSet/Ad/Tracking/Optimization). Has 4 region variants for benchmarks. INCLUDES Dropshipping Audit Checklist (creative testing velocity, CRO signals, attribution accuracy). Trigger: 'ads audit', 'ad account audit', 'Meta audit', 'Google Ads audit', 'TikTok audit', 'dropshipping ads audit'.
Referral program design for global businesses — 1-way vs 2-way, incentive structure, anti-fraud, attribution. Has 4 region variants for anti-spam compliance (TCPA US, GDPR EU, PDPA SEA, LGPD LATAM). Trigger: 'referral program', 'refer a friend', 'word of mouth', 'viral loop', 'referral marketing'.
| Triggers — "design image", "create logo", "campaign visual", "social post design", "infographic", "key visual", "hero web mockup", "marketing visual", "personal avatar", "monogram", "quote graphic", "MidJourney prompt", "DALL-E prompt", "brand mockup", "reference image", "master prompt", "brand color adaptation", "add logo". DO NOT USE for — full interactive web UI (use web-prototype/saas-landing instead), video creation (use 04-script-video-global + Seedance/Kling), animation (use motion-frames).
Design valid A/B tests for global marketing — hypothesis formulation, sample size calculation, statistical significance, multi-arm testing, primary vs secondary metrics. Tools: Optimizely, VWO, Google Optimize (sunset 2023, alternatives), built-in platform tests (Meta, Google). Trigger: 'A/B test', 'split test', 'multivariate test', 'experiment design', 'statistical significance', 'sample size calculator'.
Foundation skill for the global marketing cluster. Creates `.agents/product-marketing-context-global.md` with region-specific context (currency, primary platforms, regulations, persona research framework). Pick 1 of 4 region variants: US (USD/FTC), EU (EUR/GDPR), SEA (USD or local/PDPA), LATAM (USD or local/LGPD). All other global skills (00-29) read this context file. Trigger: 'global marketing context', 'international product context', 'US marketing context', 'EU marketing setup', 'SEA marketing context', 'LATAM marketing setup', 'multi-region context'.
Ke hoach Fullstack Marketing — master skill tong hop chien luoc, noi dung, trien khai, hieu suat, va timeline. Goi cac skill con de hoan thien output.
Lich noi dung thang — len lich dang bai da kenh voi ti le pheu, content pillar, repurposing matrix, va scoring tieu chi.
Viet script video ngan cho TikTok, Reels, YouTube Shorts — 2 ban A/B, co hook, CTA, huong dan quay chi tiet
Brief chien dich marketing — 9 phan day du tu Context den Risk, bao gom creative direction, RACI, budget allocation theo phase, va auto-trigger cac skill lien quan.
Danh gia hieu suat marketing — audit performance ads va organic, chan doan root cause, de xuat toi uu voi action plan 48h va checklist hang tuan.
Tao brief chi tiet cho UGC (khach hang), EGC (nhan vien), KOC (creator tra phi) — gom huong dan quay, do/don't, quyen su dung, quan ly batch
Phan tich doi thu canh tranh 3 tang (truc tiep, gian tiep, thu cap) — dinh vi, SWOT, content benchmark, tim khoang trong thi truong
Bao cao marketing theo nguyen tac "doc 5 phut, biet lam gi tiep" — nhan dinh truoc, so lieu minh hoa, de xuat co thoi han va nguoi phu trach
Viet 6 bien the copy quang cao theo 3 tang pheu (TOFU/MOFU/BOFU), tuan thu chinh sach quang cao, co CTA phu hop tung nen tang
Xay dung chan dung khach hang sau — Consumer vs Shopper, JTBD, hanh trinh mua hang, insight validation, internal monologue
Tinh KPI nguoc tu doanh thu ve ngan sach va tinh xuoi tu ngan sach ra doanh thu — 3 kich ban, sensitivity analysis, break-even, phan bo ngan sach theo giai doan va kenh
Thiet lap va van hanh email marketing — welcome series, nurture, promotion, re-engage — toi uu cho thi truong Viet Nam
Tao brief landing page chuyen doi cao — 7 section, 1 page = 1 goal = 1 CTA, mobile-first, toi uu conversion
Giam sat thuong hieu, doi thu, xu huong nganh tren mang xa hoi — phat hien som khung hoang va co hoi content
Huong dan thiet lap kenh marketing A-Z — TikTok Brand, Zalo OA, Facebook Page, Email (Brevo), TikTok Shop, Instagram Business, Google Business Profile — tu tao den chay 30 ngay dau
Doc data marketing tho va bien thanh insight hanh dong — phan tich theo kenh, chien dich, creative, doi tuong, thoi gian
Khi nguoi dung can ap dung nguyen tac tam ly vao marketing — cham cam xuc, tao khan cap, xay trust, thuyet phuc mua. Cung dung khi nguoi dung nhac 'tam ly khach hang', 'psychology marketing', 'scarcity', 'FOMO', 'social proof', 'Cialdini', 'thuyet phuc khach', 'trigger cam xuc'. Skill nay giai thich 7 nguyen tac tam ly + cach dung vao copy, landing page, email, ads — dieu chinh theo van hoa Vietnam.
Khi nguoi dung can thiet lap gia san pham/dich vu, thay doi chien luoc gia, hoac toi uu pricing page. Cung dung khi nguoi dung nhac 'chien luoc gia', 'dinh gia san pham', 'pricing strategy', 'pricing tier', 'goi dich vu', 'discount strategy', 'gia vs doi thu', 'goi combo'. Skill nay giup xac dinh mo hinh gia + chien thuat dinh gia + pricing page — toi uu cho tam ly khach hang VN.
Khi nguoi dung can thiet ke chuong trinh gioi thieu bạn be (referral program), affiliate, hoac word-of-mouth. Cung dung khi nguoi dung nhac 'referral program', 'chuong trinh gioi thieu', 'affiliate', 'word of mouth', 'hoa hong gioi thieu', 'ma moi ban', 'giam gia khi gioi thieu'. Skill nay thiet ke referral mechanics (thuong 1 chieu / 2 chieu), tracking, chong gian lan, va campaign launch — toi uu cho thi truong VN.
Khi nguoi dung can thiet lap A/B test cho ads, landing page, email, hoac product. Cung dung khi nguoi dung nhac 'A/B test', 'split test', 'test creative', 'test copy', 'test landing', 'test gia', 'kiem dinh thong ke', 'sample size'. Skill nay giup chon bien can test, tinh sample size, setup tracking, va phan tich ket qua thong ke (significance) — phu hop cho team khong phai data scientist.
Tao brief khach hang dien cho agency (client intake form) — form thu thap thong tin dau vao chi tiet de agency lap ke hoach marketing chinh xac. Co 20 variants chuyen biet theo nganh — moi variant la full brief toi uu hoa cho dac thu nganh do.
Audit toan dien tai khoan quang cao — cho diem Health Score 0-100, liet ke Quick Wins, phat hien vi pham Quality Gates, de xuat action plan theo muc do uu tien. Ho tro Meta Ads, TikTok Ads, Google Ads, Zalo Ads.
| Triggers — "thiết kế ảnh", "làm logo", "ảnh poster", "banner campaign", "social post", "infographic", "key visual", "hero web mockup", "ảnh truyền thông", "avatar cá nhân", "monogram", "quote graphic", "prompt MidJourney", "prompt DALL-E", "ảnh reference", "prompt master", "đổi màu thương hiệu", "thêm logo". KHÔNG dùng cho — UI wireframe full interactive (dùng web-prototype/saas-landing thay), video creation (dùng 04-script-video + Seedance/Kling), animation (dùng motion-frames).
Khi nguoi dung muon tao hoac cap nhat tai lieu goc ve san pham, khach hang, va dinh vi thuong hieu. Cung dung khi nguoi dung nhac 'product context', 'marketing context', 'thiet lap context', 'dinh vi', 'tep khach hang muc tieu', 'mo ta san pham', 'ICP', 'chan dung khach hang ly tuong', hoac muon tranh lap lai thong tin co ban cho moi task. Dung O DAU moi du an marketing truoc khi dung cac skill khac — skill nay tao file `.agents/product-marketing-context.md` ma tat ca skill khac doc truoc.
Chien luoc marketing xuat khau B2B cho doanh nghiep Viet Nam — tao ho so nha xuat khau, lap ke hoach trien khai thi truong nuoc ngoai, viet pitch deck va email chao hang quoc te, chuan bi cho hoi cho thuong mai. Triggers: "xuat khau", "B2B nuoc ngoai", "thi truong quoc te", "pitch khach nuoc ngoai", "ho so cong ty bang tieng Anh", "email chao hang export", "tham du hoi cho", "buyer nuoc ngoai", "company profile", "export marketing
Creates an opportunity solution tree connecting a desired outcome to customer opportunities and candidate solutions, preventing solution-first jumps in continuous discovery. Use when structuring scattered feature ideas or communicating how the roadmap traces to outcomes. For ranking an existing flat list of candidates, use define-prioritization-framework instead; this skill discovers the list, it does not score one.
Creates a clear problem framing document with user impact, business context, and success criteria. Use when starting a new initiative, realigning a drifted project, or communicating up to leadership.
Creates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job. Use when deeply understanding customer motivations, designing for jobs, or reframing product positioning.
Generates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy path, key failure scenarios, and non-functional expectations in testable form. Use when turning requirements into verifiable scenarios for engineering handoff and QA sign-off. For a dedicated catalog of boundary conditions, error states, and recovery paths across a feature, use deliver-edge-cases; to write the stories themselves, use deliver-user-stories.
Run applicable prioritization frameworks (RICE, ICE, MoSCoW, Weighted Scoring, Kano) against a list of features or initiatives. Produces a comparison table showing where rankings agree and diverge across frameworks, and an executive summary with recommendation. Framework applicability is filtered by data availability; Kano requires customer research. Refuses to fabricate scores; produces an estimation scaffold when input data is missing.
>- Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date.
Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.
Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date.
Creates a cross-functional pre-launch checklist covering engineering, design, marketing, support, legal, and operations readiness, with owners, dates, and go/no-go criteria so nothing is missed before release. Use for significant or cross-team launches, not a small single-team change. For the customer-facing announcement of what shipped, use deliver-release-notes instead.
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary and limit scenarios to test. Distinct from deliver-acceptance-criteria, which writes story-level Given/When/Then checks; this skill produces the whole-feature edge-case catalog.
Generates user stories in the standard persona, action, benefit story format from product requirements or feature descriptions. Use when breaking a feature into stories for sprint planning, writing tickets, or communicating scope to engineering. For testable Given/When/Then acceptance criteria on a story, use deliver-acceptance-criteria; for boundary and failure scenarios, use deliver-edge-cases.
Documents the reasoning behind design decisions including alternatives considered, trade-offs evaluated, and principles applied. Use when making significant UX decisions, aligning with stakeholders on design direction, or preserving design context for future reference.
Creates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be measured. Use when specifying features, epics, or product initiatives for engineering handoff.
Creates a concise one-page solution overview that communicates the proposed approach, key decisions, and trade-offs. Use when pitching solutions to stakeholders, aligning teams on approach, or documenting solution intent before detailed specification.
Creates an Architecture Decision Record following the Nygard format to document significant technical decisions, their context, and consequences. Use when making technical choices that affect system architecture, technology selection, or development patterns.
Creates user-facing release notes that communicate new features, improvements, and fixes in clear, benefit-focused language. Use when shipping updates to communicate changes to users, customers, or stakeholders.
Creates a structured competitive analysis comparing features, pricing, and positioning across 3-5 direct and indirect competitors, with a 2x2 map and actionable strategic recommendations. Use before entering a market, planning differentiation, or after losing deals. For market size rather than competitor positioning, use discover-market-sizing instead.
Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommendation so the team does not re-litigate the exploration. Use once a time-boxed investigation has concluded. For the architecture decision the spike informs, use develop-adr instead; for research-based exploration, use discover-interview-synthesis.
Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research into the shape of a customer's experience, end-to-end or for one phase. Without research signal yet, run discover-interview-synthesis or measure-survey-analysis first; refuses to fabricate emotional or behavioral data.
Synthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user interviews, customer calls, or usability sessions to extract and communicate findings across participants. Distinct from foundation-meeting-recap, which summarizes one internal meeting for its attendees; this skill aggregates research conversations into evidence-backed findings.
Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as signal, and produces a calibrated range with source-graded confidence labels. Refuses unbounded fabrications; always offers a labeled lower-confidence path when data is thin. Used for investment cases, go/no-go decisions, and stakeholder pitches.
Maps the people and groups with a stake in a project, documenting their needs, concerns, influence, and engagement approach. Use at project kickoff, when taking over from another PM, or when resistance signals misalignment. For the update you send to those stakeholders, use foundation-stakeholder-update instead; this skill maps them, that one talks to them.
Runs a fast pre-build risk review on a product idea, feature request, or scope change, naming the single assumption most likely to make it fail and returning a clear verdict (build small, validate first, pivot first, or don't build yet) with a no-code validation step. Use before committing build effort, when triaging whether to honor a feature request, or when deciding whether to expand scope, ahead of writing a PRD. For a launched product's pivot-or-persevere decision, use iterate-pivot-decision instead.
Produces a one-page lean canvas across nine interlocking blocks (problem, customer, UVP, solution, channels, revenue, cost, metrics, unfair advantage) with optional inline HTML and SVG visual rendering. Use when framing a new product thesis, stress-testing an existing strategy, comparing strategic options side-by-side, or aligning a team on business-model assumptions. Works as a strategic hub that cross-links to deeper PM skills without duplicating them.
Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants (standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing). Emits a shareable summary suitable for Slack or email plus a full agenda with time-boxed topics, type tags, owners, attendee prep, and logistics.
Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic (plus a consolidated action view at the end). Auto-populates topic skeleton from a sibling meeting-agenda when available and reconciles planned vs. actual topics. Accepts transcripts from Zoom, Meet, Otter, Fireflies, Krisp MCP, or manual notes; runs on variable-quality input without blocking. For synthesizing user research interviews across participants, use discover-interview-synthesis.
Claude Skills — questions
Answers built from the skills we actually parsed.