Business & Operations

You are the full marketing audit engine for `/market audit <url>`. You launch 5 parallel subagents, aggregate their results, and produce a unified MARKETING-AUDIT.md report that is client-ready and revenue-focused.

You are the advertising engine for `/market ads <url>`. You generate complete ad campaigns across platforms with full copy variations, audience targeting strategies, budget recommendations, and creative specifications. Every ad is ready for production or handoff to a media buyer.

You are a comprehensive AI marketing analysis and content generation system for Claude Code. You help entrepreneurs, agency builders, and solopreneurs analyze websites, generate marketing content, audit funnels, create client proposals, and build marketing strategies — all from the command line.

Flip any conflict, negotiation, or difficult situation to the opponent's perspective to extract superior tactical advice. Use whenever someone is dealing with a landlord dispute, bureaucratic obstruction, workplace conflict, legal challenge, scam attempt, negotiation, difficult relationship dynamic, or any situation where they feel stuck, outmaneuvered, or unsure how to respond. Trigger phrases include: dealing with, fighting with, they keep, I am being harassed, how do I handle, I don't know...

Turn insights, findings, or research into an actionable plan with deadlines and scheduled Telegram reminders. Collaboratively designs the plan with the user via AskUserQuestion, saves it to .plan/ in the project, sets up cron reminders via Telegram bot, and shows overdue/today tasks on session start. Use when asked to "make a plan", "actionize this", "turn this into tasks", "schedule this", "create deadlines", "track this", or "diagnose my planning". Invoke with "diagnose" argument to run pla...

Use when editing `server/fake-antminer/` or `server/fake-proto-rig/`. These are test doubles consumed by `tests/plugin-contract/`, the E2E suites, and the local `just dev` stack — behavior changes here ripple silently into all three surfaces.

Compile previously-generated audit artifacts into a client-ready report in Markdown or PDF format. Invoke whenever the user says "report", "final report", "deliverable", "client report", "PDF report", or runs `/market report <url>` or `/market report --format pdf <url>`. Reads existing audit files in the project root and produces one consolidated deliverable.

Client proposal and statement of work for marketing services with pricing calculator, scope definition, and success metrics. Invoke whenever the user says "proposal", "SOW", "statement of work", "quote a client", "pitch for", or runs `/market proposal <client>`. Produces PROPOSAL.md that can be sent as-is.

Four-week product / feature / campaign launch plan covering pre-launch, launch week, post-launch, and retention. Invoke whenever the user says "launch", "going live", "product launch", "launch plan", "launch sequence", or runs `/market launch <product>`. Produces LAUNCH-PLAN.md with day-by-day tasks, asset checklist, and metrics to watch.

Conversion rate optimization audit for a single landing page. Invoke whenever the user says "landing page", "CRO", "why isn't this converting", "fix my landing page", or runs `/market landing <url>`. Produces LANDING-CRO.md with a conversion score, a priority grid of issues (impact vs effort), and specific rewrites for the hero, social proof, CTAs, and form.

Generate email sequences (welcome, nurture, launch, cold outreach, cart abandon, re-engagement, onboarding) with subject line variants, cadence, and metrics benchmarks. Invoke whenever the user says "email sequence", "welcome series", "nurture", "cold outreach", "win-back", or runs `/market emails <type>`. Matches BRAND-VOICE.md if present.

Competitor intelligence scan covering positioning, pricing, messaging, social proof, and historical evolution via Wayback Machine. Invoke whenever the user says "competitors", "competitive analysis", "how do we stack up", "alternatives to", or runs `/market competitors <url>`. Produces COMPETITOR-ANALYSIS.md with a side-by-side matrix and specific differentiation plays.

Brand voice, tone, and archetype analysis with generated voice guidelines. Invoke whenever the user mentions "brand voice", "tone of voice", "how do we sound", "brand guidelines", "archetype", or runs `/market brand <url>`. Produces BRAND-VOICE.md with 4 voice dimensions, archetype mapping, do/don't chart, vocabulary lists, and 8 copy samples.

Comprehensive marketing audit of a website using 5 parallel specialist subagents. Invoke whenever the user says "audit", "marketing audit", "review my site", "how's my marketing", or runs `/market audit <url>`. Produces MARKETING-AUDIT.md with a 0-100 composite score, per-dimension scores, prioritized findings, and a 30/60/90-day action plan tied to estimated revenue impact.

Marketing command center for Claude Code. Invoke whenever the user mentions marketing audits, CRO, SEO, landing pages, copy rewrites, email sequences, ad copy, social content, competitors, brand voice, launches, funnels, proposals, or anything resembling "grow this business", "audit this site", "improve conversions", or "/market <something>". Routes subcommands to specialized skills and can run a multi-agent audit in parallel.

File-first orchestrator for business and product strategy frameworks. Frames the challenge with a CPO / CSO / VP Design role, spawns parallel framework agents (Rumelt kernel + Crux, Wardley Maps, Minto Pyramid as thinking structure, Working Backwards PR-FAQ as discovery artifact), synthesizes outputs into one strategy memo, runs a critic pass. Ships per-framework references, leadership role prompts, templates for strategy memos, PR-FAQs, Wardley maps, Minto arguments. Use when the user asks t...

Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation strategy, phase documentation.

This skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

แผนระดมทุนสำหรับ Thai startup จาก Thai VC จริงปี 2026 (500 Global, AddVentures, Beacon VC, Krungsri Finnovate, SCB10X, KX, Bualuang Ventures, InnoSpace) — stage, check size, thesis จริงไม่ใช่ YC template ฝรั่ง

คำนวน CAC / LTV / payback period ด้วย benchmark Thai marketing channels 2026 (Meta, TikTok, LINE OA push, KOC/nano/mid-tier KOL ของ Tellscore/AnyMind/MEDIA Z) — ไม่ใช้ตัวเลข US

คำนวน landed cost ของสินค้าที่ import จาก 1688/Alibaba/global supplier — รวม import duty ตาม HS code, VAT 7% on CIF, flag FDA/TISI/มอก. registration requirement

วาด Business Model Canvas สำหรับ SME ไทย โดยมีช่องที่ template ฝรั่งไม่มี — family-stakeholder map, ทุนจดทะเบียน vs ทุนชำระแล้ว, MOU vs registered partner, informal employee, "พี่/น้อง/หลาน" guarantor มาแทนที่ "co-founder equity vesting"

ตั้งราคาแบบ waterfall ที่หัก marketplace fee, payment gateway, shipping ของ Thai channels (Shopee/Lazada/TikTok Shop/LINE Shopping/หน้าร้าน) เพื่อให้ได้ margin จริงที่ user ต้องการ