菜单
Produce customer case studies from interviews or data — Problem, Solution, Results structure with perception engineering and quality gates. Use when "case study", "customer story", "testimonial", "success story", "client results", or any request to document a customer win.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Marketing team as slash commands. Current Kai inventory: 48 skill directories, 45 canonical kai-* skill docs, 42 public /kai router commands, 54 playbook docs, 36 checklists, 27 framework docs, 26 channel guides, and 8 audience persona profiles. Full marketing ops from brief to gate.
Turn a brand's positioning into a 30-day, multi-platform content batch — 3-7 pillars, subtopic matrix mapped to funnel stage and persona, pillar pieces plus derivative fan-out, proof elements in at least half the slots, all registered in the editorial calendar store and quality-gated. Use when "content batch", "batch my content", "30 days of content", "month of content", "content batching machine", "content pillars", "fill the content calendar", "plan a month of posts", or any request to produce a full month of multi-platform content in one run.
Two-layer funnel audit on collected data only — stress-test the awareness layer (hooks, messaging, proof placement, attention leaks on live pages and ads) and the lead-capture layer (opt-ins and lead magnets scored on the four Value Equation variables, friction findings, weakest-magnet rewrite), plus a phone-path check under the KaiCalls Fit Rule. Use when "funnel audit", "audit my funnel", "why is my funnel leaking", "top of funnel isn't converting", "audit our lead magnets", "opt-in audit", "awareness to lead audit", "where are we losing people", "lead capture audit", or any request to diagnose the full awareness-to-lead flow rather than one page.
Generate, rank, and gate a reusable hook bank — sourced pains × named hook formula families, scored on clarity/specificity/curiosity/proof-backing, gated at the 10/16 ad threshold, delivered in 3 lengths with per-hook provenance and downstream routing. Use when "hook bank", "generate hooks", "hook generator", "write hooks for", "ad hooks", "scroll stoppers", "opening lines", "hook ideas", "first 3 seconds", "hook matrix", "I need 50 hooks", or any request to batch-produce attention-openers for ads, social, or video.
Construct and score Grand Slam Offers using the Value Equation — sourced pain mining, dream outcome articulation, problems→solutions→trim-and-stack offer construction, guarantee/scarcity/bonus design, 1-10 scoring on the four Value Equation variables, pricing sanity pass, and compliance check. Use when "build an offer", "grand slam offer", "value equation", "offer stack", "make this offer irresistible", "design a guarantee", "hormozi offer", "why isn't my offer selling", "pricing and packaging for my offer", or any request to design, score, or rework a commercial offer.
Build and maintain a provenance-clean proof library — inventory every real proof asset (analytics, reviews, permitted testimonials, case studies, press, certifications), categorize it, rewrite each cleared item in 3 lengths, fuse top assets with narrative, and gate everything through FTC testimonial rules before it can ship. Use when "proof library", "gather our proof", "authority builder", "collect testimonials", "social proof assets", "proof points for the sales page", "what results can we claim", or any request to assemble evidence for marketing claims. NEVER invents proof — missing proof is reported as a gap.
基于 SOC 职业分类
| name | kai-case-study |
| description | Produce customer case studies from interviews or data — Problem, Solution, Results structure with perception engineering and quality gates. Use when "case study", "customer story", "testimonial", "success story", "client results", or any request to document a customer win. |
Produce compelling customer case studies using a Problem, Solution, Results structure with perception engineering layers.
Check if MARKETING.md exists in the project root (same directory as CLAUDE.md, README.md, package.json).
If it exists: Read it — skip product discovery questions. It has the product name, ICP, value prop, monetization, brand voice, current channels, and competitive landscape.
If it does NOT exist: Auto-explore the codebase to create it in the project root (next to CLAUDE.md). Do NOT ask the user what the product is. Read CLAUDE.md, README.md, PROJECT.md, package.json, landing pages, and any project files. Search for email/ad/analytics config. Then create MARKETING.md using the template from /kai-email-system. Present draft to user for confirmation.
Read from MARKETING.md. Only ask about things not covered there:
knowledge/personas/_persona-index.mdStructure the case study:
knowledge/checklists/content-checklist.mdknowledge/frameworks/content-copywriting/perception-engineering.mdWrite the case study:
Apply perception engineering layers:
Run all gates before delivery:
python scripts/quality_gates/four_us_score.py <file>
python scripts/quality_gates/banned_word_check.py <file>
Max 2 auto-retry cycles. After 2 failures, surface to human with specific failure reasons.
Deliver the final case study package:
Write output to workspace/ with filename pattern: case-study-[company]-YYYY-MM-DD.md