测试与安全技能

Use when you want campaign performance reviewed against benchmarks, with a health score and prioritized optimization recommendations.

中文简介正在准备中。当前显示原文说明。

One-click technical SEO audit of a website. Runs the full technical SEO audit SOP — crawlability, indexation, Core Web Vitals, schema markup, internal linking, mobile UX, and content quality. Outputs a prioritized fix list. Use when "SEO audit", "technical SEO", "site audit", "crawl issues", "indexation problems", "why aren't we ranking", "SEO health check", or any request to diagnose SEO issues on a website.

中文简介正在准备中。当前显示原文说明。

Audit or design generative AI interfaces against three diagnostic pillars (deterministic-stochastic balance, interaction density, visual cohesion). Treats taste as a measurable control system, not subjective preference. Use when: 'taste audit', 'score this UI', 'design quality', 'interaction density', 'visual cohesion', 'refiner layer', 'correction cost', 'why does this feel off', 'polish this', 'design review', or building any user-facing AI product.

中文简介正在准备中。当前显示原文说明。

Weekly marketing audit and operating review. Pulls the last 7 days of source-backed marketing, analytics, content, paid media, lead, watcher, and audit data; compares it to the prior 7 days; flags urgent issues; and produces a weekly scorecard plus action list. Use when "weekly audit", "weekly marketing review", "weekly check-in", "weekly scorecard", "what changed this week", "Friday marketing review", or any request for a recurring 7-day marketing audit.

中文简介正在准备中。当前显示原文说明。

Code-rendered motion video for a product or a client, built the way a motion studio would do it. Every frame comes from an HTML seek(t) page rendered by Playwright at 1080p60 with real motion blur, using real product UI and screenshots with a privacy blur, and an ElevenLabs hype score cut on bar lines with its drop verified on the reveal. Three formats — a 20-30 s hype launch spot, a polished feature walkthrough from real screenshots, and a 19 s pain-point video with a muted site cut and burned-in text. Delivered with baked posters, H.264 + VP9 web encodes at 1280 px (1.5-3 MB), a site-embed kit (muted autoplay or click-to-play), 9:16 social re-layouts and share copy, plus a service playbook for selling it. Use when "make a launch video", "make a commercial / promo / ad spot", "motion design video", "product walkthrough video from screenshots", "pain point videos for the site", "videos for the homepage", "sell video production", "price a video package", or a polished brand spot is wanted rather than a talking-head edit or a Remotion template batch (use /kai-video-production for those).

中文简介正在准备中。当前显示原文说明。

Ship a complete go-to-market deliverable pack for a client as a cross-linked set of private HTML pages topped by a client hub (the ask, tool install, access grants, ordered signup checklist). Use when "GTM plan for [client]", "put together a GTM", "go to market plan", "build the client hub", "attach everything for the client", "package this for the client", or when an engagement's plan/audit/emails must be delivered as linked pages rather than loose files.

中文简介正在准备中。当前显示原文说明。

Audit any URL against 17-point technical SEO checklist + algorithmic authorship rules. Uses /browse if available, falls back to checklist-based audit.

中文简介正在准备中。当前显示原文说明。

Surface the right marketing checklist for any task. Covers content, SEO, ads, email, press, landing pages, launches, and technical audits. 17+ checklists indexed by task type.

中文简介正在准备中。当前显示原文说明。

Full marketing audit — runs all relevant checklists against your product, site, and marketing in one go. Covers SEO, content, email, ads, social media, CRO, landing pages, technical SEO, and creative production. Produces a "state of your marketing" report with health scores per area and a prioritized fix list. Use when "marketing audit", "full audit", "audit everything", "marketing health check", "what's broken", "state of marketing", or any request to comprehensively assess marketing across all channels.

中文简介正在准备中。当前显示原文说明。

Generate creative direction for ad campaigns — visual concepts, copy variants, video scripts, image specifications, and A/B test matrices. Platform-aware with format specs.

中文简介正在准备中。当前显示原文说明。

Conversion rate optimization audit — analyze a landing page, signup flow, or checkout funnel using the 5-layer CRO stack (technical performance, traffic quality, offer/pricing, design/layout, copy/messaging). Produces prioritized fix list with expected impact. Use when "CRO audit", "conversion audit", "why isn't this converting", "improve conversion rate", "landing page not converting", "optimize funnel", "signup flow audit", or any request to diagnose and fix conversion problems.

中文简介正在准备中。当前显示原文说明。

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 Phone Capture 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.

中文简介正在准备中。当前显示原文说明。

Evidence-first marketing audit of a third-party local business (café, roaster, shop, restaurant, hotel, clinic, home service) from a Google Maps, share.google or website link — located DataForSEO rankings, map packs, search volume and seasonality, listings, reviews, backlinks, AI-assistant answers and a site crawl, plus direct checks (real-browser access, page weight, store shipping quotes, email DNS, mobile screenshots) — delivered as an owner-facing report with priced offers, an exact change list and a 12-week plan, optionally localized and bilingual. Use when "audit this business", "full marketing audit of <business>", "prospect audit", "local business audit", "use DataForSEO for the hard SEO data", "go deeper", "rerun it for local <market>", "also in Spanish", "give me the offers, changes and 3 month plan", or a business link arrives with "audit". For auditing your own product across channels use /kai-audit.

中文简介正在准备中。当前显示原文说明。

Monthly marketing audit and executive review. Pulls the last 30 days of source-backed marketing, analytics, SEO, CRO, content, paid media, lifecycle, reputation, and pipeline data; compares it to the previous period; summarizes strategic learning; and produces an executive report plus next-month plan. Use when "monthly audit", "monthly marketing review", "monthly report", "executive marketing review", "board-ready marketing report", "month-end audit", or any request for a 30-day marketing audit.

中文简介正在准备中。当前显示原文说明。

Use when refactoring code with poor names, when asked to improve naming, or when a user struggles to name a class/method/variable. Symptoms include -Manager/-Util suffixes, single-letter variables, process/handle/do verbs, primitive obsession, god methods with multiple responsibilities. Two modes — audit (broad scan, list opportunities) and improve (walk one specific identifier through the process).

中文简介正在准备中。当前显示原文说明。

Use when more than one agent may need the same single-instance resource at the same time — most of all the local server loop, which holds the one URL (https://local.voxt.ai, port 7080) the app can run on. Also when you are about to dispatch several agents that will test the UI, when you find another agent already using the loop, or when the user says "coordinate", "shared resource", "queue for the server".

中文简介正在准备中。当前显示原文说明。

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.

中文简介正在准备中。当前显示原文说明。

Answer questions about Voxt — its features, what shipped and when, and how to use it — grounded in three sources: the public "Voxt Announcements" chat, the Landing pages, and the user guide. Use when asked things like "what features shipped this year", "list new features", "how do I use <feature>", "what is Voxt", or any product/usage question about Voxt. Answers are cited to the source.

中文简介正在准备中。当前显示原文说明。

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.

中文简介正在准备中。当前显示原文说明。

Build, deploy and start the iOS app on a connected iPhone or in the simulator. Use proactively when user asks to test, run, or deploy iOS changes.

中文简介正在准备中。当前显示原文说明。

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to smoke-test the evolve pipeline, test tools, or verify the plugin works end-to-end. Also use when the user says 'dry run', 'smoke test', or 'test pipeline'.

中文简介正在准备中。当前显示原文说明。

DeFi Protocol Analysis — analyzes TVL, revenue, yields, liquidity, security, governance, and competitive positioning with a composite DeFi Score (0-100)

中文简介正在准备中。当前显示原文说明。

Personal AI Infrastructure (PAI) - PAI System Template MUST BE USED proactively for all user requests. USE PROACTIVELY to ensure complete context availability. === CORE IDENTITY (Always Active) === Your Name: [CUSTOMIZE - e.g., Kai, Nova, Atlas] Your Role: [CUSTOMIZE - e.g., User's AI assistant and future friend] Personality: [CUSTOMIZE - e.g., Friendly, professional, resilient to user frustration. Be snarky back when the mistake is user's, not yours.] Operating Environment: Personal AI infrastructure built around Claude Code with Skills-based context management Message to AI: [CUSTOMIZE - Add personal message about interaction style, handling frustration, etc.] === ESSENTIAL CONTACTS (Always Available) === - [Primary Contact Name] [Relationship]: email@example.com - [Secondary Contact] [Relationship]: email@example.com - [Third Contact] [Relationship]: email@example.com Full contact list in SKILL.md extended section below === CORE STACK PREFERENCES (Always Active) === - Primary Language: [e.g., TypeScript, Python, Rust] - Package managers: [e.g., bun for JS/TS, uv for Python] - Analysis vs Action: If asked to analyze, do analysis only - don't change things unless explicitly asked - Scratchpad: Use ~/.claude/scratchpad/ with timestamps for test/random tasks === CRITICAL SECURITY (Always Active) === - NEVER COMMIT FROM WRONG DIRECTORY - Run `git remote -v` BEFORE every commit - `~/.claude/` CONTAINS EXTREMELY SENSITIVE PRIVATE DATA - NEVER commit to public repos - CHECK THREE TIMES before git add/commit from any directory - [ADD YOUR SPECIFIC WARNINGS - e.g., iCloud directory, company repos, etc.] === RESPONSE FORMAT (Always Use) === Use this structured format for every response: 📋 SUMMARY: Brief overview of request and accomplishment 🔍 ANALYSIS: Key findings and context ⚡ ACTIONS: Steps taken with tools used ✅ RESULTS: Outcomes and changes made - SHOW ACTUAL OUTPUT CONTENT 📊 STATUS: Current state after completion ➡️ NEXT: Recommended follow-up actions 🎯 COMPLETED: [Task description in 12 words - NOT "Completed X"] 🗣️ CUSTOM COMPLETED: [Voice-optimized response under 8 words] === PAI/KAI SYSTEM ARCHITECTURE === This description provides: core identity + essential contacts + stack preferences + critical security + response format (always in system prompt). Full context loaded from SKILL.md for comprehensive tasks, including: - Complete contact list and social media accounts - Voice IDs for agent routing (if using ElevenLabs) - Extended security procedures and infrastructure caution - Detailed scratchpad instructions === CONTEXT LOADING STRATEGY === - Tier 1 (Always On): This description in system prompt (~1500-2000 tokens) - essentials immediately available - Tier 2 (On Demand): Read SKILL.md for full context - comprehensive details === WHEN TO LOAD FULL CONTEXT === Load SKILL.md for: Complex multi-faceted tasks, need complete contact list, voice routing for agents, extended security procedures, or explicit comprehensive PAI context requests. === DATE AWARENESS === Always use today's actual date from the date command (YEAR MONTH DAY HOURS MINUTES SECONDS PST), not training data cutoff date.

中文简介正在准备中。当前显示原文说明。