Intelli Verse X Skills

Multi-source account research and lead pipeline: scrape, enrich, verify, dedupe. Use for lead dossiers, account research, or cascade enrichment.

Generate developer documentation, API docs, and technical specifications. Use when writing docs, generating docstrings, or creating API references.

Skill for designing and using feature stores in ML pipelines. Use when sharing features across models, ensuring consistency between training and serving.

Design, optimize, and evaluate LLM prompts for content generation and agent behavior. Use when creating prompt templates, optimizing existing prompts, or building prompt registries.

Sid Orchestra — multi-agent swarm with run IDs, lock leases, plan critic, canary harness, PASS/FAIL evals, and anti-hallucination gates. Use when the user says sid orchestra, @sid-orchestra, sid swarm, sid evals, or wants research→plan→build→review with a communication bus and loop.

Create visual storyboards and scene plans for AI-generated content. Use when planning creative campaigns, designing narrative flow, or structuring video content.

Shared long-term memory for IntelliVerse-X agents and Cursor sessions, backed by the "hindsight" MCP server. Stores root causes, gotchas, decisions, and process rules learned once so they never have to be re-explained or re-discovered. Use PROACTIVELY at the start of any non-trivial task (bug investigation, "why is X happening", error triage, unfamiliar area of a repo, or anything that smells like "we've probably hit this before") by calling recall BEFORE reading the repo from scratch or asking the user to restate context. Also use after solving something non-obvious to write the lesson back with retain/sync_retain, and applies across every workspace (QuizVerse Unity, Quizverse-web-frontend, Intelliverse-X-AI, nakama, intelli-verse-kube-infra).

Comprehensive EKS operational review for the IntelliVerse production cluster. Triggers on requests like "review our cluster", "EKS audit", "best practices check", "cluster health", "security review", "upgrade readiness", or "cost optimization". Uses the upstream eks-operation-review skill as a base, with IntelliVerse-specific context layered on top.

The "Make content" MCP tiles — Google Stitch UI design, QR Studio codes & landing pages, OpenSEO keyword research, and Firecrawl web scraping. Use when creating design mockups, QR campaigns, SEO research, or scraping the web for source material.

Use when implementing Disney's 12 animation principles with Framer Motion in React applications

Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

Guides users through setting up an ElevenLabs API key for ElevenLabs MCP tools. Use when the user needs to configure an ElevenLabs API key, when ElevenLabs tools fail due to missing API key, or when the user mentions needing access to ElevenLabs. First checks whether ELEVENLABS_API_KEY is already configured and valid, and only runs full setup when needed.

Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.

Create professional videos autonomously using claude-code-video-toolkit — AI voiceovers, image generation, music, talking heads, and Remotion rendering.

Expert in UX psychology, motion design, and microinteraction patterns for QuizVerse. Grounds every design decision in peer-reviewed research: Laws of UX, Apple HIG, NNGroup, and 60fps best-in-class mobile patterns. Use when "UX, feel, delight, polish, feedback, animation timing, microinteraction, psychology, engagement, reward, streak, confetti, transition, splash, loading, button feel" is mentioned.

Run autonomous marketing A/B experiments with hypotheses, bootstrap CI, Mann-Whitney scoring, weekly scorecards, and pacing alerts. Use for growth experiments, channel tests, playbook promotion, or weekly marketing scorecards.

Backend person pack for Content Factory. Use when the user says person backend, @person-backend, backend person, FastAPI person, or API engineer person. Auto-loads senior-backend-engineer, api-architect, database-architect personas plus api-design, contentx-pipeline-dev, testing, security-review skills.

Easy person packs for Content Factory personas. Use when the user says person pack, persona router, person backend, person frontend, person unity, which persona, or asks for backend/frontend/Unity/devops/creative/ML/product person. Maps one person type to the right .cursor/agents persona plus required skills, then auto-loads them.

Trigger a Content Factory pipeline run via the public API, capture the task_id, then immediately post an operator kanban card on the `content-factory` board so a `ivx/cf-pipeline-operator` worker drives it to completion. Use one dispatcher card per pipeline-kind per trigger (cron / webhook / manual).

Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.

LiteLLM AI gateway operations for IntelliVerse. Use when managing LLM models, updating model routing, checking model availability, investigating AI inference failures, adjusting Qwen/Kimi/Claude/vLLM configurations, or monitoring LLM costs via Langfuse.

Schedule and analyze social-media posts (Instagram, X, LinkedIn, TikTok) through the Postiz wrapper MCP — list channels, find free slots, create/schedule posts, pull analytics. Use for any "post this / what's scheduled / how did the post do" request.

Official Kling direct API guidance for OpenMontage providers. Use before calling `kling_official_video`, `kling_official_image`, `kling_tts`, `kling_avatar`, or `kling_lip_sync`.

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.

Generate speech audio from text using HeyGen's Starfish TTS model. Use when: (1) Generating standalone speech audio files from text, (2) Converting text to speech with voice selection, speed, and pitch control, (3) Creating audio for voiceovers, narration, or podcasts, (4) Working with HeyGen's /v1/audio endpoints, (5) Listing available TTS voices by language or gender.

Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.

This skill should be used when the user asks to validate, reindex, repair registries, check links, check continuity, count words, summarize a story project, import an existing manuscript, export a manuscript, run the story CLI, or perform deterministic maintenance on a Story Skills markdown project.

CRO audit any landing page and turn survey data into lead magnets. Use for conversion rate optimization, landing page scoring, or survey-to-lead-magnet.

Generate professional slide decks with AI images and style presets. Use for pitch decks, presentations, or Google Slides assembly.

Turn anonymous website visitors into qualified pipeline: RB2B routing, deal resurrection, trigger prospecting, and ICP learning from win/loss. Use for visitor-to-pipeline, dead deal revive, or ICP optimization.

Value-based pricing playbook: pre-call briefings, tiered packages, call analysis, pattern library. Use to upsell deals, prep pricing calls, or train sales on value pricing.

Skill for managing dataset versioning and lineage in ML workflows. Use when tracking dataset changes, reproducing experiments, or sharing data artifacts.

Design resilient systems that gracefully handle failures. Use when building retry logic, circuit breakers, fallback mechanisms, or disaster recovery plans.

ContentX Growth Calendar — plan the Mon–Sun content week from today for QuizVerse, Redlight, Last to Live, and IntelliVerse games. Use when the user says @cf-growth-calendar, @cf-content-calendar, content calendar, week plan, growth calendar, or multi-brand launch ladder (comic→anime→game).

Pick and change Content Factory LLM / image / video / music models safely. Use whenever the user asks which model a pipeline uses, which file to edit for chat/image/video defaults, SiliconFlow vs self-hosted, LiteLLM routing, vision judges, FLUX, Wan 2.2, ACE-Step, Qwen3-30B, DeepSeek V4 Pro, dead providers (OpenRouter/PiAPI/Kling), invalid model IDs, PREFER_SELFHOSTED, or anything in docs/LLM_MODEL_USAGE.md / configs/llm_models.yaml / configs/model_catalog.yaml / configs/pipelines/*.yaml. Prefer this skill over guessing provider SDKs or inventing nicknames that are not in the catalog.

Creative / media person pack for Content Factory. Use when the user says person creative, @person-creative, creative director person, video scientist person, or image person. Auto-loads creative-ai-director, video-generation-scientist, image-generation-scientist, prompt-engineer plus the video-skills pack and cf-creative-marketing.

Easy pipeline skill pack for Content Factory. Use when the user says pipeline skills, @pipeline-skills, new pipeline, ContentX pipeline, or pipeline pack. Auto-loads contentx-pipeline-dev, pipeline-orchestration, cf-llm-model-usage, and contentx-firecrawl-validation.

Audit code and architecture for security vulnerabilities. Use when reviewing code for security issues, designing auth systems, or responding to security incidents.

Create Cursor hooks. Use when you want to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.

Create Cursor rules for persistent AI guidance. Use when you want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.

Place AI voice calls and manage voice applications, numbers, and trunks on the self-hosted Fonoster deployment via its MCP. Use when the user asks to call someone, list voice apps, or check call status.

Send marketing email and push campaigns and track opens via the Notifuse MCP (workspace intelliversex). Use for newsletters, product announcements, campaign stats, and list management.

Answer "how much money came in" from Stripe — balance, revenue summary with fees/refunds, charges, subscriptions, invoices, payouts, disputes — via the read-only Stripe wrapper MCP. Pair with RevenueCat for mobile IAP revenue.

The "Talk to people" MCP tiles — email campaigns (Notifuse), WhatsApp (OpenBSP), voice calls (Fonoster), social scheduling (Postiz), CRM (Twenty), shared inbox (Chatwoot), newsletters (beehiiv), SMS (Telnyx). Use whenever the user wants to reach customers or leads on any outbound channel.

Personal long-term memory via Mem0 Platform (MCP + CLI). Use PROACTIVELY at the start of non-trivial tasks to search_memories before deep repo exploration, and after resolving non-obvious bugs to add_memory. Complements Hindsight (team ops bank) with user-scoped Mem0 memories. Default user_id: user_30dff4fab4c9. Applies across QuizVerse, web frontend, NestJS backend, and Nakama workspaces.

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

Read-only overnight fraud / risk pulse for QuestX via admin-mcp questx tools. Summarize flags; never ban, refund, or move money without a human.

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management for QuizVerse (Unity 6, Built-in pipeline, mobile).

Router for ericosiu/ai-marketing-skills installed as personal Cursor skills (ams-*). Use when the user says AI marketing skills, ams skills, growth engine, outbound engine, content ops expert panel, SEO ops, sales pipeline, podcast-to-everything, short-form clip pipeline, X longform, YouTube competitive analysis, CRO audit, or asks which Single Grain / Single Brain marketing skill to load.

Design and optimize cold outbound email: ICP, sequences, expert scoring to 90+, infra audit, Instantly-ready campaigns. Use for cold email, outbound sequences, or Instantly campaign design.

Write long-form X posts/threads with founder voice and a 24-pattern AI slop humanizer. Use for X articles, thought leadership threads, or viral founder posts.

Extract clean, LLM-ready markdown from a single known URL using Firecrawl scrape. Handles JS-rendered pages and strips nav/boilerplate so the content can go straight into prompts or artifacts.

Discover pages on the live web by query using Firecrawl search, returning ranked results with titles, URLs, and snippets (optionally full-page content). The entry point for any web task where you don't yet have a URL.

Optimize GPU kernels, memory usage, and inference throughput for ML workloads. Use when profiling GPU code, optimizing CUDA kernels, or designing GPU-efficient models.

Shared IntelliVerse-X long-term memory via Hindsight MCP. Recall before deep repo exploration; sync_retain after non-obvious fixes, decisions, and process rules. Use for content-factory, kube-infra, QuizVerse, Nakama. Triggers: hindsight, team memory, retain, recall, root cause, gotcha, continuous memory save, "we've hit this before".

Content Factory HY-WorldPlay + Fortnite/UEFN map loop. Use when the user says @hyworld, @fortnite-map, make a 3D world / navigable scene / Creative island with RunPod hyworld-weights, or wants WorldPlay trajectories + world_scene pipeline. Enforces research → plan APPROVE → RunPod volume → generate.

Design and execute image generation pipelines using diffusion models. Use when generating images, optimizing image quality, or building image production workflows.

Weekly maintenance pass over the CF prompt_registry, character_identity bank, AND the rolling CF_IMPROVER_ISSUES.csv. Roll up 30-day metrics, score CF across 7 audit dimensions (Intelliverse pattern), propose version promotions, demote regressions, prune unused prompts, reconcile S3 provenance, file beads for HIGH+ severity findings, and publish a weekly digest PR with 30/60/90-day action plan style roll-up.