Video & Animation

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

>

>

Turn a speech-led video into two complete story edits based on a retained viral reference. Transcribe with local Whisper, present two full text flows for user approval, then edit and export both in CapCut. Use for 爆紅格式、兩個 flow、先審文字再剪片, especially Cantonese personal-brand videos.

YouTube Shorts / TikTok AI video skill

AI Video Studio — Generate and assemble AI video assets with Seedance 2.0, Fish Audio, FFmpeg, CapCut/Jianying drafts, multilingual storyboards, and the scenario-based `drama` pipeline. Use when the user explicitly requests Seedance generation, AI B-roll, short drama, Fish Audio TTS, CapCut/Jianying drafts, multilingual AI variants, or names AI Video Studio. Route general multi-stage video work through video-production-orchestrator, real-footage editing through video-use, and cinematic product/UI films through video-shotcraft.

Audience simulation for short-form clips

AI short video production pipeline

Faceless frozen-diorama AI videos

Remove the background from an image with OpenClip and get back a transparent PNG. FREE with just an OpenClip account, no subscription. Use when asked to

Regroup CapCut template-backed caption word timing metadata and remove filler tokens in CapCut desktop draft JSON. Use when Chinese subtitles, auto-scrolling captions, karaoke/highlight templates, or word-by-word effects split real words apart, show character-level chunks, or need filler words like 呃 removed while preserving compact text-template tracks.

Assign a delivering persona and an independent physical scene to a

Fill a UGC ad-generation template with product/persona/scene variables

Generate platform-native search phrases for sourcing TikTok/UGC visual

Split a TikTok/UGC voiceover script (English or Spanish plain text)