Video & Animation

Edit and convert images with the ImageMagick `magick` CLI — resize, crop, convert format, compress, rotate, montage, annotate. Use for any still-image transformation.

Chinese-platform last-30-days research skill covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao. Includes Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output.

抖音/快手短视频脚本 - 前3秒hook、脚本结构、热门音乐建议、话题标签策略

Use when the user wants to check, fix, or verify Prisma Cloud vulnerability scan results for the Taurus Docker image (blazemeter/taurus:unstable). Run this skill on Opus 5 (1M context) or newer — choosing and applying the correct CVE fix requires strong reasoning.

从 Markdown 文件或网页链接提取文章并发布到微信公众号。适用于需要“自动创建草稿/提交发布”、统一微信样式（standard/viral）和批量复用发布流程的场景。

Agent/AI 产品宣传片的创意导演层：先锁产品主角、观众信念变化与影片格式，再把不可见的 Agent 协作翻译成可拍的故事、镜头、运动、声音和 provenance contract。Use when: 用户问 Agent 产品宣传片 如何导演/剪辑/叙事/配声音、要拆参考片、写 creative brief/beat sheet，或 video-forge 开机前仍未锁定 主语与镜头语法。Not for: brief 已冻结后的录制/TTS/对齐/渲染（用 video-forge）、教程/功能 walkthrough、 纯动画生产（用 anime-forge）、只找时效性竞品（先用 deep-research）。Output: product-hero sentence + audience belief change + format decision + claim/proof beat sheet + shot/motion/sound maps + provenance ledger + operator acceptance questions。GOTCHA: 用户举的

Use when the user asks to "design our change narrative", "build the old-world-to-new-game story arc", or "frame the shift our category is undergoing"; produces a Raskin-style strategic narrative arc — old world → the undeniable shift → winners vs losers under the new rules → the promised land → proof the promised land is real — derived from the positioning truth set and the belief/objection map, feeding the TALE Architecture arc sub-item. Every proof beat is labeled Measured / User-provided / [n

Evaluate extracted personas against their source profiles with the canonical EXTRACTION_QUALITY_RUBRIC.md. Use when asked to check persona quality, score Stack Overflow/Wikipedia/Amazon persona extractions, run M1-M7 validation, compare LLM judges, or perform parallel multi-model persona review. Reviews exactly one persona per judge task and supports GPT-5.6 Sol, Claude Opus 4.8, Gemini 3.5 Flash, MAI-Code-1-Flash, and other capable models.

Collect Douyin competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, hook, format, audience-language, or creator research that needs reproducible raw evidence and a documented selection method.

PR review-and-update cycle — the orchestrator that takes a PR from review to resolved. It runs a local review (by delegating to the `pr-review` skill), fetches open GitHub review comments, evaluates all findings, applies valid fixes, runs CI, commits, pushes, resolves threads, and re-requests Copilot review. Supports three modes — `full` (default, everything), `local` (only the local-review-and-fix loop; no GitHub PR-conversation reads or mutations), and `remote` (only the GitHub PR feedback loo

Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nightly deep dive. Uses Opus 4.6 as the auditor model.

Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on "Team Coordinate ".

Use when you need a NEW or optimized MPK CUDA kernel (a per-task `.cuh` under include/mirage/persistent_kernel/tasks/) that must PROVABLY beat a target WITHOUT the kernel-optimizer cheating its own correctness test. This is the frozen-gate Ferret system — a 3-agent orchestration (dispatcher → independent test-writer → optimizer) that makes "the optimizer ships a simplified-math kernel and self-reports a passing test" structurally impossible. Triggers — phrasings like "dispatch ferret to optimize

One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.

Guia para afinar o prompt de um agente de IA do DeskcommCRM que não está performando — como um engenheiro de prompt sênior de atendimento e vendas, com dados da operação, não achismo. Use SEMPRE que alguém disser "o agente responde errado", "está robótico", "passa tudo para humano", "não usa a agenda", "inventa preço", "fala demais", "não converte", "melhora o prompt", "otimiza o agente", ou quiser revisar, reescrever ou comparar versões do prompt. Diagnostica pelas execuções, vetos e custos, pr

在装有匹配版本剪映的 Apple Silicon Mac 上，无界面生成可编辑草稿、修改已有多轨草稿的独立副本，或按明确要求导出原生 MP4。需要另行检出 Jianying Headless 核心项目；纯转写不使用本 Skill。

A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

Continual learning infra for self-improving agents

Cross-platform local MCP capabilities for ChatGPT with Chrome integration, Goal, Compact & Resume, and durable multi-agent workflows.

开放的侧边栏底座，支持三方拓展注册新侧边栏页面。内置文件渲染编辑/终端/侧边对话/Git/子代理页面 ｜ Open sidebar foundation, supports third-party extensions to register new sidebar pages. Built-in file rendering/editing, terminal, side chat, Git, and sub-agent pages.

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

Dispatch stateless coding agents through Claude Code or Codex. Model catalog checked 2026-08-25: Claude Code includes Sonnet 5, Opus 5, and Fable 5; Codex includes GPT-5.6 Luna, Terra, and Sol. Use when you're stuck, need a second opinion, or need parallel research on a hard problem. They have no memory, so you must provide all context.

Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI, or when a UI change involves motion or a sequence of steps.