Video & Animation

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

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

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.

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

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 ".

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

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

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.

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

Design, write, or rewrite one practical bilingual bpf-developer-tutorial lesson with pinned Claude Opus 4.5, then verify the public workflow and prose against the implementation. Use when creating README.md and README.zh.md, checking whether a tutorial tool has a realistic CLI and lifecycle, preserving complete kernel source, testing the example, or preparing tutorial changes for review.

Writing, exploit——把原始素材组装成一段节拍旅程，在某个 beat 依赖一个术语之前先把它 grounded。

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

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.

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.

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

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.

🧩 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.

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill，开箱即用。

Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

Continual learning infra for self-improving agents