Explore

Use when a video needs its spoken words on screen through Scenario via MCP: burned-in styled captions for a TikTok, Reels, or Shorts cut, ad captions for sound-off feeds, YouTube subtitles, an SRT sidecar, transcription of a clip's audio, captions translated into another language, karaoke or word-by-word styles, or restyling and correcting an existing transcript. Keywords: captions, subtitles, SRT, transcribe, karaoke, word-by-word, burn in, closed captions, translate video, caption style.

Use when building a visual identity or brand kit with Scenario: a logo, wordmark, or icon as editable SVG, a color palette and typography spec, logo variants (mono, reversed, favicon), and brand applications like social templates, avatars, banners, or merchandise mockups. Also for a rebrand or refreshing an existing mark. Keywords: brandkit, brand kit, visual identity, logo, monogram, wordmark, SVG, vectorize, color palette, typography, brand guidelines, brand board, launch kit.

Use when generating or handling audio on Scenario via MCP. Triggers include music tracks, full-length songs with vocals written from lyrics, background scores, soundtracks, game sound effects, SFX, foley, ambience, looping audio, voiceover, narration, speech, TTS, text-to-speech, dialogue, voice cloning, re-voicing a recording, scoring or adding sound to a video, transcription, or requests to create, wait on, play, or download audio files (MP3, WAV) with Scenario tools.

Use when finished Scenario assets have to give something back: a caption for a dataset or alt text, a reusable style description, a verdict against a brief, a canny, depth, pose, or segmentation control map for the next model, or the asset itself found again by text, tags, or visual similarity and filed into a collection. Keywords: caption, describe, analyze, QA, control map, find similar, reverse image search, semantic search, tag, collection.

Use when making multiple independent ad or campaign edits from existing footage with Scenario: hook, CTA, copy, end-card, placement, or targeted visual variants. Also for revising one variant or resuming a partially completed batch. Not for a new commercial from a still image, ordinary single-clip grading, or automatic Cartesian combinations.

Use when creating or editing music with ACE-Step models on Scenario via MCP: text-to-music songs with sung vocals from a lyric sheet, instrumental tracks, covering or restyling an existing song, repainting one section in place, changing sung lyrics, adding an instrument layer, completing a partial recording into a full arrangement, extracting stems, or choosing between Turbo and Quality lanes. Keywords: ACE-Step 1.5, cover strength, repaint, Vocal2BGM, stem separation, karaoke, BPM.

Use when generating navigable 3D worlds or Gaussian splat scenes on Scenario via MCP: text-to-world, image-to-world, a 360 panorama or skybox turned into a walkable splat, multi-view photos or a video walkthrough reconstructed as a splat, or one object photo to splat. Keywords: World Labs Marble 1.1, 1.1 Plus, 1.0 Draft, Hunyuan World, HY World, image-to-skybox, skybox-to-splat, multiview-to-splat, TripoSplat, gaussian splatting, 3DGS, spz, world generation, explorable scene, VR.

Use when generating or handling 3D assets through the Scenario MCP server, including text-to-3D or image-to-3D meshes, GPT-6 Astra 3D or Claude Opus 5.5 3D, GLB, FBX, OBJ, STL, or VOX files, PBR-textured or game-ready models, voxel models, multi-view reconstruction, editing a mesh by prompt, retexture, remesh, UV unwrap, auto-rigging a biped or quadruped, or retargeting an animation, previewing a mesh in the 3D viewer, or downloading a model for import into Unity, Unreal, Godot, or Blender.

MANDATORY for every coding agent (Claude Code, Codex, or any other) on every change-set — every applicable source file the agent creates or updates MUST start with the project's copyright/authorship header (file overview + exact author line). Use automatically whenever writing a new file or editing an existing one; do not wait to be asked. Covers JS/TS/TSX/CJS/MJS, Python, shell, and CSS. Includes the audit script to verify repo-wide compliance.

Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage reviews, repeated corrections, retries, stuck sessions, false delivery reports and crashes. Never upload private usage data.

Reproduce agent-deck bugs from an issue, transcript excerpt, or description in an isolated environment, and prove fixes with the same reproduction and a regression test. Use for a concrete agent-deck issue or candidate, verifying a fix, preparing a contributor bug-fix PR, or when deck-retro passes a candidate. Broad usage or transcript mining starts with deck-retro; it invokes this skill only after identifying each candidate. Includes a test-first fix loop and evidence-backed reproduced, not reproduced, and fixed verdicts.

Use when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts, approval gates, loops), authoring editor_info, publishing, unpublishing or renaming, importing an exported workflow JSON, migrating a graph built in Weavy, ComfyUI, or another node tool, copying a workflow, or turning a prompt chain into an app. Running or pricing a workflow is scenario-workflows. Keywords: node graph, editor_info, CEL.

Use when text must appear letter-perfect on generated media: taglines, CTAs, prices, legal supers, lower thirds, end cards, nameplates, or styled rich cards composited over Scenario images and video. Keywords: text overlay, text card, caption card, CTA, legal super, tagline, end card, lower third, price card, HUD text, transparent PNG.

Use when animating 2D game art with Scenario: walk, idle or attack cycles in 4 or 8 directions, isometric sprite sheets, animated GIFs, frame-by-frame pixel art animation, VFX loops such as fire or smoke, looping a sprite seamlessly, animating an existing character image, a full animation sheet from one prompt, extracting animation frames from a generated video, or slicing a sprite sheet into engine-ready frames for Unity, Godot, or Unreal. Keywords: spritesheet, keyframes, frame grid, GIF.

Use when making the art for a side-scroller or 2D platformer: side-view pixel-art sprite sheets for a hero and ground enemies (run, walk, idle, attack, hurt cycles, air spin, jump and fall poses) and per-level layers (parallax background and midground, seamless wall texture, platform strip, props). Also use when a magenta key eats part of a sprite, a walk loop will not close, a slash trail keys into a solid block, generated textures do not tile, or poses on one sheet will not split.

Use when turning a song, track, or audio master into a finished music video with Scenario and Seedance: planning shots against beats and sections, transcribing lyrics, generating clips that cut to music, keeping the shots' own sound while the song stays the only score, assembling a delivery over the untouched master soundtrack, or verifying the final cut. Keywords: music video, beat sync, shot list, lyric transcription, reference frames, ffmpeg assembly, Seedance.

Use when retexturing an existing 3D asset with PATINA PBR materials through the Scenario MCP server: a GLB or Blender scene (an image-to-3D result with flat colors, a prop, a diorama) whose surfaces need basecolor, normal, roughness, metalness, and height maps per material family with geometry untouched, or a matched before-and-after comparison film rendered in Blender with one camera path, lighting, and cut. Keywords: PATINA, PBR retexture, material families, Blender EEVEE, comparison video.

Use when a single image of a character, creature, prop, vehicle, or building must be seen from new camera angles through the Scenario MCP server: turnarounds, a 360 orbit, views from behind, above, below, or straight down, consistent multi-angle renders on the same grounded background or on transparency, or novel views that go through a 3D intermediary instead of guessing.

Use when turning a song into a kinetic-typography or motion-design music video, lyric video, visualizer or K-pop style MV with Scenario, landscape or vertical 9:16 for TikTok, Reels and Shorts: a generated subject sheet, style frames and footage, plus a deterministic JavaScript/three.js engine for lyric type, mattes and tracked graphics timed to sung onsets. Also for revising, recutting or cutting teasers from such a video.

Use when a creative task has no direction yet: finding inspiration, exploring looks or styles, proposing concept directions to pick between, building a moodboard or reference board, doing visual research, mining existing assets for a style, or escaping generic AI-looking output. Also when a saved Scenario collection should drive a new batch as art direction. Keywords: inspiration, moodboard, references, art direction, style exploration, concepts, serendipity, ideation, surprise me.

Use when creating game art through Scenario MCP: sprites, sprite sheets, icons, props, loot, tilesets and autotile terrain transitions, seamless tiles, isometric buildings, top-down maps, pixel art, UI buttons and panels, parallax background layers or depth planes for side-scrollers, and character or concept art; or when assets need transparent backgrounds, background removal, style-consistent variation batches, upscaling, pixel-grid cleanup, or PNG export for Unity, Godot, or Unreal.

Use when creating a ChatGPT pet or Codex pet with Scenario: hatching an animated companion from a text idea, a character, mascot or brand cue, or reference photos and art; making the 1536x2288 v2 pet sprite sheet with nine animation states and sixteen look directions, the 1536x1872 v1 sheet ChatGPT web uploads, a pixel-perfect pixel-art pet, an animated GIF of the pet, or a Codex pet.json package.

Use when answering Scenario admin analytics questions about Creative Unit consumption, most-used models, usage by user or project, AI adoption observability, cached usage data, CSV exports, enterprise PDF reports with charts, or a local analytics dashboard. Keywords: usage API, CU, analytics, adoption, reporting, consumption, cache.

Use when building or fixing an Unreal Engine 5 level or open world: World Partition, OFPA, Data Layers, Level Instances, Packed Level Actors, HLOD, landscape size, heightmap import or clipping, edit layers, terrain material rules, foliage and grass, a PCG forest or rock scatter, runtime GPU grass, Nanite and tessellation choices, modular kits, a river or village, streaming pop-in, cells not loading, landscape black spots, "PCG shows nothing in the editor", or a world too heavy to hand to lighting.

Use when a UE5 task involves Niagara or Chaos destruction: a Niagara fireball, projectile trail, impact explosion, muzzle flash, spell, smoke, sparks, debris, Niagara fluids or flipbooks; "Niagara is too expensive", stat NiagaraOverview, Effect Types, pooling, Data Channels, lightweight emitters, VFX scalability; judging an effect's readability, value, color, timing, white blowout or strobing; or a wall that shatters, geometry collection fracture, Dataflow, damage thresholds, floating chunks, debris cost, Chaos Visual Debugger.

Use when importing FBX, USD, OBJ or glTF from Maya, ZBrush or Blender into Unreal Engine 5.8 in bulk or reimporting changed files, writing Editor Python tools, Interchange pipelines or import presets, enforcing naming conventions, assigning material instances by script, setting Nanite, collision and LODs per asset class, writing data validators or automation tests, fixing redirectors, or cooking and packaging from the command line (BuildCookRun, RunUAT, CI, Perforce). Also when a scripted import ignores its settings or names, a Python validator never runs, or a Mac build will not package.

Use when an Unreal Engine 5.8 project misses its frame rate or stutters: "optimize to 60 fps", "we run at 38 fps", CPU or GPU bound, game or render thread too long, hitches, traversal or shader stutter (PSO), GC spikes, camera-cut spikes, Lumen, Nanite, VSM, ray tracing, foliage, crowds or Niagara too expensive, async compute, stat unit, ProfileGPU, Unreal Insights, TraceQuery, snapshothitches, scalability and device profiles, dynamic resolution and TSR, streaming budgets, or proving a fix with before and after captures.

Use when a UE5 task involves materials or textures: a master material and instances for a kit, Substrate or legacy, Blendable vs Adaptive GBuffer, glass, emissive screens, decals, edge wear and dirt, landscape layers and RVT, toon or cel shading, "too many shaders" or shader permutations, static switches, usage flags, texture compression (BC7, normal maps, ORM packing, sRGB), texture memory, or "is this material expensive".

Use when lighting or rendering in Unreal Engine 5.8: physical light units and exposure (EV100, lux, lumens), Lumen GI and reflections, MegaLights, virtual shadow maps, sky, fog and clouds, post process and color grading, the path tracer, or Movie Render Graph stills. Triggers: "Lumen is noisy", "MegaLights noise", "the interior is too dark", "light leaks", neon signs, a night or dusk scene, "fireflies", "path tracer vs Lumen", "render a still", EXR settings.

Use when building or debugging UE5 gameplay: a character with double jump or dash, abilities with cooldowns, enemy AI that patrols, chases and attacks, a health bar or HUD; choosing Blueprint vs C++, GAS or not, StateTree vs Behavior Tree, EQS or Mass; setting up Enhanced Input, Common UI or UMG; replication, RepNotify, save games, World Partition state; "Blueprints are slow", Tick, casts and hard references; "ability won't activate", "enemy ignores the player"; or writing automated gameplay tests with injected input.

Use when an agent drives Unreal Engine 5.8 on a Mac for any task: Editor Python (the unreal module), headless UnrealEditor-Cmd -run=pythonscript jobs, Epic's Unreal MCP server, the Remote Control API, console commands and cvars; when a script breaks on 5.8 (EditorLevelLibrary, Remote Control calls refused, Substrate materials black, MRQ presets); when a level, material, shot or build must be judged by numbers and a screenshot before it is called done; or when a brief must go to the right scenario-unreal-* specialist.

Use when making a trailer, cutscene, cinematic or short film in Unreal Engine 5.8 with Sequencer: shot lists, master and shot sequences, cameras, lenses, depth of field, camera cuts, spawnables, character animation in shots, per-shot lighting, Movie Render Graph or Movie Render Queue EXR renders, "render darker than the viewport", "first frames pop", "last frame missing", ACES or OCIO to DaVinci Resolve, the 180-degree rule, Sequencer Python, or reviewing a cut.

Use when a UE5 task involves characters in motion: "import FBX from Maya" with a skeleton, "retarget animations", IK Rig, IK Retargeter, feet sinking or floating after retarget, mocap cleanup, Motion Matching, Pose Search, Choosers, GASP, state machine vs motion matching, root motion, offset root bone, foot IK, Control Rig, Animation Blueprint cost, "animation is expensive", budget allocator, URO, MetaHuman LODs, ML Deformer, cloth.

Use when building a Unity 6.3 level or open world: terrain from code or heightmaps, procedural islands, erosion, splat and foliage rules, trees and grass, ProBuilder graybox, level gym, modular kit and prefab placement, set dressing, landmarks and player guidance, the island's edge, spline roads, WFC, fog, additive scene streaming, or a world that hitches, pops in, leaks memory or runs slow on mobile. Keywords: Terrain, TerrainData, ProBuilder, blockout, graybox, modular kit, NavMesh, LoadSceneAsync, open world.

Use when a Unity 6.3 game must run in a browser: 'export to WebGL', Web build settings or Build Profiles, gzip or Brotli, Decompression Fallback, server headers, 'Unable to parse .framework.js.br', build too big or slow to load, itch.io, CrazyGames or Poki limits, Addressables or AssetBundles on the Web, 'Could not produce class with ID', Task.Run freezing the browser, WebGL 2 vs WebGPU, .jslib and SendMessage interop, a page text field that gets no keystrokes, mobile browsers crashing, HTTPS for sensors, hosting and rollout.

Install and configure shadcn/ui components for React projects. Guides component selection, installation order, dependency management, customisation with semantic tokens, and common UI recipes (forms, data tables, navigation, modals). Use after tailwind-theme-builder has set up the theme infrastructure, when adding components, building forms, creating data tables, or setting up navigation.

React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React components. Triggers: 'react patterns', 'react review', 'react performance', 'optimise components', 'react best practices', 'composition patterns', 'why is it slow', 'reduce re-renders', 'fix waterfall'.

Generate a complete, deployable landing page from a brief. Produces a single self-contained HTML file with Tailwind CSS (via CDN), responsive design, dark mode, semantic HTML, and OG meta tags. Sections: hero with CTA, features, social proof, pricing (optional), FAQ, footer. Use when building a marketing page, product launch page, coming soon page, or any standalone landing page. Triggers: 'landing page', 'create a page', 'marketing page', 'launch page', 'coming soon page', 'one-page site'.

Extract a complete design system from an existing website or screenshot into a DESIGN.md file. Analyses colours, typography, component styles, spacing, and atmosphere through browser automation and HTML inspection. Produces a semantic design system document optimised for consistent page generation. Triggers: 'extract design system', 'design system', 'create DESIGN.md', 'analyse the design', 'what design does this site use', 'extract styles from', 'reverse engineer the design'.

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.

Exhaustively extract UX patterns from a reference web app. Walks every screen, captures screenshots of every state, records interaction patterns, copy verbatim, keyboard shortcuts, responsive treatments, motion, and empty/error/loading states. Produces a reusable pattern library that other audits can compare against. The inverse of ux-audit — asks 'what is the bar?' rather than 'does this match the bar?'. Trigger with 'learn from X', 'extract patterns from X', 'study X's UX', 'reverse engineer the UX of X', 'build a pattern library from X'.

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the multi-pane stress matrix, visual polish sweep, component perfection checklist, automated a11y (axe-core), pragmatic performance budget (LCP/CLS/INP), scenario battery (11 scenarios), and stress recipes including the real-flavour data battery. Hard gates: console errors/warnings = 0, network 5xx = 0, layout collapse = 0, axe Critical/Serious = 0, perf budget green. Audit-the-audit meta-check rejects rushed reports. Each finding has reproduction steps, evidence path, and suspected code location. Trigger with 'ux audit', 'walkthrough', 'qa sweep', 'audit the app', 'dogfood this', 'check all pages', 'find what's broken', 'stress the UI'.

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.

Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.

Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'. Not for cited fact-checking research reports (a separate harness does those); this is pre-build product discovery.

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.

Generate complete user documentation for a web app with screenshots. Browses the app via browser automation, screenshots every screen, and produces a structured user guide with step-by-step instructions, annotated screenshots, workflow diagrams, and reference tables. Supports quick (key screens), standard (all pages), thorough (every state and flow), and exhaustive (publishable documentation suite). Triggers: 'document the app', 'user guide', 'app documentation', 'screenshot docs', 'generate user docs', 'help docs', 'how-to guide', 'write the docs'.

帮用户接入/配置 MCP（Model Context Protocol）服务。当用户说「帮我接 MCP」「连上某个服务的 MCP」「配置 Model Context Protocol」「加个工具服务器」「为什么 MCP 连不上」等时使用。按服务官方文档把配置写进 pi 的 mcp.json，并用 pi mcp list 验证连接，全程不破坏用户已有配置。

生成图片。当用户想让 AI 生成图片、插画、海报、头像等图像内容时使用。读取生图供应商配置，调用 OpenAI 兼容的图片生成 API（支持 OpenAI、火山方舟、SiliconFlow 三种方言与参考图），把生成的图片保存到项目目录。

Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing. Use when the user asks to cut model costs or latency, says the big model handles everything, or wants a triage / routing / filter layer in front of an agent. Analysis plus an optional baseline scaffold. Do NOT use for auditing context layout (context-audit) or for building eval suites (evals-bootstrap).

Prepare arcade-mcp changes for review by verifying intended behavior, filling the repository PR template, and creating or updating the PR. Use for "open a PR", "get this reviewed", or "make this PR ready". Resume existing work. PR preparation is separate from releasing; use a code-review skill for review-only requests.

Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking credits or quota, hitting Scenario auth, scope, or Forbidden errors, or setting up mcp.scenario.com in Claude Code, Cursor, VSCode, or another agent.

Share Claude Code sessions between developers. Use when user mentions "share session", "export session", "import session", "send session to", "continue from colleague", or needs to (1) export current session to file, (2) import session from another developer, (3) hand off work context. Enables private, secure session transfer via direct file sharing.

Use when explicitly asked to run a live or plan-only application test for a published Scenario skill.

Use when explicitly asked to handle a pull request in the Scenario skills repository, including review comments and skill validation.

Generate one short Conventional Commits squash message describing only the net diff between the PR's base and head, set its header as the PR title, validate it with the repository's commitlint and both copy its description to the clipboard and display it, when asked for a squash message. Works in any Scenario repository, whatever its default branch.

Handle review comments received on GitHub for the current branch's PR or a given PR number or URL, by triaging each unresolved thread, fixing what is warranted, pushing, and replying in each thread, when asked to address, fix or answer PR comments. Works in any Scenario repository.

Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a Figma design turned into code — e.g. 'code this design', 'implement this frame', 'build this screen/component', 'turn this Figma into React/Vue', 'convert this design to code' — or whenever a Figma URL or the current Figma selection appears alongside a coding request. Works for full screens, single sections, or one component.

Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g. 'build this in Figma', 'create a Figma design for this', 'push this component/screen to Figma', 'turn this React/Vue into a Figma design', 'recreate this UI in Figma', 'make a Figma version of …', 'design a landing page/screen in Figma' — or whenever a coding artifact (a component, page, or spec) appears alongside a request to author in a connected Figma file. Works for full screens, sections, single components, or design-system assets.

Upgrade @modelcontextprotocol/server (the MCP TypeScript SDK v2) and prove the wire contract survived. The SDK is a runtime dependency whose breakage lands on the wire, not in the type checker — so this sorts each release by which SDK source files it touched (Figwright uses only the server + stdio slice of a client/server/multi-runtime package family), then diffs what a real MCP client observes — negotiated protocol version, every tool JSON Schema, annotations, prompts — before and after the bump. Use whenever the user wants @modelcontextprotocol/server or the other @modelcontextprotocol/* packages updated or audited, asks what a new SDK version changes for the server or its clients, or lands on a Renovate bump PR for that package.