- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ChatCut-Inc/agent-plugin --skill shader-gen -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ChatCut-Inc/agent-plugin --skill shader-gen -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ChatCut-Inc/agent-plugin --skill shader-gen -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ChatCut-Inc/agent-plugin --skill shader-gen -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/ChatCut-Inc/agent-plugin/tree/HEAD/antigravity/skills/shader-gen來自發布者
If submit_shader or inspect_item are not loaded yet, load them with ToolSearch before calling them, so you use their real parameters instead of guessing.
Submit-only: creates a backend generation job, returns jobId. Use the track_progress tool for job lifecycle after submission.
Always use generate.ts for new shaders. Manual authoring is only for editing existing asset code — never as a fallback when generation fails.
Before generating a shader, call browse_library unless the user names an exact asset id that is already visible in browse_assets.
browse_library is the source of truth for built-in effects, built-in transitions, and project effect/transition assets. Built-ins are stable global asset ids, not per-project DB assets, so they may not appear in browse_assets.
Apply catalog entries with edit_item, do not call submit_shader.
Good catalog searches:
browse_library(query: "zoom")
browse_library(category: "transitions", query: "dissolve")
browse_library(category: "audio-fx")
Generate only when no catalog entry matches the user's intent closely enough.
builtin:zoom uses the same track-bound placement as every effectEffects always have timeline geometry. For a whole-clip effect, pass targetItemId; ChatCut resolves it to a clip-anchored range covering that clip. For an explicit timeline range, pass trackId + trackBoundFrom + trackBoundDurationInFrames.
# Zoom on the entire video clip
edit_item(json: '{"adds":[{"type":"effect","assetId":"builtin:zoom","targetItemId":"<clip-id>","propertyOverrides":{"magnification":1.5,"shape":"hold"}}]}')
# Zoom on a sub-range of the clip (e.g. frames 90–150 only, a punch zoom on a beat)
edit_item(json: '{"adds":[{"type":"effect","assetId":"builtin:zoom","mode":"track-bound","trackId":"<trackId>","trackBoundFrom":90,"trackBoundDurationInFrames":60,"propertyOverrides":{"magnification":2,"shape":"punch"}}]}')
Use preview_timeline({views:["timeline"],tracks:["V1"]}) to obtain track item ids and timeline-frame ranges. Use inspect_item({itemId:"..."}) when exact item detail is needed.
Omit propertyOverrides entirely for default zoom. Send only the keys you want to change — patch semantics.
Effect items have two placements, both with a concrete time range:
targetItemId for the whole clip, or include an explicit range that intersects the clip. The stored range is local to that clip and follows it when it moves.trackId + trackBoundFrom + trackBoundDurationInFrames for a range over empty track space. The range is absolute on the timeline.Use targetItemId for whole-clip effects. Use explicit track geometry only when the requested range differs from a clip's full duration.
edit_item(json: '{"adds":[{"type":"effect","targetItemId":"<clip-id>","assetId":"builtin:slog3-s709","propertyOverrides":{"intensity":1}}]}')
To swap: delete the effect and re-add with a different assetId. To remove: delete the effect item.
User-uploaded .cube LUT assets take this exact same shape — only assetId differs. See "Applying an Existing LUT Asset" below.
Effects and transitions apply to video, image, and gif items.
Before generating anything, check two non-generation paths first:
browse_library for built-in and project effects/transitions..cube LUT asset that already exists in the project library — bind it instead of generating, see "Applying an Existing LUT Asset" below. It shows up in browse_assets as type: effect with a lut-typed entry in editableProperties."LUT-style" in the table means generating a fresh GLSL color grade that resembles a LUT — only when the user wants something new. If they want to apply a .cube file already in the library, don't generate; bind the existing asset instead.
No separate LUT or mask generator for the generation path — those are all effect.
Default target is the timeline. "Apply this LUT" means an edit_item effect on the clip. Only reach for edit_asset sourceLut when the user asks for the source itself everywhere it appears — every clip cut from that asset, or a log-to-Rec.709 normalization of the footage — because that changes every instance of the asset on every timeline.
.cube files uploaded by the user become effect assets with category: "lut". Applying one to a clip is not generation — it is the same edit_item effect shape as a built-in LUT, with that asset's own id as assetId:
edit_item(json: '{"adds":[{"type":"effect","targetItemId":"<clip-id>","assetId":"<lut-effect-asset-id>","propertyOverrides":{"intensity":1}}]}')
Key points:
assetId is the LUT effect asset's real id. There is no literal "lut" assetId, and no LUT binding nested inside propertyOverrides.propertyOverrides carries only intensity (0–1, default 1). The .cube binding lives on the asset, not on the effect item.browse_assets type:"effect": a LUT asset is the one whose editableProperties contain a lut-typed key. Built-in LUTs come from browse_library category:"luts".targetItemType defaults to video; also supports image, gif.assetId. To remove: delete the effect item.edit_asset update with {"sourceLut":{"assetId":"<lut-effect-asset-id>"}} on the video/image/gif asset; {"sourceLut":null} removes it..cube is not in the project yet, you cannot get it in: this surface has no LUT import path, and .cube is not an accepted chat attachment either, so never ask the user to send you the file. Ask them to drag it into the editor's media pool instead — the editor registers it as a LUT asset and it then shows up in browse_assets. Do not tell them ChatCut cannot handle .cube; the editor can.Do not call submit_shader for this path.
After applying, confirm with preview_timeline that the effect is listed on the target clip's track. Do not report success from the edit_item response alone.
Before calling submit_shader, restate the user's intent in one concrete sentence, then proceed immediately. After track_progress returns, state what was produced in one line — do NOT ask "Keep it or regenerate it?".
submit_shader({
type: "effect",
prompt: "Chromatic aberration with RGB split",
name: "Chromatic Aberration",
});
submit_shader({
type: "transition",
prompt: "Smooth crossfade with soft edge",
name: "Crossfade",
});
submit_shader({
type: "effect",
prompt: "Cinematic teal-orange color grade",
});
submit_shader({
type: "effect",
prompt: "Stronger version",
referenceAssetIds: ["effect_asset_id"],
});
track_progress tool for status/wait after submission.Any time you're about to edit shader asset.properties, applied effect/transition item.propertyOverrides, or promote a hardcoded shader value, read references/property-changes.md first.
It reinforces that shader properties is an array, but the allowed shader property types are only number, boolean, color, select, and vec2. Motion Graphic properties are also arrays, but use a different type set.
Returns { success, job: { jobId, status }, manage: { status, wait, watch } }.
Only when user explicitly requests. Refresh the affected timeline with view:"timeline", passing track to narrow the read when appropriate.
edit_item(json: '{"adds":[{"type":"effect","targetItemId":"<id>","assetId":"<id>","enabled":true,"propertyOverrides":{}}]}')
Requires two adjacent same-track endpoints. edit_item validates live seam feasibility and refuses durations that would require freeze frames or overlapping neighboring transitions. If the add fails, retry with the suggested durationInFrames, trim the clips to expose handles, delete/shorten neighboring transitions, or keep a hard cut.
edit_item(json: '{"adds":[{"type":"transition","assetId":"<id>","outgoingItemId":"<id1>","incomingItemId":"<id2>","durationInFrames":30}]}')
When generating via generate.ts, the backend handles validation automatically (transpile, AST security, class structure, retry on failure).
NEVER write shader code from scratch. Always use generate.ts for new shaders. This section is ONLY for modifying existing shader code that was already generated.
When writing shader code manually, read references/design-principles.md first. If the change touches editable properties, also read references/property-changes.md.
Typical workflow:
inspect_asset with the shader assetId and includeCode: true — read the current source.edit_asset with action=update, the same assetId, and the full replacement source inline in json.code. Validation runs automatically on update — if code is invalid, the update is rejected with error details.AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe /
---name: shader-gendescription: AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film…---# antigravity/skills/shader-gen/SKILL.md總覽
AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.
常見問題
從發布者下載 antigravity/skills/shader-gen/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/ChatCut-Inc/agent-plugin。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。