Media Claude Skills

Full production pipeline — story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation

Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node — render one branch up to an output, preview-tap latents/masks/preprocessor maps, localize the first bad stage, then fix. Use when a final image/video comes out wrong — artifacts, wrong subject/pose/composition/color, blur, a ControlNet/IPAdapter/mask/LoRA not taking, a two-stage refiner or upscale degrading the result — rather than the run failing with an error (for errors/OOM/missing nodes use the troubleshooting skill).

Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows — primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT instruction-grounded editing — use Qwen-Image-Edit or Flux Kontext for "change X in this photo" edits).

Build Krea 2 Turbo txt2img workflows — native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting

Build Lightricks LTX-2 / LTX-2.3 video workflows — text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models

Curated download URLs and target directories for every model the comfyui-mcp skills reference — checkpoints, VAEs, text encoders, LoRAs — organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL). Use when downloading models with download_model / download_civitai_model, when a workflow fails with a missing-model error, or when setting up a new machine.

Model family compatibility matrix — loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models

Drive the LTX Director (Timeline) node — its Add Image/Text/Audio buttons are DOM-only and cannot be clicked by an agent; edit the hidden timeline_data JSON widget instead. Load when a workflow contains LTXDirector / LTXDirectorGuide / PromptRelayEncodeTimeline, or when asked to add, move, retime, or remove timeline segments (image / text / audio / motion).

Build Qwen Image Edit workflows — model loading, conditioning, LoRAs, prompt patterns, and XY plot testing

Build Qwen Image 2512 text-to-image workflows — QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants

Upscale and restore video in ComfyUI — both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and temporal-aware super-resolution (SeedVR2, the newer FlashVSR) with the downscale-first restore pipeline; RIFE/FILM frame interpolation via the BUILT-IN ComfyUI 0.26 FrameInterpolate (rife_v4.26 in models/frame_interpolation/) or the ComfyUI-Frame-Interpolation pack; 2x/4x scaling, VRAM tiers, VHS encode. Captures the classic downscale→SeedVR2→RIFE recipe and the current 2026 recommendation.

Common ComfyUI errors and fixes — OOM, missing nodes, dtype mismatches, black images, and debugging strategies

Extend / continue a video temporally with Pusa 2.2 in ComfyUI — temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, gotchas, and the extend→upscale handoff.

Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs) — Windows-first (triton-windows + woct0rdho prebuilt SageAttention wheels matched to torch/CUDA/python into the RIGHT python), plus Linux (official triton + build) and Mac (N/A → sdpa/MPS). Critically also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed (video-extend TRAP 5). Use when a loader crashes with "No module named 'sageattention'" / "triton: unavailable", when asked to speed up Wan/video workflows, or when deciding whether to install acceleration vs. fall back.

Build WAN 2.2 First-Last-Frame video workflows — native dual hi-lo (required), and WanVideoWrapper VACE approaches

SCAIL-2 in-video character replacement on WAN 2.1 — WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls

Build WAN MultiTalk audio-driven talking-avatar / lip-sync video workflows — MeiGen-AI MultiTalk on WAN 2.1 14B I2V via kijai WanVideoWrapper (portrait + audio → lip-synced video)

Build WAN 2.2 Text-to-Video workflows — dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass

Lay out and organize a ComfyUI workflow cleanly on the live panel canvas — dependency-layered node placement with no overlaps, subgraphs, colored group boxes, and subgraph rail alignment. Use when asked to tidy / clean up / organize / arrange a workflow, add groups or subgraphs, fix overlapping nodes, or build a workflow that should look good from the start.

Build Z-Image txt2img workflows — RedCraft checkpoint, Z-Image Turbo/Base LoRAs, ControlNet, and sampler presets

Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).

Repurpose existing content into a native LinkedIn post. Take a tweet, thread, YouTube video, blog, or newsletter and rebuild it for LinkedIn: re-hook before the fold, expand to the 900 to 1300 char sweet spot, add whitespace and a CTA, move links to the first comment, run the humanizer, publish via Publora on approval. Not for writing from scratch (use linkedin-post-writer), not for auditing a draft (use linkedin-humanizer --mode audit).

Audit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL, recommendations. Triggers on "review my profile", "rewrite my headline", "fix my About", "optimize banner", "profile audit", "LinkedIn bio". Converts resume-style profiles to ones that convert 3-5x better.

| Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.

公众号运营｜微信公众号｜公众号一条龙｜公众号全流程｜自媒体运营｜wechat automation｜content pipeline｜AIGC workflow — 公众号一条龙运营总控入口，选题→写稿→审稿→排版→配图→发布串联 8 个子 skill，单条指令完成整篇图文从 0 到上架。面向公众号小编、自媒体、品牌内容。触发词分层：**一条龙流程**「一条龙」「完整流程」「从头做」「从 0 到发布」；**新做新发**「帮我写篇公众号文章」「做一篇公众号文章」「我想发一篇」「帮我发一篇」「再来一篇」；**选题起点**「今天写什么好」「有什么好写的」「找个话题」「爆款选题」「热点选题」「起个爆款标题」；**策划起点**「内容日历」「系列策划」「专栏规划」「连载」；**流程恢复**「接着上次那篇」「继续昨天的」「继续上次的」「接着之前的进度」；**显式模型新写**「用 GPT 写一篇」「用 DeepSeek 写一篇」「把提纲写成文章」。子 skill（topics/writing/review/formatting/images/publish/sticker/assets）单独触发仅限对**已有产物**的修改场景（如"改标题""润色这段""排版""审稿""加封面""发布"）；新做/策划/多环节串联一律走本入口。

公众号素材｜业务资料库｜预设包｜.aws 预设包｜主题包｜品牌包｜aiworkskills.cn — 用户业务资料库与预设包管理：业务资料按产品名组织在 `.aws-article/products/{产品名}/`（介绍 .md 直挂产品根 + 配图归 `images/` 子目录含同名说明 .md），AI 与用户对话产出业务介绍内容时引导用户保存；图片入库走 `product_image_ingest.py --product <产品名> --stem <中文名>`。导入 .aws ZIP 预设包（本地文件或 `https://aiworkskills.cn/**/*.aws` URL）合并主题/配色/字体配置到 `.aws-article/presets/`；`config.yaml` 仅本地不存在时从包内复制，已存在则 stdout 输出差异 JSON 不覆盖。面向内容运营、品牌团队、设计支持岗。触发词：「素材库入库」「stock images」「上传图到素材库」「.aws」「预设包」「导入预设」「主题包」「aiworkskills.cn 链接」「.aws 下载地址」。

公众号封面｜公众号配图｜公众号插图｜AI 生图 — 公众号 AI 封面与配图生成，按文章标题与内容自动匹配画风，一稿多方案，多风格预设可复用。面向公众号编辑、自媒体、品牌设计。触发词：「封面」「配图」「插图」「生成图片」「给文章加图」「做个封面」「文章插图」「配个图」。不写正文只发一组图请走 aws-wechat-sticker；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。

公众号贴图｜九宫格｜多图推送｜图片消息｜表情包 — 贴图与多图推送：从创意构思、AI 生图到公众号图片消息发布全流程，含九宫格自动排布、多图压缩、组图打包。面向公众号运营、自媒体、IP 账号。触发词：「贴图」「多图推送」「发组图」「图片消息」「九宫格」「做一组图」「图片帖子」「发几张图」「不写正文发图」「只发图不写字」。是文章内配图/封面请走 aws-wechat-article-images；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。

独立校验与审查文件系统短剧项目中的故事、剧本、资产、连续性、资产图片提示词、分镜、关键帧和视频提示词。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”“审查或诊断模板感”，或判断一集能否交付文本或 JSON 时使用；只发布审查问题、审查结论和修订要求，不代替负责人修改来源文件。

为已接受的短剧镜头和关键帧编写或修改可复制的通用视频提示词与运动规格。用户提到视频提示词、文生视频、图生视频动作、人物表演过程、运镜、对白口型、环境运动、镜头时长、起止状态或把分镜转成视频提示词时直接使用；只描述单个已编镜头内的运动、表演、摄影与声音，不生成视频，不调用模型或供应商接口，也不改写分镜边界。

从短剧剧本拆解并统筹角色/造型、场景/视图、道具/状态和跨场连续性。用户说‘拆角色/场景/道具’、‘做资产表/角色表/场景表/道具表’、‘判断复用还是新变体’、‘更新造型/道具状态’，或拿现成剧本直接做视觉资产准备时使用；本 skill 不写资产图提示词，也不生成图片或视频。

为已确认的短剧角色、造型、场景、视角、道具和状态编写或修改可复制的通用资产图片提示词。用户提到角色设定图、三视图、人物参考图、场景设定图、场景空镜、场景板、道具图、造型或状态变体、局部编辑提示词，或要求用自然语言修改现有图片提示词时直接使用；只产出结构化规格与 Markdown 文本，不生成图片，也不调用模型或供应商接口。

Use this skill to fix scroll jank, lost item state, and broken animateItem() animations in LazyColumn, LazyRow, LazyVerticalGrid, and LazyHorizontalGrid. Covers stable item keys, contentType for mixed-type feeds, Modifier.animateItem() requirements, hoisting modifier chains and painters out of the items lambda, and validating item composable stability. Use when the developer mentions LazyColumn jank, dropped frames while scrolling, items losing scroll state on insert/remove/reorder, mixed feeds of cards/headers/ads feeling sluggish, animateItem() not animating, RecyclerView view-type analog, key parameter, or contentType parameter. The prefetch-window tuning lives in a sibling skill.

Use this skill to push frequently-changing Jetpack Compose state reads (scroll position, animation values, drag offsets) out of the Composition phase and down into Layout or Draw using lambda-based modifiers like Modifier.offset { }, Modifier.layout { }, Modifier.graphicsLayer { }, Modifier.drawBehind { }, and Modifier.drawWithCache { }. Covers the three-phase model (Composition, Layout, Draw), why a state read at phase N invalidates phase N and every phase below, the modifier-phase cheat sheet, and lambda providers (() -> T) for hoisting hot values across composables. Use when the developer mentions every-frame work, scroll jank, animation jank, dropped frames, animated alpha or offset, "the whole subtree recomposes on scroll", Modifier.alpha(state.value), Modifier.offset(x.dp), or graphicsLayer.

Speak the last response aloud using text-to-speech

Stop any currently playing text-to-speech audio

Enable auto TTS for this session

Disable auto TTS for this session

Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Same endpoint as plain STT but with analytics params. Covers both REST (`client.listen.v1.media.transcribe_url`/`transcribe_file`) and the WSS-supported subset (`client.listen.v1.connect`). Use `deepgram-python-speech-to-text` for plain transcription, `deepgram-python-text-intelligence` for analytics on already-transcribed text. Triggers include "diarize", "summarize audio", "sentiment from audio", "redact PII", "topic detection audio", "audio intelligence", "detect language audio".

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.connect()`, `AgentV1Settings`, `send_settings`, `send_media`, event handling, and function/tool calling. Full-duplex STT + LLM + TTS with barge-in. Use `deepgram-python-text-to-speech` for one-way synthesis, `deepgram-python-speech-to-text` / `deepgram-python-conversational-stt` for transcription only. Triggers include "voice agent", "agent converse", "full duplex", "interactive assistant", "barge-in", "agent.v1", "function calling", "AgentV1Settings".

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST (`client.speak.v1.audio.generate`) and streaming WebSocket (`client.speak.v1.connect`). Also covers the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly before synthesis. Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in. Triggers include "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder".

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.connect(...)`, Flux models, end-of-turn detection. Use `deepgram-python-speech-to-text` for standard v1 ASR, `deepgram-python-voice-agent` for full-duplex interactive assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", "listen.v2", "flux-general-en", "flux-general-multi".

> Generate and improve accessible alt text for data visualizations and images in R packages and Quarto documents. Use when the user wants to add, improve, or audit alt text for figures in a pkgdown site or .qmd files. Activate for requests that mention fig-alt, fig.alt, figure descriptions, or alt text in the context of an R package or Quarto document.

Expert patterns for 2D animation in Godot using AnimatedSprite2D and skeletal cutout rigs. Use when implementing sprite frame animations, procedural animation (squash/stretch), cutout bone hierarchies, or frame-perfect timing systems. Trigger keywords: AnimatedSprite2D, SpriteFrames, animation_finished, animation_looped, frame_changed, frame_progress, set_frame_and_progress, cutout animation, skeletal 2D, Bone2D, procedural animation, animation state machine, advance(0).

Expert patterns for AnimationTree including StateMachine transitions, BlendSpace2D for directional movement, BlendTree for layered animations, root motion, transition conditions, advance expressions, and state machine sub-states. Use for complex character animation systems with movement blending and state management. Trigger keywords: AnimationTree, AnimationNodeStateMachine, BlendSpace2D, BlendSpace1D, BlendTree, transition_request, blend_position, advance_expression, AnimationNodeAdd2, AnimationNodeBlend2, root_motion.

Expert patterns for Godot audio including AudioStreamPlayer variants (2D positional, 3D spatial), AudioBus mixing architecture, dynamic effects (reverb, EQ,compression), audio pooling for performance, music transitions (crossfade, bpm-sync), and procedural audio generation. Use for music systems, sound effects, spatial audio, or audio-reactive gameplay. Trigger keywords: AudioStreamPlayer, AudioStreamPlayer2D, AudioStreamPlayer3D, AudioBus, AudioServer, AudioEffect, music_crossfade, audio_pool, positional_audio, reverb, bus_volume.

Expert patterns for AnimationPlayer including track types (Value, Method, Audio, Bezier), root motion extraction, animation callbacks, procedural animation generation, call mode optimization, and RESET tracks. Use for timeline-based animations, cutscenes, or UI transitions. Trigger keywords: AnimationPlayer, Animation, track_insert_key, root_motion, animation_finished, RESET_track, call_mode, animation_set_next, queue, blend_times.