All authors
Claude Skills by Wanfeng1028
github.com/Wanfeng1028590 skills0 installs0 views
- Shortvideodirector Scriptwriter Fix Script当现有剧本的对白、可拍性、连续性、时长或制作资产清单需要按授权请求或当前 findings 修正时使用。Votes: 0GitHub stars: 5
- Shortvideodirector Scriptwriter Script当故事需要可拍摄剧本、文学改编，或现成剧本需要采用、场景整理与制作资产识别时使用。Votes: 0GitHub stars: 5
- Shortvideodirector Series Video在用户要求开始多集系列、续作下一集或查看系列配置时使用。Votes: 0GitHub stars: 5
- Shortvideodirector Short Video在用户要求开始单集短视频、提供现有故事材料或查看短视频配置时使用。Votes: 0GitHub stars: 5
- Shortvideodirector Simple LeafA simple leaf skill fixtureVotes: 0GitHub stars: 5
- Shortvideodirector Storyboarder Fix Storyboard在已有分镜需要局部修正、连续性排查或可生成性诊断时使用。Votes: 0GitHub stars: 5
- Shortvideodirector Storyboarder Storyboard在剧本需要镜头设计、空间调度或可生成性诊断时使用；保留七字段 shot 与完整视听描述。Votes: 0GitHub stars: 5
- Shorz McpControl Shorz via MCP to create and edit projects, configure panels, import assets, generate videos and thumbnails, build and run Canvas node graphs, publish to YouTube or TikTok, and run headless single-file video/image edits (no project required).Votes: 0GitHub stars: 5
- Shot ListTurn a scene, synopsis or script excerpt into a practical shot list (shot size, angle, movement, lens, action, duration). Use when the user is planning how to film or storyboard a scene, or asks for coverage, shot breakdowns or a shooting plan.Votes: 0GitHub stars: 5
- Shuohao Skills Character Refs给任何故事里的角色真出参考图（小说改编、自己原创的故事、单独设计一个角色都行，不需要小说原文）： 一段话描述角色，拆成分层字段、补全后确认， 先出一张正面全身锚点，其余视图（大头照、90° 侧面、背面、细节、45° 大头照）都只参考这张锚点， 按需分档出图。每张图带标识、可单独重出，重出后自动标出哪些图过期。 支持 Qwen Image（ComfyUI）、codex 内置出图、OpenAI Images API（GPT Image 2）和自定义命令，主图与派生图可以使用不同模型。 产出 asset.json + 一组 PNG + 双击就能开的报告。零依赖。 只要提示词、不出图的话使用 novel-characters。 Use when asked to 出角色图、做角色参考图、给我的角色出图、定妆照、真出三视图、character reference images。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Art给 AI 短剧出美术设定集（场景 + 叙事道具）：场景的设计意图、一致性锚点、光照时段变体、 空景提示词；道具的戏剧功能、状态变体、尺度参照、白底无手提示词。 产出 art.json + Markdown + 单页评审报告（含导出 JSON）。 为 AI 生成而设计，不是实拍——环境和道具都是生成资产，交付的是让它们跨集长一样的一致性方案； 10 道质量门全部由脚本确定性检查（锚点 3–5、无人无手、白底可抠、尺度短语、提示词英文……）。 有 novel-outline 的 outline.json 就用 seed 预填场景清单与出现集。 零依赖、零 API key、不出图——交付的是提示词，出图在下游。 Use when asked to 场景设定、出场景、环境设定集、场景一致性、scene bibles for AI short drama。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Characters从小说或短故事里拆出角色表、人物画像、形象提示词、音色提示词， 其中形象提示词含一张角色设定图的完整版面指令（左半身像 + 右全身三视图 + 细节条）， 产出 JSON + Markdown + 可交互的 report.html。 报告语言可指定（--lang），默认中文，任意语言都支持；零依赖、零 API key、不出图。 Use when asked to 拆小说角色、分析人物、生成角色卡、character sheets from a novel。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Outline把一本小说改编成短剧大纲五件套：改编说明、人物表、爽点表、分集梗概、资产清单， 产出 outline.json + Markdown + 单页评审报告（KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门）。 14 道质量门全部由脚本确定性检查（角色分档上限、主场景上限随集数动态、爽点间隔≤3集、每集钩子悬念必填……），不靠模型自觉； 支持体检模式：贴一份现成大纲进来，只跑质量门给诊断。 零依赖、零 API key，用当前会话额度。 Use when asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Script给 AI 短剧写剧本：把 novel-outline 的分集梗概落成结构化的场次 + 节拍流（动作节拍与台词行交替）， 台词逐句带说话人与语气，时长逐集按语速确定性折算。产出 script.json + Markdown + 单页评审报告 （时长仪表 / 分集剧本 / 场次总表 / 按角色聚合的台词本，含导出 JSON）。 剧本管戏，分镜管拍——本 skill 不分镜头、无镜号、不写生成提示词，那些是下一层分镜 skill 的活。 10 道质量门全部由脚本确定性检查（每集时长 ±15%、单句 ≤35 字、说话人合法、钩子悬念落纸、 钩子具象前 3 拍内兑现（hookBeat 认领冷开场）、每场至少一个动作节拍、爽点认领、 角色/场景/光照/道具对账上游……）。 有 outline.json 就用 seed 预填每集骨架；给 --art 连光照状态一起对账。 零依赖、零 API key，用当前会话额度。 Use when asked to 写剧本、出剧本、台词、场次、写戏、screenwriting for AI short drama。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Staging给 AI 短剧的每一场排开场站位：先从场景图里认出能站能坐的东西（推算到俯视平面上）， 再按剧本给每一场排谁在哪件东西的哪一侧、坐还是站、面朝哪、有没有群演， 程序写出每一场的开场走位句，分镜这一场第一段照抄它。 默认交付能拖动调整站位的 HTML 工具报告，页面内可导出 staging.json；JSON 同时作为工作数据保存，Markdown 按需导出。 8 道质量门全部由脚本确定性检查（认图件数、东西在图上、出场人物不多不少、在场的人落在认出来的东西上、 同一侧不叠人、群演写明在哪……）。吃 novel-script 的 script.json 和 novel-art 的 art.json 预填骨架。 零依赖、零 API key。 Use when asked to 站位、开场站位、群戏站位、谁坐在哪、排座位、走位、blocking、staging for AI short drama。Votes: 0GitHub stars: 5
- Shuohao Skills Novel Storyboard给 AI 短剧出分镜：三层结构——段（一次视频生成，≤15 秒）→ 分镜（段内 2–5 秒的剪切，认领剧本节拍） → 分镜图（每切一张关键帧：主分镜图钉 0.00 秒，子分镜图钉各自切点）。 每段自带一条 MiniMax H3 视频提示词（官方口径默认英文、逐镜换行，promptLang 可切中文）：对齐指令和 [Shot k] 切点时刻由分镜结构推导、逐字对账，台词逐字进 <d> 块（写法规范已内化为 references/h3-prompt.md，不依赖外部 skill）。 产出 storyboard.json + Markdown + 单页评审报告（分镜节奏带 / 分集分镜表 / 生成批次单 / 配音对齐单，含导出 JSON）。不出图——交付的是每格的画面提示词和它该挂哪些参考图。 18 道质量门全部由脚本确定性检查（第 18 道 shot-recipe 可选：挂上 shot-recipes 卡库才查，不挂就明说跳过）； export 一键导出 H3 投产包（每段提示词 + 按 Picture 序的分镜图清单）。零依赖、零 API key，用当前会话额度。 Use when...Votes: 0GitHub stars: 5
- SkipwatchTurns a tutorial video (YouTube, X, TikTok, Instagram, Facebook or any yt-dlp URL) or a local screen recording into an installed Agent Skill whose steps cite timestamps. Use when the user runs /skipwatch, or shares a video link or recording and asks to make, capture or save it as a skill. Also handles /skipwatch doctor, resume, list, pack, install and share. Not for requests to summarize, download or transcribe a video, or to follow its steps right now.Votes: 0GitHub stars: 5
- Slack Demo VideoCreate or revise an illustrative Slack conversation video with channel and thread chrome, typing, attachments, agent progress, Block Kit-style results, approvals, replies, and reactions. Use for rendered Slack UI demos and clean editor footage; use actual capture for a requested live Slack integration and do not use this skill to send Slack messages.Votes: 0GitHub stars: 5
- Smixs ImageImage prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst). Writes ready-to-use prompts with model/quality/size recommendations. Use when: "нарисуй", "сгенерируй картинку", "image prompt", "промпт для картинки", blog covers, slides, posters, product shots, UI mockups, storyboards, character sheets, edit/colorize, style transfer, vision analysis, image-to-prompt, nb, NBP, NB2, gpt-image-2.5, multi-panel grids, ecommerce product photography, fashion editorial, food/bever...Votes: 0GitHub stars: 5
- Smixs VideoUse this skill whenever the user asks to create, improve, audit, or split prompts for AI video generators (Seedance, Kling, Veo, Runway, Luma, Pika, Sora, any image-to-video system). The skill also covers storyboards, shot lists, director treatments, dynamic montage, multi-clip story structure, camera direction, lighting, blocking, pacing, character continuity, dialogue, and sound design. Trigger even when the user says things like "придумай сцену для видео", "разбей на склейки", "сделай раск...Votes: 0GitHub stars: 5
- Smy Seedance Storyboard专业的上美影风格AI短剧制作系统（基于Seedance 2.0平台）。当用户要求：(1) 将故事/小说/神话/民间传说转换为上美影风格视频脚本，(2) 生成上美影风格（上海美术电影制片厂复古手绘动画）的Seedance 2.0分镜提示词，(3) 规划多集国风动画短剧系列，(4) 为Midjourney、GPT-Image-2、Seedream、Nano Banana Pro等图像模型创建上美影风格的角色/场景/异兽/道具生成提示词时使用。输入可以是完整的小说、神话典故、历史故事或简短的故事大纲。输出包括标准脚本格式的完整剧本（△镜头描述+对白+OS/VO+闪回+字幕，含说书人旁白体制）、剧集分解、剧组色盘声明、资产生成提示词和Seedance 2.0格式的分镜脚本。支持"文-资-视-剪"工作流，所有视觉输出统一为上美影风格（水墨线条、矿物颜料纯平涂色块、概括造型、胶片颗粒感，纯2D无阴影无渐变）。Votes: 0GitHub stars: 5
- Social Qa VideoBiến một bài hỏi-đáp trên Threads hoặc Facebook thành video dọc 9:16 kiểu TikTok — ảnh chụp thật của bài đăng và bình luận trôi trên nền phong cảnh, có giọng đọc tiếng Việt và nhạc nền. Dùng khi người dùng gửi link threads.com hoặc facebook.com kèm ý muốn "làm video", "dựng video từ bài này", "cap màn hình bình luận làm video", "làm video hỏi đáp", "biến bài này thành TikTok/Reels", hoặc chỉ dán link mà ngữ cảnh đang làm video ngắn. Cũng dùng khi muốn sửa nội dung, đổi giọng, đổi nhạc hay ren...Votes: 0GitHub stars: 5
- Sound DesignMusic, sound effects, mixing and loudness for video, podcasts, apps and games. Chooses and analyses music (tempo, bars, key, energy, finding the drop), edits it on bars with blind listening tests, syncs picture to beats, places SFX by their measured transient, synthesises a deterministic foley and UI sound kit tuned to the song's key, ducks music under voice, mixes offline from a cue list into stems and a master, and masters to platform loudness (-14 LUFS / -1 dBTP for social, -16 for podcast...Votes: 0GitHub stars: 5
- Spark Video CastScaffold and generate reference assets for characters (cast), locations (movie-set / set dressing), and key props — the three pillars of visual consistency in spark-video. Wraps bl image generate / edit for cast reference sheet creation. Use when adding new characters/locations/props or when costume/state changes are needed.Votes: 0GitHub stars: 5
- Spark Video Clip ReviewPer-clip quality reviewer + render retry state machine. After each rendered shot, score it on 6 axes via `bl omni` (qwen3.5-omni-plus), then decide ACCEPT / REJECT-and-rewrite / REJECT-and-escalate. Handles up to N retry rounds with auto prompt rewriting; escalates to spark-video-director when retries are exhausted.Votes: 0GitHub stars: 5
- Spark Video DirectorTranslate a screenplay (one scene at a time) into a provider-agnostic storyboard fragment for the spark-video pipeline. Wraps Shanyin Super Director Master when available — the upstream Shanyin SKILL is the single source of truth for craft when present.Votes: 0GitHub stars: 5
- Spark Video ProducerProducer stage for the spark-video pipeline. Orchestrates screenwriter, director, cast, VFX review, clip review, render chain DAGs, and final stitching with the 4+2 user confirmation gates. Use internally when running the end-to-end spark-video production workflow.Votes: 0GitHub stars: 5
- Spark Video ScreenwriterTurn a user's premise into a structured screenplay (one scene at a time) for the spark-video pipeline. Wraps Shanyin Super Screenwriting Master when available — that upstream Shanyin SKILL is the single source of truth for craft when present.Votes: 0GitHub stars: 5
- Spark Video Vfx ReviewPre-render quality gate. Read a finished storyboard.json and produce a structured review report flagging visual inconsistencies, prompt defects, and continuity errors that would waste render budget. You find problems; the director fixes them. Opt-in — bypassed unless the producer explicitly invokes you.Votes: 0GitHub stars: 5
- Spark VideoInstall, set up, diagnose, and run the full spark-video AI video production pipeline from premise to screenplay, storyboard, render, review, and final mp4. Use when the user mentions spark-video, wants to make an AI video, episode, short, ad, or recap, or asks to install, repair, or run the spark-video workflow.Votes: 0GitHub stars: 5
- Speechlab0210 Tutorial VideoPlan, produce, review, or revise a lecture, tutorial, workshop recording, or course video with a coherent learning progression and synchronized editable slides, narration, captions, and media. Use for any subject and for existing instructor materials; a request for slides alone does not require producing a video.Votes: 0GitHub stars: 5
- Sports Athletics HighlightSports and athletics video: highlight reels, athlete profiles, club brand films and match-day hype. Beat-matched impact cuts, slow-motion, kinetic stat overlays, with a mandatory asset-request and rights-clearance protocol. Use for clubs, athletes, academies, leagues and recruiting reels.Votes: 0GitHub stars: 5
- SpotlightTurn a website, a code project, footage or photos, and a description into a short video that brags (a launch), promotes a point (a promo), or explains a topic (a presentation as a video), with music, on-screen text in any language, a poster and a caption. Use when someone says "/spotlight", "make a video about this", "launch video", "brag about this", "promo from these photos/videos", "reel from this footage", "explainer video", "presentation video", or points at a site, folder or topic and w...Votes: 0GitHub stars: 5
- Story Video DirectorTurn any story, article, script, synopsis, anecdote, advertisement concept, poem, or one-line video idea into a director-led AI video production package and, when explicitly requested, render and assemble the video through a configured image-to-video API. Use when Codex should determine runtime, split the narrative into clips no longer than 15 seconds, design characters and locations, generate assets, create Chinese audiovisual prompts with inline filename references, prepare manifests, submi...Votes: 0GitHub stars: 5
- Story VideoCreate narrated faceless story videos (mystery, drama, true-crime style fiction) with characters that keep the same face in every scene. Writes the script, generates character/location/prop reference sheets and 40+ scene images, records the voiceover (Vbee or ElevenLabs), and renders a vertical video with Ken Burns motion, CapCut-style punch/shake/glitch, word-by-word captions, suspect/clue cards and a countdown — via Remotion. Use when the user asks for a story video, a narrated illustrated ...Votes: 0GitHub stars: 5
- Storyboard Director Storyboard Aggregate PromptWrite the aggregate video prompt for a confirmed line-art storyboard session. Use after the user confirms line art. Produces the fixed subject/scene/music preface plus ordered Shot blocks without redesigning the storyboard.Votes: 0GitHub stars: 5
- Storyboard Director Storyboard Final Frame OptionalOptional branch for generating final styled storyboard frames from approved line art. Use only when the user explicitly asks for finished frames; accept either a user-provided style image or a text style lock.Votes: 0GitHub stars: 5
- Storyboard Director Storyboard Lineart GeneratorGenerate and register per-shot storyboard line-art from an approved storyboard session. Use after script package approval and text-only prompt preflight. Supports parallel/multi-agent generation and updates session JSON/HTML with saved asset paths.Votes: 0GitHub stars: 5
- Storyboard Director Storyboard Script PlannerPlan the script package for a storyboard session: ingest story ideas plus optional character/scene references, lock aspect ratio and project mode, write shot text, production anchors, line-art prompts, and text-only script/prompt review. Use this before storyboard line-art generation.Votes: 0GitHub stars: 5
- Storyboard DirectorRun a prompt-controlled story-to-storyboard workflow: ingest a story idea and optional character/scene references, prepare an approved shot package, generate and register per-shot line art, collect user review in one HTML board, and deliver one ordered aggregate video prompt. Use for complete storyboard runs or for coordinating the included stage skills. Finished colored frames are optional and only run when explicitly requested.Votes: 0GitHub stars: 5
- StorycutTurn an interview, podcast, lecture, founder story, or other spoken video/audio file into a verified transcript, meaningful highlights, and an ordered, timestamped story cut list. Use whenever the user asks for the best moments, clips, an interview highlight reel, a rough cut, an edit decision list, or transcript-to-video storytelling, even if they do not mention StoryCut by name.Votes: 0GitHub stars: 5
- Tabcom Video EditEdit video dọc (9:16) cho Tabcom từ source người nói + asset minh họa, bằng pipeline ffmpeg + Pillow. Dùng khi người dùng gửi video source vào folder "Tabcom edit video" và muốn "edit video", "dựng video", "làm video mới", "cắt video", "edit vid", hoặc yêu cầu chỉnh sửa/render lại một bản draft video Tabcom. Bao gồm bóc timestamp lời thoại, tách nền người bằng AI, dựng cảnh chữ có animation, chèn ảnh minh họa liên tục, logo thật, zoom punch, flash chuyển cảnh và sound effect.Votes: 0GitHub stars: 5
- Tabcom Video ThumbnailTạo thumbnail (ảnh bìa) cho video ngắn dọc 9:16 của Tabcom từ chính source người nói - cắt khung, viền nét đứt trắng quanh người, gradient xanh teal trên dưới, panel trắng bo góc với tiêu đề IN HOA 2 dòng. Dùng khi người dùng nói "tạo thumb", "làm thumbnail", "ảnh bìa video", "cover video", hoặc đổi tiêu đề/khung hình của một thumbnail đã tạo. Skill này chạy TỰ ĐỘNG ngay sau khi dựng xong video bằng skill tabcom-video-edit, không cần đợi người dùng nhắc.Votes: 0GitHub stars: 5
- Timoteoaltobrando Ai VideoMake and edit videos with Claude Opus 5.5, end to end, from a blank page or from the user's own footage — product and launch films, ads, talking-head and founder videos, interviews, explainers, tutorials and screen demos, event and trip montages, highlight reels, podcast clips, Reels/TikTok/Shorts, animated logos and intros, music and lyric videos, and changes to a finished video (shorter cut, vertical version, subtitles, translation, new music). Remotion is the backbone; Codex (image_gen) ma...Votes: 0GitHub stars: 5
- Toonflow CanvasToonflow 画布操控手册，覆盖画布的新建切换重命名、节点的增删改移与连线、整图排布与视口调整，以及调用节点注册函数；适用于用户要求改动当前画布或搭建节点流程的场景。Votes: 0GitHub stars: 5
- Toonflow V118workflow把 Toonflow v1.1.8 的编剧手法、12 类叙事技法、11 种美术风格与资产、分镜、图像及视频提示词知识，按阶段逐步制作并确认；统一维护剧本、资产与单集三块画布，用于旧流程复现、分集制作与续作；讨论或编辑技能本身不启动制作。Votes: 0GitHub stars: 5
- Toonflow Workflow在 Toonflow 当前画布中把创意、小说或定稿剧本制作成可查看的文本、图片资产和视频片段，支持复用素材、续作与局部修改。用于实际制作或继续已有项目；明确只要对话文字时不操作画布，讨论或编辑技能本身时不启动制作。Votes: 0GitHub stars: 5
- True Crime DocTrue-crime documentary and docuseries: thriller structure, hook episode, accordion second act, ticking clock, low-res surveillance aesthetic, present-tense aliveness and labelled re-enactments. Use for true-crime and investigation-led crime storytelling.Votes: 0GitHub stars: 5
- Ui Mockup VideoBuild and render an animated product interface from screenshots, designs, or an existing app, including cursor actions, typing, streaming, approvals, navigation, and result states. Use for UI mockup animation videos and short product interaction clips; use real capture instead when the user explicitly requests actual recorded behavior.Votes: 0GitHub stars: 5
- Unclewang2088 Short Drama Director爆款微短剧剧本全流程创作技能。当用户想要创作短剧、微短剧、竖屏短剧剧本、写分集、选题立项、付费卡点设计、短剧爽点设计、短剧出海时使用。覆盖选题→角色→分集大纲→逐集撰写→质量自检→合规审核→导出全流程，50-100集。基于爆款短剧工业方法论（爽点矩阵/节奏曲线/钩子设计/付费卡点）。Votes: 0GitHub stars: 5