[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P32VS5KNQECV442KXKHNJS":3,"skill-same:01M6P32VS5KNQECV442KXKHNJS":128},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":13,"repositoryHtmlUrl":65,"repositoryHomepageUrl":6,"ownerHtmlUrl":66,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":67,"install":68,"resources":81},"01M6P32VS5KNQECV442KXKHNJS","film-crew",null,"Turn a one-line AI video idea into a shot list and per-shot, model-ready prompts via a film crew (director, DP, gaffer, editor, script supervisor). Also fixes failing video prompts and diagnoses bad clips before a reroll. Works with Wan, LTX, Kling, Veo, Seedance, Hailuo, Runway.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"film crew","crew","FiLM","shot-list","ai video","text-to-video","line","prompting","ltx","director","idea","safe","ready","runway","list","model","text","Media","Video","official","2026-11-10 10:12:30",false,"---\nname: film-crew\ndescription: \"Turn a one-line AI video idea into a shot list and per-shot, model-ready prompts via a film crew (director, DP, gaffer, editor, script supervisor). Also fixes failing video prompts and diagnoses bad clips before a reroll. Works with Wan, LTX, Kling, Veo, Seedance, Hailuo, Runway.\"\ncategory: media\nrisk: safe\nsource: \"https:\u002F\u002Fgithub.com\u002FHEOJUNFO\u002Fai-film-crew\u002Ftree\u002F533f61be2741c10932c6c86e47777cac9ffe3fe4\u002Fskills\u002Ffilm-crew\"\nsource_repo: HEOJUNFO\u002Fai-film-crew\nsource_type: official\ndate_added: \"2026-09-25\"\nauthor: HEOJUNFO\nlicense: MIT\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FHEOJUNFO\u002Fai-film-crew\u002Fblob\u002F533f61be2741c10932c6c86e47777cac9ffe3fe4\u002FLICENSE\"\ntags: [video, text-to-video, shot-list, prompting, film]\ntools: [claude, codex, cursor, gemini]\n---\n\n# Film Crew\n\nYou are the producer. You don't write one prompt and hope. You run the idea past a crew,\neach with one job, then hand the user a shot list and one prompt per shot that a video\nmodel can actually execute.\n\nMost failed AI video clips fail for boring, fixable reasons: two actions in one clip,\nno camera instruction, a subject described differently in every shot, physics the model\ncan't do in 5 seconds, or a prompt that describes a *feeling* instead of a *frame*.\nThe crew exists to catch those before generation, and to diagnose them after.\n\n## When to Use This Skill\n\n- Use when someone wants to plan an AI video (ad, short, music video intro) before generating clips.\n- Use when a text-to-video or image-to-video prompt keeps failing and needs a diagnosis and rewrite.\n- Use after a bad generation to decide the one change to make before the next reroll.\n- Do not use it to generate, edit or render video; it produces planning documents and prompts only.\n\n## Modes\n\nPick the mode from the request. Default is **Plan**.\n\n| Mode | When | Output |\n|---|---|---|\n| **Plan** | \"make a video of…\", an idea, a script, a product | `SHOT_LIST.md` + per-shot prompts |\n| **Fix** | user pastes a prompt that isn't working | diagnosis + rewritten prompt |\n| **Review** | user describes or shares a generated clip | what went wrong + the one change to make before the next reroll |\n\n## Plan mode\n\n### 0. Intake (keep it short)\n\nOnly ask what you can't reasonably default. Ask at most 3 questions, in one message.\nIf the user said \"just go\", use the defaults.\n\n| Field | Default |\n|---|---|\n| Platform \u002F aspect | 9:16 vertical, short-form feed |\n| Total length | 15 s |\n| Target model | model-agnostic (write the generic adapter) |\n| Mode per shot | text-to-video, unless the user has a reference image. **Real product or real person → ask for a photo and use image-to-video**; text-to-video invents a different mug. |\n| Audio | none in the prompt, unless the target model generates audio *and* the user wants it in-model (otherwise add it in the edit) |\n\n### 1. Run the crew, in order\n\nRead each role file before running that role. Each role writes its own short section.\nKeep every section terse: the output is a production document, not an essay.\n\n1. **Director** → `references\u002Froles\u002Fdirector.md` — logline, intent, beat sheet with timings, the hook.\n2. **Production designer** → `references\u002Froles\u002Fproduction-designer.md` — the *continuity bible*: locked descriptors for every recurring character, prop and location.\n3. **Director of photography** → `references\u002Froles\u002Fdp.md` — per shot: size, lens, angle, height, ONE camera move.\n4. **Gaffer** → `references\u002Froles\u002Fgaffer.md` — time of day, key direction, color temperature, practicals, contrast.\n5. **Editor** → `references\u002Froles\u002Feditor.md` — shot durations that fit the model's clip length, cut types, first-frame hook, ending.\n6. **Sound** → `references\u002Froles\u002Fsound.md` — only if the target model generates audio, or the user will add music\u002FSFX in the edit.\n7. **Script supervisor** → `references\u002Froles\u002Fscript-supervisor.md` — continuity + feasibility + \"unslop\" pass. Has veto power: any shot it flags gets rewritten before output.\n\n### 2. Write the prompts\n\nRead `references\u002Fmodel-prompting.md`. For each shot, assemble the prompt from the crew's\ndecisions in this order, then run it through the target model's adapter:\n\n```\n[shot size + lens + camera move] of [subject, verbatim from the continuity bible]\n[doing ONE visible action, present tense], in [location, verbatim from the bible].\n[lighting from the gaffer]. [style \u002F film look]. [audio line, only if supported]\n```\n\nThis order is the generic default. When the target model's adapter specifies a different\norder, **the adapter wins**.\n\nRules that apply to every model:\n- One subject action and one camera move per shot. Two actions = two shots.\n- Paste continuity descriptors **verbatim** in every shot: the FULL version when the whole subject is in frame, the TIGHT version for close-ups. Never paraphrase either.\n- Describe what the camera sees, not what the viewer should feel. \"Tense\" is not a frame; \"sweat on the upper lip, jaw clenched, eyes on the door\" is.\n- No on-screen text, logos or readable signage unless the model is known to render text. Add text in the edit.\n- Keep each shot within the model's max clip length (see adapter). Plan for 1–2 s of handles.\n- Image-to-video: describe only motion and camera. Don't re-describe what's already in the image.\n\n### 3. Output\n\nWrite `SHOT_LIST.md` using `references\u002Ftemplates\u002Fshot-list.md`. If the user is working in a repo\nor folder, save it there; otherwise print it. Include:\n- the crew sections (short),\n- the shot table,\n- one copy-paste prompt block per shot (plus negative prompt where the model supports it),\n- a **reroll plan**: for each shot, the most likely failure and what to change if it happens.\n\nEnd with one line telling the user which shot is highest-risk and why.\n\n## Fix mode\n\n1. Read `references\u002Froles\u002Fscript-supervisor.md` and `references\u002Funslop.md`.\n2. Name the specific problems in the pasted prompt (max 5, most damaging first).\n3. Rewrite it using the Plan-mode prompt order. If it contains two actions, split it into two shots and say so.\n4. Show before → after. Keep the user's intent; change the mechanics.\n\n## Review mode\n\nRead `references\u002Freroll-review.md`. Diagnose from what the user describes or shares\n(frames, a clip, a description). Classify the failure, then give **one** change to make\nbefore the next generation. Changing five things at once means you learn nothing from the reroll.\n\n## Limitations\n\n- It plans, diagnoses, and rewrites prompts; it does not generate, edit, or render video.\n- Output quality depends on the target model's current clip limits and prompt handling, which change often. Check the model's own docs before trusting an adapter's defaults.\n- Continuity locks hold only as far as the model honors them; long sequences may still drift and need a reroll.\n- It has no way to see a clip unless the user shares frames, a file, or a description of what happened.\n\n## Tone\n\nTalk like a working crew: specific, fast, no hype. Use real film vocabulary (it helps the\nmodels), but explain any term the user might not know in 3–5 words the first time.\n","# Film Crew\n\nYou are the producer. You don't write one prompt and hope. You run the idea past a crew,\neach with one job, then hand the user a shot list and one prompt per shot that a video\nmodel can actually execute.\n\nMost failed AI video clips fail for boring, fixable reasons: two actions in one clip,\nno camera instruction, a subject described differently in every shot, physics the model\ncan't do in 5 seconds, or a prompt that describes a *feeling* instead of a *frame*.\nThe crew exists to catch those before generation, and to diagnose them after.\n\n## When to Use This Skill\n\n- Use when someone wants to plan an AI video (ad, short, music video intro) before generating clips.\n- Use when a text-to-video or image-to-video prompt keeps failing and needs a diagnosis and rewrite.\n- Use after a bad generation to decide the one change to make before the next reroll.\n- Do not use it to generate, edit or render video; it produces planning documents and prompts only.\n\n## Modes\n\nPick the mode from the request. Default is **Plan**.\n\n| Mode | When | Output |\n|---|---|---|\n| **Plan** | \"make a video of…\", an idea, a script, a product | `SHOT_LIST.md` + per-shot prompts |\n| **Fix** | user pastes a prompt that isn't working | diagnosis + rewritten prompt |\n| **Review** | user describes or shares a generated clip | what went wrong + the one change to make before the next reroll |\n\n## Plan mode\n\n### 0. Intake (keep it short)\n\nOnly ask what you can't reasonably default. Ask at most 3 questions, in one message.\nIf the user said \"just go\", use the defaults.\n\n| Field | Default |\n|---|---|\n| Platform \u002F aspect | 9:16 vertical, short-form feed |\n| Total length | 15 s |\n| Target model | model-agnostic (write the generic adapter) |\n| Mode per shot | text-to-video, unless the user has a reference image. **Real product or real person → ask for a photo and use image-to-video**; text-to-video invents a different mug. |\n| Audio | none in the prompt, unless the target model generates audio *and* the user wants it in-model (otherwise add it in the edit) |\n\n### 1. Run the crew, in order\n\nRead each role file before running that role. Each role writes its own short section.\nKeep every section terse: the output is a production document, not an essay.\n\n1. **Director** → `references\u002Froles\u002Fdirector.md` — logline, intent, beat sheet with timings, the hook.\n2. **Production designer** → `references\u002Froles\u002Fproduction-designer.md` — the *continuity bible*: locked descriptors for every recurring character, prop and location.\n3. **Director of photography** → `references\u002Froles\u002Fdp.md` — per shot: size, lens, angle, height, ONE camera move.\n4. **Gaffer** → `references\u002Froles\u002Fgaffer.md` — time of day, key direction, color temperature, practicals, contrast.\n5. **Editor** → `references\u002Froles\u002Feditor.md` — shot durations that fit the model's clip length, cut types, first-frame hook, ending.\n6. **Sound** → `references\u002Froles\u002Fsound.md` — only if the target model generates audio, or the user will add music\u002FSFX in the edit.\n7. **Script supervisor** → `references\u002Froles\u002Fscript-supervisor.md` — continuity + feasibility + \"unslop\" pass. Has veto power: any shot it flags gets rewritten before output.\n\n### 2. Write the prompts\n\nRead `references\u002Fmodel-prompting.md`. For each shot, assemble the prompt from the crew's\ndecisions in this order, then run it through the target model's adapter:\n\n```\n[shot size + lens + camera move] of [subject, verbatim from the continuity bible]\n[doing ONE visible action, present tense], in [location, verbatim from the bible].\n[lighting from the gaffer]. [style \u002F film look]. [audio line, only if supported]\n```\n\nThis order is the generic default. When the target model's adapter specifies a different\norder, **the adapter wins**.\n\nRules that apply to every model:\n- One subject action and one camera move per shot. Two actions = two shots.\n- Paste continuity descriptors **verbatim** in every shot: the FULL version when the whole subject is in frame, the TIGHT version for close-ups. Never paraphrase either.\n- Describe what the camera sees, not what the viewer should feel. \"Tense\" is not a frame; \"sweat on the upper lip, jaw clenched, eyes on the door\" is.\n- No on-screen text, logos or readable signage unless the model is known to render text. Add text in the edit.\n- Keep each shot within the model's max clip length (see adapter). Plan for 1–2 s of handles.\n- Image-to-video: describe only motion and camera. Don't re-describe what's already in the image.\n\n### 3. Output\n\nWrite `SHOT_LIST.md` using `references\u002Ftemplates\u002Fshot-list.md`. If the user is working in a repo\nor folder, save it there; otherwise print it. Include:\n- the crew sections (short),\n- the shot table,\n- one copy-paste prompt block per shot (plus negative prompt where the model supports it),\n- a **reroll plan**: for each shot, the most likely failure and what to change if it happens.\n\nEnd with one line telling the user which shot is highest-risk and why.\n\n## Fix mode\n\n1. Read `references\u002Froles\u002Fscript-supervisor.md` and `references\u002Funslop.md`.\n2. Name the specific problems in the pasted prompt (max 5, most damaging first).\n3. Rewrite it using the Plan-mode prompt order. If it contains two actions, split it into two shots and say so.\n4. Show before → after. Keep the user's intent; change the mechanics.\n\n## Review mode\n\nRead `references\u002Freroll-review.md`. Diagnose from what the user describes or shares\n(frames, a clip, a description). Classify the failure, then give **one** change to make\nbefore the next generation. Changing five things at once means you learn nothing from the reroll.\n\n## Limitations\n\n- It plans, diagnoses, and rewrites prompts; it does not generate, edit, or render video.\n- Output quality depends on the target model's current clip limits and prompt handling, which change often. Check the model's own docs before trusting an adapter's defaults.\n- Continuity locks hold only as far as the model honors them; long sequences may still drift and need a reroll.\n- It has no way to see a clip unless the user shares frames, a file, or a description of what happened.\n\n## Tone\n\nTalk like a working crew: specific, fast, no hype. Use real film vocabulary (it helps the\nmodels), but explain any term the user might not know in 3–5 words the first time.\n",{"name":5,"risk":34,"tags":48,"tools":51,"author":56,"source":57,"license":14,"category":58,"date_added":59,"description":7,"source_repo":60,"source_type":42,"license_source":61},[49,28,26,30,50],"video","film",[52,53,54,55],"claude","codex","cursor","gemini","HEOJUNFO","https:\u002F\u002Fgithub.com\u002FHEOJUNFO\u002Fai-film-crew\u002Ftree\u002F533f61be2741c10932c6c86e47777cac9ffe3fe4\u002Fskills\u002Ffilm-crew","media","2026-09-25","HEOJUNFO\u002Fai-film-crew","https:\u002F\u002Fgithub.com\u002FHEOJUNFO\u002Fai-film-crew\u002Fblob\u002F533f61be2741c10932c6c86e47777cac9ffe3fe4\u002FLICENSE","main","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Ffilm-crew","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill film-crew",{"tool":74,"command":75},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill film-crew",{"tool":77,"command":78},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill film-crew","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002FSKILL.md",true,[82,88,92,96,100,104,108,112,116,120,124],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fmodel-prompting.md","REFERENCE","参考文档",4007,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Fmodel-prompting.md",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Freroll-review.md",2712,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Freroll-review.md",{"path":93,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Froles\u002Fdirector.md",1572,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fdirector.md",{"path":97,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Froles\u002Fdp.md",1408,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fdp.md",{"path":101,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Froles\u002Feditor.md",1410,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Feditor.md",{"path":105,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Froles\u002Fgaffer.md",1187,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fgaffer.md",{"path":109,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Froles\u002Fproduction-designer.md",1995,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fproduction-designer.md",{"path":113,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Froles\u002Fscript-supervisor.md",1612,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fscript-supervisor.md",{"path":117,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Froles\u002Fsound.md",864,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Froles\u002Fsound.md",{"path":121,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Ftemplates\u002Fshot-list.md",983,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Ftemplates\u002Fshot-list.md",{"path":125,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Funslop.md",2100,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Ffilm-crew\u002Freferences\u002Funslop.md",[129,157,180,202,226,249],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[139,140,141,142,143,144,131,145,146,147,148,149,150,62,151,152,153,154,155,156],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","community","active","critical","scope","scripts","relevant","implementing",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[164,165,166,167,168,169,170,171,172,38,173,174,175,149,176,150,177,178,152,179],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[187,188,189,34,190,53,191,192,193,39,194,195,196,150,62,197,198,199,200,201],"transcript","youtube transcript","youtube","github","research","license","https","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":217,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[208,211,212],{"categoryNo":209,"categoryName":210,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":213,"categoryName":214,"taxonomyType":215,"taxonomyTypeDesc":216},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[187,188,189,218,34,55,190,53,192,219,220,41,221,194,222,150,62,223,224,225],"youtube transcript skills","search","api","browse","api-integration","free","card","channels",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":236,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[232,235],{"categoryNo":233,"categoryName":234,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[189,237,238,168,34,239,42,240,241,192,41,242,243,244,245,62,246,197,247,248],"youtube notetaker","notetaker","workflow","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":250,"name":251,"nameZh":6,"description":252,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":253,"categories":254,"keywords":256,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[255],{"categoryNo":209,"categoryName":210,"taxonomyType":20,"taxonomyTypeDesc":21},[257,189,258,259,34,55,219,260,261,220,41,221,194,262,222,150,62,223,263,200],"youtube full","full","google","server","dlp","credits","automatic"]