[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70J88S8JQNPMAW2AJGAPCEB":3,"skill-same:01M70J88S8JQNPMAW2AJGAPCEB":90},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":38,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M70J88S8JQNPMAW2AJGAPCEB","higgsfield-youtube-thumbnail",null,"Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a truthful information-gap concept, preserves up to three referenced identities, supports logos and controlled variants, renders the main image with Nano Banana Pro, and applies focused Seedream edits. Use when: \"make a YouTube thumbnail\", \"thumbnail for this video\", \"MrBeast-style cover\", \"Shorts cover\", or \"Instagram video cover\". Chain after any video workflow once its truthful topic and visual direction are known. NOT for producing the video itself (use higgsfield-generate), product catalog photos (use higgsfield-product-photoshoot), or marketplace cards (use higgsfield-marketplace-cards).","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"youtube","higgsfield","thumbnail","higgsfield youtube thumbnail","thumbnails","Bash","image","workflow","when","information","logo","main","variants","nano banana pro","up","direction","chain","video workflow","click","Video","2026-11-10 10:12:30",false,"---\nversion: 0.14.0\nname: higgsfield-youtube-thumbnail\ndescription: |\n  Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a truthful information-gap concept, preserves up to three referenced identities, supports logos and controlled variants, renders the main image with Nano Banana Pro, and applies focused Seedream edits. Use when: \"make a YouTube thumbnail\", \"thumbnail for this video\", \"MrBeast-style cover\", \"Shorts cover\", or \"Instagram video cover\". Chain after any video workflow once its truthful topic and visual direction are known. NOT for producing the video itself (use higgsfield-generate), product catalog photos (use higgsfield-product-photoshoot), or marketplace cards (use higgsfield-marketplace-cards).\nargument-hint: \"[video-topic-or-title] [--image \u003Cface-or-logo>] [--ratio 16:9|9:16|4:5]\"\nallowed-tools: Bash\n---\n\n# Higgsfield YouTube Thumbnail\n\nCreate a clean thumbnail concept, generate each variant through the `higgsfield` CLI, inspect it, and make only requested surgical edits.\n\n## Bootstrap\n\nBefore any generation:\n\n1. If `higgsfield` is missing, install it:\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fhiggsfield-ai\u002Fcli\u002Fmain\u002Finstall.sh | sh\n   ```\n2. If `higgsfield account status` reports `Session expired` or `Not authenticated`, ask the user to run `higgsfield auth login`, then wait.\n3. Confirm the locked model contracts when the catalog may have changed:\n   ```bash\n   higgsfield model get nano_banana_pro --json\n   higgsfield model get gpt_image_2 --json\n   higgsfield model get seedream_v5_pro --json\n   ```\n\n## UX rules\n\n1. Match the user's language. Keep CLI\u002Fmodel mechanics out of normal chat.\n2. Do not ask for facts already present in the brief. Ask one compact question only when a missing choice changes the result.\n3. Never invent claims, outcomes, products, people, screenshots, or statistics that are not true of the video.\n4. Do not print raw JSON or job IDs to the user. Deliver the image URL and a short variant label.\n5. A style-reference thumbnail is for visual analysis only. Never pass it with `--image`; copying its identity or exact composition is forbidden.\n6. Do not use `--count`. Every concept, emotion, or camera take gets its own prompt and generation call.\n7. `use_unlim` is not a current CLI parameter. Never add `--use-unlim`; if the user explicitly asks to use an unlimited allowance, explain that this workflow must run on credits in CLI or through a surface that supports that allowance.\n\n## Intake gates\n\nCollect only what the brief does not answer:\n\n- The video's topic\u002Ftitle and the truthful promise the thumbnail may imply.\n- Exact scene requirements, if any.\n- Who appears: 0–3 people. If a concept needs a person and no face photo was provided, ask whether to use the user, another provided person, or a generic generated character. Never choose silently.\n- Optional style-reference thumbnail. Analyze it with host vision for energy, framing, split layout, palette, and emotion; do not send it to Higgsfield.\n- Optional logo and whether it stays flat or becomes a 3D object.\n- Optional headline, 2–4 words. Default delivery is a clean image with no text. Use a deterministic overlay when the user requests an overlay; bake text into the generated image only when explicitly requested.\n- Ratio: `16:9` for YouTube by default, `9:16` for Shorts, or `4:5` for Instagram.\n- One final concept or a variant set. If unspecified and alternatives would materially help, offer a set of about four. Hard cap: 16 total generations.\n\nIf the user gives an emotion count without names, use this ladder: shock, hype, rage, awe, laugh, fear, smug, charisma, confusion, determination, disgust.\n\n## Concept gate\n\nRead `references\u002Fthumbnail-frameworks.md`. Brainstorm at least five truthful concepts internally, across multiple frameworks, then select the strongest information gap with one focal subject and minimal clutter. Combine frameworks only when the result still reads in under one second at roughly 120px wide.\n\nWhen a reference thumbnail exists, extract this structure before prompting:\n\n```text\nbrief, generic subject pose\u002Faction, elements, location, composition, background,\nsplit (true\u002Ffalse), split_count, person_count, emotion, emotion_detail\n```\n\nThe reference supplies art direction, never a specific identity. User instructions override it field by field.\n\n## Reference order\n\nPass face photos first in character order, then the logo. Repeat `--image` for every reference. When two or more references are attached, the prompt's first line must be a manifest such as:\n\n```text\nIMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.\n```\n\nLocal paths are auto-uploaded. Previous completed job IDs also work as `--image` inputs.\n\n## Prompt contract\n\nAssemble every main-render prompt in this order:\n\n1. **Frame:** `Bold, punchy YouTube-thumbnail composite — poster-grade, photoreal and high-impact, NOT a muted cinematic movie still, \u003Cratio>, single unified frame — no split-screen, no diagonal divide, everything blends smoothly and organically across the same continuous shot.` For `9:16`, add `faces in the upper two-thirds`. A requested graphical representation replaces photoreal language with a clean diagram\u002Fgraphic brief.\n2. **Scene brief:** depict the user's exact content.\n3. **Text:** default `No text, no readable UI labels, no watermark.` For explicit baked headline: `TEXT: bold thumbnail headline text baked into the image, reading exactly \"\u003CTEXT>\" — massive, ultra-legible sans-serif with a clean outline\u002Fglow treatment, placed where it never covers the subject's face. No other text, no watermark.`\n4. **Subjects:** large, foreground-dominant, chest-up or medium-close, filling about 40–60% of the frame. End with `All faces crisply sharp as the anchors of the shot.`\n5. **Key elements:** only signature props\u002Feffects that explain the information gap.\n6. **Logo:** preserve exact shapes, colors, proportions, and letterforms; keep it away from faces.\n7. **Location:** place, time, weather, and atmosphere when relevant.\n8. **Composition:** one power-third hero, clear scale hierarchy, depth, and strong subject\u002Fbackground separation.\n9. **Background:** vivid high-contrast color field or environment, soft vignette and edge falloff; do not divide it unless a split layout was explicitly requested.\n10. **Lighting on people:** `signature YouTube thumbnail lighting rig — strong key light sculpting the face, soft dreamy fill lifting shadows, and defined back light plus hair light tracing a clean bright rim around hair, shoulders and silhouette.` Only the rim may use a colored accent.\n11. **Grade:** vivid, bright, glossy, poster-punchy, deep blacks, crisp highlights, rich saturated colors, cohesive as one image. Restrain it only for an explicit calm\u002Fpremium\u002Fmuted brief.\n\nFor each photo-referenced person, include:\n\n```text\nCHARACTER N: the person from attached face reference #K — IDENTITY LOCK: reproduce\nthis exact person with a photographic identity match — same bone structure, eye shape,\nnose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average,\nor restyle the face. Expression: \u003Cemotion phrase>.\n```\n\n### Split layouts\n\nUse a split only when the user asks for `split`, `before\u002Fafter`, `versus`, `side by side`, or the analyzed reference is split. A topical phrase such as `X vs Y` does not itself require a split. Replace the normal frame block with a clear halves\u002Fpanels contract and keep all labels out unless short, truthful baked UI was explicitly requested.\n\n## Optional 3D logo\n\nFirst create a 1:1 4K logo render, then use its completed job ID as the last `--image` on every thumbnail call:\n\n```bash\nhiggsfield generate create gpt_image_2 \\\n  --prompt \"Transform the attached 2D logo into a premium 3D logo render: extrude the exact logo shapes into glossy dimensional volumes; preserve every letterform, proportion and brand color; soft studio reflections, subtle bevels, crisp edges, clean dark neutral background, soft contact shadow, centered, generous margins, no extra text, no watermark.\" \\\n  --image .\u002Flogo.png \\\n  --aspect_ratio 1:1 \\\n  --quality high \\\n  --resolution 4k \\\n  --wait --json\n```\n\n## Main render\n\nUse Nano Banana Pro at explicit 4K. Write the final prompt to a temporary text file and pipe it on stdin so punctuation and multiline blocks are preserved safely:\n\n```bash\nhiggsfield generate create nano_banana_pro \\\n  --aspect_ratio 16:9 \\\n  --resolution 4k \\\n  --image .\u002Fface-1.png \\\n  --image .\u002Flogo.png \\\n  --wait --json \u003C thumbnail-prompt.txt\n```\n\nOmit all `--image` flags when there are no references. For a variant set, make one call per distinct prompt. Keep the same references and settings; vary only the selected concept, expression, or camera-take line.\n\nThe completed JSON result contains `id` and `result_url`. Preserve both privately: the URL is delivered; the ID is the source for later edits.\n\n## Post-render gate\n\nInspect every result with host vision when available:\n\n- Referenced identities visibly match.\n- No stray text or watermark exists unless baked text was ordered.\n- Explicit baked text matches character-for-character.\n- The face\u002Femotion and hero element remain readable at about 120px wide.\n- The concept truthfully matches the video promise.\n\nOn a hard failure, retry the same prompt at most twice. If visual inspection is unavailable, do not claim it passed; deliver the result for user review. Present every passing variant and let the user pick before making optional tweaks.\n\n## Surgical tweaks\n\nUse the picked completed job ID as the only image input. Keep the edit prompt narrowly scoped and state that every other pixel-level property remains unchanged.\n\n```bash\nhiggsfield generate create seedream_v5_pro \\\n  --prompt \"Change ONLY the person's facial expression to: \u003Cphrase>. Keep identity, face structure, hair, pose, body, clothing, logo, background, lighting and composition EXACTLY unchanged, pixel-faithful. Keep the YouTube thumbnail lighting rig intact.\" \\\n  --image \u003Cpicked_job_id> \\\n  --aspect_ratio 16:9 \\\n  --resolution 2k \\\n  --wait --json\n```\n\nIf `seedream_v5_pro` is absent or rejects the submit, retry once with `seedream_v4_5 --quality high`. For a `4:5` main render, Seedream has no `4:5`; ask before changing the edit to `3:4`, and disclose the crop\u002Fratio change. Each accepted edit becomes the source ID for the next tweak.\n\nCLI compatibility: versions through `1.1.20` can mislabel a `nano_banana_pro` job reference as `nano_banana_pro_job`. If the edit is rejected with a `medias.0...data.type` error, download the picked `result_url` to a local image and retry the same edit with `--image .\u002Fpicked-thumbnail.png`. A local path is auto-uploaded as `media_input`; do not retry the invalid job-id payload.\n\nAllowed tweak scopes: expression only, background replacement only, background recolor only, or rim-light recolor only. Never silently regenerate the full composition for a surgical request.\n\n## Text overlay\n\nKeep the generated image text-free by default. When a headline overlay is requested, read `references\u002Ftext-overlay-bake.md` and use one of its five presets: Beast, Fire, Neon Lime, Clean Glass, or Marker. The overlay path requires an environment capable of rendering HTML canvas; if unavailable, offer either the clean image or an explicitly approved baked-text regeneration. Never pretend an HTML preview is a flattened PNG.\n\n## Delivery\n\nReturn the passing `result_url` values with short semantic labels such as `shock \u002F close-up` or `product \u002F size contrast`. Mention the selected ratio and whether the deliverable is clean, overlay-ready, or text-baked. Do not expose internal prompts, job IDs, or retry mechanics unless the user asks.\n\n## Reference files\n\n- `references\u002Fthumbnail-frameworks.md` — 16 concept frameworks, information-gap rule, truthfulness law.\n- `references\u002Ftext-overlay-bake.md` — five deterministic text-overlay styles and 4K canvas-bake recipe.\n","# Higgsfield YouTube Thumbnail\n\nCreate a clean thumbnail concept, generate each variant through the `higgsfield` CLI, inspect it, and make only requested surgical edits.\n\n## Bootstrap\n\nBefore any generation:\n\n1. If `higgsfield` is missing, install it:\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fhiggsfield-ai\u002Fcli\u002Fmain\u002Finstall.sh | sh\n   ```\n2. If `higgsfield account status` reports `Session expired` or `Not authenticated`, ask the user to run `higgsfield auth login`, then wait.\n3. Confirm the locked model contracts when the catalog may have changed:\n   ```bash\n   higgsfield model get nano_banana_pro --json\n   higgsfield model get gpt_image_2 --json\n   higgsfield model get seedream_v5_pro --json\n   ```\n\n## UX rules\n\n1. Match the user's language. Keep CLI\u002Fmodel mechanics out of normal chat.\n2. Do not ask for facts already present in the brief. Ask one compact question only when a missing choice changes the result.\n3. Never invent claims, outcomes, products, people, screenshots, or statistics that are not true of the video.\n4. Do not print raw JSON or job IDs to the user. Deliver the image URL and a short variant label.\n5. A style-reference thumbnail is for visual analysis only. Never pass it with `--image`; copying its identity or exact composition is forbidden.\n6. Do not use `--count`. Every concept, emotion, or camera take gets its own prompt and generation call.\n7. `use_unlim` is not a current CLI parameter. Never add `--use-unlim`; if the user explicitly asks to use an unlimited allowance, explain that this workflow must run on credits in CLI or through a surface that supports that allowance.\n\n## Intake gates\n\nCollect only what the brief does not answer:\n\n- The video's topic\u002Ftitle and the truthful promise the thumbnail may imply.\n- Exact scene requirements, if any.\n- Who appears: 0–3 people. If a concept needs a person and no face photo was provided, ask whether to use the user, another provided person, or a generic generated character. Never choose silently.\n- Optional style-reference thumbnail. Analyze it with host vision for energy, framing, split layout, palette, and emotion; do not send it to Higgsfield.\n- Optional logo and whether it stays flat or becomes a 3D object.\n- Optional headline, 2–4 words. Default delivery is a clean image with no text. Use a deterministic overlay when the user requests an overlay; bake text into the generated image only when explicitly requested.\n- Ratio: `16:9` for YouTube by default, `9:16` for Shorts, or `4:5` for Instagram.\n- One final concept or a variant set. If unspecified and alternatives would materially help, offer a set of about four. Hard cap: 16 total generations.\n\nIf the user gives an emotion count without names, use this ladder: shock, hype, rage, awe, laugh, fear, smug, charisma, confusion, determination, disgust.\n\n## Concept gate\n\nRead `references\u002Fthumbnail-frameworks.md`. Brainstorm at least five truthful concepts internally, across multiple frameworks, then select the strongest information gap with one focal subject and minimal clutter. Combine frameworks only when the result still reads in under one second at roughly 120px wide.\n\nWhen a reference thumbnail exists, extract this structure before prompting:\n\n```text\nbrief, generic subject pose\u002Faction, elements, location, composition, background,\nsplit (true\u002Ffalse), split_count, person_count, emotion, emotion_detail\n```\n\nThe reference supplies art direction, never a specific identity. User instructions override it field by field.\n\n## Reference order\n\nPass face photos first in character order, then the logo. Repeat `--image` for every reference. When two or more references are attached, the prompt's first line must be a manifest such as:\n\n```text\nIMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.\n```\n\nLocal paths are auto-uploaded. Previous completed job IDs also work as `--image` inputs.\n\n## Prompt contract\n\nAssemble every main-render prompt in this order:\n\n1. **Frame:** `Bold, punchy YouTube-thumbnail composite — poster-grade, photoreal and high-impact, NOT a muted cinematic movie still, \u003Cratio>, single unified frame — no split-screen, no diagonal divide, everything blends smoothly and organically across the same continuous shot.` For `9:16`, add `faces in the upper two-thirds`. A requested graphical representation replaces photoreal language with a clean diagram\u002Fgraphic brief.\n2. **Scene brief:** depict the user's exact content.\n3. **Text:** default `No text, no readable UI labels, no watermark.` For explicit baked headline: `TEXT: bold thumbnail headline text baked into the image, reading exactly \"\u003CTEXT>\" — massive, ultra-legible sans-serif with a clean outline\u002Fglow treatment, placed where it never covers the subject's face. No other text, no watermark.`\n4. **Subjects:** large, foreground-dominant, chest-up or medium-close, filling about 40–60% of the frame. End with `All faces crisply sharp as the anchors of the shot.`\n5. **Key elements:** only signature props\u002Feffects that explain the information gap.\n6. **Logo:** preserve exact shapes, colors, proportions, and letterforms; keep it away from faces.\n7. **Location:** place, time, weather, and atmosphere when relevant.\n8. **Composition:** one power-third hero, clear scale hierarchy, depth, and strong subject\u002Fbackground separation.\n9. **Background:** vivid high-contrast color field or environment, soft vignette and edge falloff; do not divide it unless a split layout was explicitly requested.\n10. **Lighting on people:** `signature YouTube thumbnail lighting rig — strong key light sculpting the face, soft dreamy fill lifting shadows, and defined back light plus hair light tracing a clean bright rim around hair, shoulders and silhouette.` Only the rim may use a colored accent.\n11. **Grade:** vivid, bright, glossy, poster-punchy, deep blacks, crisp highlights, rich saturated colors, cohesive as one image. Restrain it only for an explicit calm\u002Fpremium\u002Fmuted brief.\n\nFor each photo-referenced person, include:\n\n```text\nCHARACTER N: the person from attached face reference #K — IDENTITY LOCK: reproduce\nthis exact person with a photographic identity match — same bone structure, eye shape,\nnose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average,\nor restyle the face. Expression: \u003Cemotion phrase>.\n```\n\n### Split layouts\n\nUse a split only when the user asks for `split`, `before\u002Fafter`, `versus`, `side by side`, or the analyzed reference is split. A topical phrase such as `X vs Y` does not itself require a split. Replace the normal frame block with a clear halves\u002Fpanels contract and keep all labels out unless short, truthful baked UI was explicitly requested.\n\n## Optional 3D logo\n\nFirst create a 1:1 4K logo render, then use its completed job ID as the last `--image` on every thumbnail call:\n\n```bash\nhiggsfield generate create gpt_image_2 \\\n  --prompt \"Transform the attached 2D logo into a premium 3D logo render: extrude the exact logo shapes into glossy dimensional volumes; preserve every letterform, proportion and brand color; soft studio reflections, subtle bevels, crisp edges, clean dark neutral background, soft contact shadow, centered, generous margins, no extra text, no watermark.\" \\\n  --image .\u002Flogo.png \\\n  --aspect_ratio 1:1 \\\n  --quality high \\\n  --resolution 4k \\\n  --wait --json\n```\n\n## Main render\n\nUse Nano Banana Pro at explicit 4K. Write the final prompt to a temporary text file and pipe it on stdin so punctuation and multiline blocks are preserved safely:\n\n```bash\nhiggsfield generate create nano_banana_pro \\\n  --aspect_ratio 16:9 \\\n  --resolution 4k \\\n  --image .\u002Fface-1.png \\\n  --image .\u002Flogo.png \\\n  --wait --json \u003C thumbnail-prompt.txt\n```\n\nOmit all `--image` flags when there are no references. For a variant set, make one call per distinct prompt. Keep the same references and settings; vary only the selected concept, expression, or camera-take line.\n\nThe completed JSON result contains `id` and `result_url`. Preserve both privately: the URL is delivered; the ID is the source for later edits.\n\n## Post-render gate\n\nInspect every result with host vision when available:\n\n- Referenced identities visibly match.\n- No stray text or watermark exists unless baked text was ordered.\n- Explicit baked text matches character-for-character.\n- The face\u002Femotion and hero element remain readable at about 120px wide.\n- The concept truthfully matches the video promise.\n\nOn a hard failure, retry the same prompt at most twice. If visual inspection is unavailable, do not claim it passed; deliver the result for user review. Present every passing variant and let the user pick before making optional tweaks.\n\n## Surgical tweaks\n\nUse the picked completed job ID as the only image input. Keep the edit prompt narrowly scoped and state that every other pixel-level property remains unchanged.\n\n```bash\nhiggsfield generate create seedream_v5_pro \\\n  --prompt \"Change ONLY the person's facial expression to: \u003Cphrase>. Keep identity, face structure, hair, pose, body, clothing, logo, background, lighting and composition EXACTLY unchanged, pixel-faithful. Keep the YouTube thumbnail lighting rig intact.\" \\\n  --image \u003Cpicked_job_id> \\\n  --aspect_ratio 16:9 \\\n  --resolution 2k \\\n  --wait --json\n```\n\nIf `seedream_v5_pro` is absent or rejects the submit, retry once with `seedream_v4_5 --quality high`. For a `4:5` main render, Seedream has no `4:5`; ask before changing the edit to `3:4`, and disclose the crop\u002Fratio change. Each accepted edit becomes the source ID for the next tweak.\n\nCLI compatibility: versions through `1.1.20` can mislabel a `nano_banana_pro` job reference as `nano_banana_pro_job`. If the edit is rejected with a `medias.0...data.type` error, download the picked `result_url` to a local image and retry the same edit with `--image .\u002Fpicked-thumbnail.png`. A local path is auto-uploaded as `media_input`; do not retry the invalid job-id payload.\n\nAllowed tweak scopes: expression only, background replacement only, background recolor only, or rim-light recolor only. Never silently regenerate the full composition for a surgical request.\n\n## Text overlay\n\nKeep the generated image text-free by default. When a headline overlay is requested, read `references\u002Ftext-overlay-bake.md` and use one of its five presets: Beast, Fire, Neon Lime, Clean Glass, or Marker. The overlay path requires an environment capable of rendering HTML canvas; if unavailable, offer either the clean image or an explicitly approved baked-text regeneration. Never pretend an HTML preview is a flattened PNG.\n\n## Delivery\n\nReturn the passing `result_url` values with short semantic labels such as `shock \u002F close-up` or `product \u002F size contrast`. Mention the selected ratio and whether the deliverable is clean, overlay-ready, or text-baked. Do not expose internal prompts, job IDs, or retry mechanics unless the user asks.\n\n## Reference files\n\n- `references\u002Fthumbnail-frameworks.md` — 16 concept frameworks, information-gap rule, truthfulness law.\n- `references\u002Ftext-overlay-bake.md` — five deterministic text-overlay styles and 4K canvas-bake recipe.\n",{"name":5,"version":52,"description":53,"allowed-tools":32,"argument-hint":54},"0.14.0","Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a truthful information-gap concept, preserves up to three referenced identities, supports logos and controlled variants, renders the main image with Nano Banana Pro, and applies focused Seedream edits. Use when: \"make a YouTube thumbnail\", \"thumbnail for this video\", \"MrBeast-style cover\", \"Shorts cover\", or \"Instagram video cover\". Chain after any video workflow once its truthful topic and visual direction are known. NOT for producing the video itself (use higgsfield-generate), product catalog photos (use higgsfield-product-photoshoot), or marketplace cards (use higgsfield-marketplace-cards).\n","[video-topic-or-title] [--image \u003Cface-or-logo>] [--ratio 16:9|9:16|4:5]","7092b664627bf326748a6fcbf27fee6a34c4da1d","skills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill higgsfield-youtube-thumbnail",{"tool":68,"command":69},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill higgsfield-youtube-thumbnail",{"tool":71,"command":72},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill higgsfield-youtube-thumbnail","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail\u002FSKILL.md",true,[76,82,86],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"agents\u002Fopenai.yaml","REFERENCE","参考文档",230,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail\u002Fagents\u002Fopenai.yaml",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ftext-overlay-bake.md",11356,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail\u002Freferences\u002Ftext-overlay-bake.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fthumbnail-frameworks.md",4063,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-youtube-thumbnail\u002Freferences\u002Fthumbnail-frameworks.md",[91,99,107,114,121,128],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":98},"01M767791C1KRP2ZRW2Z73VZ5Q","system-lifecycle-designer","Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fmy_skills\u002Fsystem-lifecycle-designer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":106},"01M748ABPN5F1FANHH6HKZQMXT","style-sampling","Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for \"an episode of\", \"in the style of\", \"sample this style\", 「用这个风格做一集」. One video to copy is reverse-any-video.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Fstyle-sampling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":106},"01M748A59V04PKW4HA0XQ81FGP","reverse-any-video","Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Freverse-any-video\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":106},"01M7487T50P55CSXMWXZ0G9KRG","typescript-patterns","TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftypescript-patterns\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":106},"01M7487ERZRGPC5NJ75077Y238","test-collaboration","Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit\u002Fintegration\u002Fcontract\u002FE2E\u002Fsmoke classification, bug-to-test regression protection, consumer\u002Fprovider contract testing, test-necessity review, and pre-delivery evidence review.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftest-collaboration\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":106},"01M748721J3GKR2WS6K0QWFC35","story-lifecycle","Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira\u002FLinear\u002FTaiga but needs structured delivery tracking.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fstory-lifecycle\u002FSKILL.md",[],[]]