[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M733D02APSQVD2Y9ASAV0QWX":3,"skill-same:01M733D02APSQVD2Y9ASAV0QWX":50},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M733D02APSQVD2Y9ASAV0QWX","hivemindos-brand-visuals",null,"Generate and deliver HivemindOS brand visuals — logos, sigils, abstract emblems, banners, and other identity assets — using one clear visual thesis, genuinely distinct directions, mark-first review, verified image outputs, and the correct delivery target.","LiamVisionary\u002Fhivemindos","LiamVisionary","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F102138294?v=4","01M73379NZZ99TT4ZS17XR3Q9D","01M73379PX6AKQNWN05VNSYRXW",13,"MIT","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fpackaged-skills\u002Foptional\u002Fbrand\u002Fhivemindos\u002Fhivemindos-brand-visuals\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: hivemindos-brand-visuals\ndescription: Generate and deliver HivemindOS brand visuals — logos, sigils, abstract emblems, banners, and other identity assets — using one clear visual thesis, genuinely distinct directions, mark-first review, verified image outputs, and the correct delivery target.\n---\n\n# HivemindOS Brand Visuals\n\nUse this skill when the user wants a HivemindOS-branded visual asset generated, verified, and delivered somewhere practical for sharing.\n\nThis is the umbrella for:\n- abstract sigils and emblems\n- logo-like identity graphics\n- brand banners and social imagery\n- image-only delivery flows where the image itself is the product\n\n## Core workflow\n\n1. Clarify the destination only if needed.\n   - If the request says Telegram or another platform explicitly, use that target.\n   - If the request is just to generate the image, deliver locally or return the file path.\n\n2. Write the brand job in one concrete sentence:\n   - `[Brand] is a [specific product] for [specific audience] that should signal [specific promise].`\n   - If the product, audience, or promise is unknown and materially changes the result, ask.\n\n3. Choose one sharp visual thesis.\n   - Use one primary metaphor or meaning-bearing mechanism.\n   - Add at most one supporting geometric device.\n   - Do not force every brand trait into the mark.\n\n4. Generate the image with:\n   - logo, emblem, sigil, or identity-system language appropriate to the request\n   - no readable text unless typography is explicitly part of the direction\n   - high contrast and centered composition for mark-only studies\n\n5. Verify the output is a real image.\n   - Check file type, dimensions, and size.\n   - Reject blank, tiny, or corrupted outputs.\n\n6. Review the mark before polishing the presentation.\n   - Inspect it alone on a neutral background and at small size.\n   - Reject a concept that only looks good because of mockup lighting, texture, or scenery.\n   - Apply the chosen mark to mockups only after its silhouette and visual idea hold up.\n\n7. Deliver the image in the requested channel.\n   - For Telegram or similar chat delivery, send the image as media rather than pasting text.\n   - Keep captions minimal unless the user asked for copy.\n\n## Prompting guidance\n\n- Start from the concrete product, audience, and visual thesis. A prompt recipe without that grounding tends to collapse into generic category imagery.\n- Treat hexagons as one option, not a diagnosis or house default. Hexes are not inherently difficult; semantic overconstraint is. Do not automatically stack hexagons, honeycombs, nodes, swarm motion, protected cores, sacred geometry, and intelligence symbolism.\n- Prefer one visual sentence, such as “independent parts forming a calm whole” or “a protected opening into coordinated work.” Translate that sentence into shape, negative space, rhythm, or typography.\n- Delete prestige adjectives that do not change a visible decision. Piles of words such as “timeless,” “iconic,” “luxurious,” “sophisticated,” and “meaningful” usually add noise rather than direction.\n- When generating multiple directions, change the underlying system:\n  - metaphor\n  - silhouette and negative space\n  - geometric versus organic construction\n  - symbol versus monogram versus wordmark\n  - typography and proportion\n  Do not submit the same node network or honeycomb in different colors.\n- For HivemindOS, avoid literal bees, robot heads, brains, and generic AI node graphs unless the user explicitly chooses one of those directions.\n- Once a direction wins, iterate one variable at a time instead of rewriting the entire prompt.\n- Use negative prompts to suppress text, watermarking, blur, and low-quality artifacts.\n\n## Diagnosing repetitive results\n\n- If every option feels like the same generic AI-infrastructure logo, hold the prompt structure constant and test it on unrelated concrete brands. If the outputs improve, the original brand semantics were overloaded; if they still converge, the prompt recipe is the problem.\n- Make each test brand concrete enough to imply a distinct form language. Changing only the invented name is not a meaningful test.\n- Separate generator quality from art direction quality. A technically polished image can still be a weak identity concept.\n\n## Verification checklist\n\n- The file opens as a valid image\n- The dimensions are reasonable for the task\n- The file size is non-trivial\n- The image actually contains a visible composition\n- Each proposed direction has a distinct visual thesis and silhouette\n- The preferred mark still works without presentation-board polish\n\n## Delivery guidance\n\n- Prefer native media upload paths over inline links when the platform supports it.\n- Discover the correct target if the platform has multiple DMs\u002Fchannels.\n- Keep the message body minimal for image-first delivery.\n\n## Pitfalls\n\n- Do not return a file path without verifying it exists.\n- Do not assume a generated image is good just because the job completed.\n- Do not include unreadable text in the design unless the user explicitly wants typography.\n- Do not hard-code platform targets when the environment provides a discovery step.\n- Do not present a raster image-model concept as a finished vector identity, an original trademark, or a trademark-safe mark. Treat it as concept exploration that still needs vector construction and clearance.\n\n## Support files\n\nUse `references\u002F` for prompt variants, platform-specific delivery notes, and example compositions.\nUse `templates\u002F` for reusable prompt skeletons.\nUse `scripts\u002F` for repeatable checks or delivery helpers.\n","# HivemindOS Brand Visuals\n\nUse this skill when the user wants a HivemindOS-branded visual asset generated, verified, and delivered somewhere practical for sharing.\n\nThis is the umbrella for:\n- abstract sigils and emblems\n- logo-like identity graphics\n- brand banners and social imagery\n- image-only delivery flows where the image itself is the product\n\n## Core workflow\n\n1. Clarify the destination only if needed.\n   - If the request says Telegram or another platform explicitly, use that target.\n   - If the request is just to generate the image, deliver locally or return the file path.\n\n2. Write the brand job in one concrete sentence:\n   - `[Brand] is a [specific product] for [specific audience] that should signal [specific promise].`\n   - If the product, audience, or promise is unknown and materially changes the result, ask.\n\n3. Choose one sharp visual thesis.\n   - Use one primary metaphor or meaning-bearing mechanism.\n   - Add at most one supporting geometric device.\n   - Do not force every brand trait into the mark.\n\n4. Generate the image with:\n   - logo, emblem, sigil, or identity-system language appropriate to the request\n   - no readable text unless typography is explicitly part of the direction\n   - high contrast and centered composition for mark-only studies\n\n5. Verify the output is a real image.\n   - Check file type, dimensions, and size.\n   - Reject blank, tiny, or corrupted outputs.\n\n6. Review the mark before polishing the presentation.\n   - Inspect it alone on a neutral background and at small size.\n   - Reject a concept that only looks good because of mockup lighting, texture, or scenery.\n   - Apply the chosen mark to mockups only after its silhouette and visual idea hold up.\n\n7. Deliver the image in the requested channel.\n   - For Telegram or similar chat delivery, send the image as media rather than pasting text.\n   - Keep captions minimal unless the user asked for copy.\n\n## Prompting guidance\n\n- Start from the concrete product, audience, and visual thesis. A prompt recipe without that grounding tends to collapse into generic category imagery.\n- Treat hexagons as one option, not a diagnosis or house default. Hexes are not inherently difficult; semantic overconstraint is. Do not automatically stack hexagons, honeycombs, nodes, swarm motion, protected cores, sacred geometry, and intelligence symbolism.\n- Prefer one visual sentence, such as “independent parts forming a calm whole” or “a protected opening into coordinated work.” Translate that sentence into shape, negative space, rhythm, or typography.\n- Delete prestige adjectives that do not change a visible decision. Piles of words such as “timeless,” “iconic,” “luxurious,” “sophisticated,” and “meaningful” usually add noise rather than direction.\n- When generating multiple directions, change the underlying system:\n  - metaphor\n  - silhouette and negative space\n  - geometric versus organic construction\n  - symbol versus monogram versus wordmark\n  - typography and proportion\n  Do not submit the same node network or honeycomb in different colors.\n- For HivemindOS, avoid literal bees, robot heads, brains, and generic AI node graphs unless the user explicitly chooses one of those directions.\n- Once a direction wins, iterate one variable at a time instead of rewriting the entire prompt.\n- Use negative prompts to suppress text, watermarking, blur, and low-quality artifacts.\n\n## Diagnosing repetitive results\n\n- If every option feels like the same generic AI-infrastructure logo, hold the prompt structure constant and test it on unrelated concrete brands. If the outputs improve, the original brand semantics were overloaded; if they still converge, the prompt recipe is the problem.\n- Make each test brand concrete enough to imply a distinct form language. Changing only the invented name is not a meaningful test.\n- Separate generator quality from art direction quality. A technically polished image can still be a weak identity concept.\n\n## Verification checklist\n\n- The file opens as a valid image\n- The dimensions are reasonable for the task\n- The file size is non-trivial\n- The image actually contains a visible composition\n- Each proposed direction has a distinct visual thesis and silhouette\n- The preferred mark still works without presentation-board polish\n\n## Delivery guidance\n\n- Prefer native media upload paths over inline links when the platform supports it.\n- Discover the correct target if the platform has multiple DMs\u002Fchannels.\n- Keep the message body minimal for image-first delivery.\n\n## Pitfalls\n\n- Do not return a file path without verifying it exists.\n- Do not assume a generated image is good just because the job completed.\n- Do not include unreadable text in the design unless the user explicitly wants typography.\n- Do not hard-code platform targets when the environment provides a discovery step.\n- Do not present a raster image-model concept as a finished vector identity, an original trademark, or a trademark-safe mark. Treat it as concept exploration that still needs vector construction and clearance.\n\n## Support files\n\nUse `references\u002F` for prompt variants, platform-specific delivery notes, and example compositions.\nUse `templates\u002F` for reusable prompt skeletons.\nUse `scripts\u002F` for repeatable checks or delivery helpers.\n",{"name":5,"description":7},"main","f270c4ae4f9d09c4e5da9cfa8adab7e89ae1f53e","packaged-skills\u002Foptional\u002Fbrand\u002Fhivemindos\u002Fhivemindos-brand-visuals",4,"https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos","https:\u002F\u002Fgithub.com\u002FLiamVisionary","2026-11-10 21:48:41",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add LiamVisionary\u002Fhivemindos --skill hivemindos-brand-visuals",{"tool":36,"command":37},"bunx","bunx skills add LiamVisionary\u002Fhivemindos --skill hivemindos-brand-visuals",{"tool":39,"command":40},"pnpm","pnpm dlx skills add LiamVisionary\u002Fhivemindos --skill hivemindos-brand-visuals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fpackaged-skills\u002Foptional\u002Fbrand\u002Fhivemindos\u002Fhivemindos-brand-visuals\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},".hivemind-skill-source.json","REFERENCE","参考文档",987,"https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fpackaged-skills\u002Foptional\u002Fbrand\u002Fhivemindos\u002Fhivemindos-brand-visuals\u002F.hivemind-skill-source.json",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M734AA85KQEXDQXQJ3T7769M","tailscale-generation-skill-authoring","This skill should be used when the user asks to \"create a Tailscale generation skill\", \"add a local generation skill\", \"document a generation endpoint\", \"add an image generation provider\", \"add a TTS provider\", \"add video generation\", \"add 3D generation\", or needs guidance on where HivemindOS Tailscale or local generation providers belong in the shared skills shelf.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Ftailscale-generation-skill-authoring\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M734A7VD69PRA0C0EV5EFY9T","localtts","This skill should be used when the user asks to \"generate local TTS\", \"use local text to speech\", \"use remote TTS over Tailscale\", \"make speech audio\", \"add a TTS provider\", \"use Qwen3-TTS\", or needs TTS endpoint setup through local or HivemindOS Tailscale routes.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Flocaltts\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M734A4K2Z0F74QZP7V7WBFRY","karpathy-guidelines","Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Fkarpathy-guidelines\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M734A1HMVYVJX3YJGNQ6KF6C","comfyui-image-generation","This skill should be used when the user asks to \"generate images\", \"generate images with ComfyUI\", \"use local ComfyUI\", \"use remote ComfyUI\", \"use Z-Image\", \"add an image generation provider\", or needs image-generation endpoint setup through local or HivemindOS Tailscale routes.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Fcomfyui-image-generation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7349Y684Q676DNNHZPSC8W1","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Fcloudflare\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7349V3WCBF835QP74SA9Q8C","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FLiamVisionary\u002Fhivemindos\u002Fblob\u002Fmain\u002Fskills\u002Fcloudflare\u002Fworkers-best-practices\u002FSKILL.md",[],[]]