[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M98KSSWXGN09G0EFCT11Y4":3,"skill-same:01M6M98KSSWXGN09G0EFCT11Y4":117},{"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":34,"publishedAt":63,"linkOnly":64,"markdownContent":65,"markdownBody":66,"frontMatter":67,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":76,"ownerHtmlUrl":77,"ownerBlogUrl":78,"ownerDescription":79,"updatedAt":80,"install":81,"resources":94},"01M6M98KSSWXGN09G0EFCT11Y4","suede-image",null,"Use when asked \"create an Open Graph image\" or to produce marketing heroes, banners, social graphics, mockups or image workflows. Suede AI chooses generation, editing, templates or real screenshots, then specifies layout, rights, export sizes, compression and image SEO. NOT FOR: paid-ad systems (use suede-ad-creative), video (use suede-video), app-store assets (use suede-aso), or social strategy (use suede-social).","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002FSKILL.md",[18,23,26,31],{"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},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":32,"categoryName":33,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000035","市场营销",[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62],"suede image","image","use","Banners","ai image","for","rights","ad","store","app","systems","layout","social","social strategy","export","strategy","editing","assets","aso","marketing","open","Video","seo","graph","create","workflows","graphics","screenshots","2026-11-10 10:12:30",false,"---\nname: suede-image\ndescription: \"Use when asked \\\"create an Open Graph image\\\" or to produce marketing heroes, banners, social graphics, mockups or image workflows. Suede AI chooses generation, editing, templates or real screenshots, then specifies layout, rights, export sizes, compression and image SEO. NOT FOR: paid-ad systems (use suede-ad-creative), video (use suede-video), app-store assets (use suede-aso), or social strategy (use suede-social).\"\nmetadata:\n  display-name: \"Suede AI Image Skills\"\n  version: 2.1.0\n---\n\n# Suede AI Image Skills\n\nProduce marketing imagery as a rights-aware, placement-specific system: choose the right production method, protect canonical brand assets, preserve real product truth, and verify the exported result. Use generation models and design tools to create efficient hero, social, mockup, banner, and preview workflows without fabricating interfaces or provenance.\n\n## Compatibility\n\nAn agent with visual inspection and access to supplied brand assets. Image production requires an available generation or editing tool; local export commands require their named utilities. Prompt-only delivery remains available when production tools are absent.\n\n## Before Starting\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing.md` exists (or `.claude\u002Fproduct-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Image Goal\n- What type of image? (Blog hero, social graphic, product mockup, banner, brand asset, OG image)\n- What platform or placement? (Website, social, directory listing, app store, email)\n- What dimensions do you need?\n\n### 2. Production Approach\n- Do you have existing brand assets? (Logo, colors, fonts, style guide)\n- Do you need photorealistic or illustrative style?\n- Is this a one-off or a template for repeated use?\n\n### 3. Technical Context\n- Which image, browser, design, or local conversion tools are currently callable?\n- What is the approved maximum cost and data-handling boundary?\n- Do you need the image optimized for web performance?\n\nDo not ask the user to paste API keys or secrets into the conversation.\n\n---\n\n## Choosing Your Approach\n\nFirst discover the current production surface. Inspect callable tools and connected\naccounts; do not assume a named model, provider, API, plugin, or design app is\navailable. Then choose among these methods:\n\n| Approach | Best For | Candidate surface |\n|----------|----------|-------------------|\n| **Generation** | Original concepts and scenes | A callable image-generation tool |\n| **Editing** | Authorized changes to supplied images | A callable editor with image-input support |\n| **Template design** | Brand-consistent recurring assets | An authorized design app or local template |\n| **Screenshot + overlay** | Truthful product showcases | Callable browser capture plus local layout |\n| **Licensed media** | Existing photography or illustration | User-owned library or verified license source |\n\n---\n\n## AI Image Generation\n\nUse generation only after the current tool and authority gates pass.\n\n### Capability and authority gate\n\n1. Confirm a generation or editing tool is callable in the current session.\n2. Check its current official documentation for model availability, accepted\n   inputs, output sizes, editing\u002Freference support, safety restrictions, retention,\n   commercial-use terms, and pricing. Record the source and check date.\n3. Confirm rights to every uploaded logo, screenshot, photo, font, and reference\n   image. Do not upload confidential or personal material outside its approved\n   boundary.\n4. Calculate the maximum cost for the requested attempts and get explicit approval\n   before using a paid account or exceeding an already approved budget.\n5. Confirm whether the user's request authorizes generation only, editing of\n   supplied files, overwriting a source, or publication. These are separate gates.\n\nProvider names and model versions are volatile. Examples such as OpenAI, Google,\nBlack Forest Labs, Ideogram, Midjourney, Recraft, and self-hosted diffusion are\nresearch candidates, not routing instructions or capability claims.\n\n### Selection criteria\n\n- For text-heavy assets, prefer a deterministic overlay or design template; test\n  any verified in-image text capability before committing to it.\n- For repeated brand work, prefer locked templates and approved assets over a\n  claimed consistency feature.\n- For edits, use a tool whose current documentation and callable schema confirm\n  image input and the required edit mode.\n- For vectors, require a real vector export and inspect its paths; a raster image\n  labeled as vector is not sufficient.\n- For product UI, capture the live authorized interface rather than generating it.\n- For volume, compare verified cost, rate limits, review time, and output quality\n  on a small test batch.\n\nIf no suitable renderer or editor is callable, deliver a production-ready prompt,\nlayout spec, asset manifest, rights checklist, and export checklist. State clearly\nthat no image was generated; do not route the user to an unavailable tool as\nthough execution occurred. Use these exact headings:\n\n```markdown\n## Prompt\n\u003CSubject + Setting + Style + Lighting + Composition + Technical, one block,\nready to paste; note any text that must be a deterministic overlay instead>\n\n## Layout Spec\nCanvas WxH + ratio | safe margins | focal point | text zones with max character\ncounts | logo placement and clear space | color values\n\n## Asset Manifest\nAsset | origin (owned \u002F licensed \u002F captured \u002F to be generated) | rights basis\nand holder | attribution or expiry | file path or \"to source\"\n\n## Rights Checklist\n- [ ] Every uploaded or referenced asset has a confirmed rights basis\n- [ ] No real person, endorsement, or product interface is fabricated\n- [ ] Brand mark is the approved file, unmodified, or omitted\n- [ ] Paid-tool cost approved, or no paid tool used\n\n## Export Checklist\nDestination | dimensions | format | quality target | file-size budget | alt text\nThen apply the Optimization Checklist in \"Image Optimization\" before delivery.\n\n## Not Done\nNo image was generated. What would unblock production: \u003Ctool, authority, asset>\n```\n\n### Prompting Basics\n\nA strong image prompt follows: **Subject + Setting + Style + Lighting + Composition + Technical**\n\n```\nA laptop on a minimal white desk with an abstract analytics motif,\nsoft directional lighting from the left, shallow depth of field,\nclean commercial photography style, 16:9 aspect ratio, 4K\n```\n\n**Common mistakes:**\n- Too vague (\"a business image\"): add specific details\n- Forgetting aspect ratio: always specify dimensions\n- Requesting complex text: use overlays instead for anything beyond short headlines\n- No style direction: \"photorealistic,\" \"flat illustration,\" \"3D render\"\n\nFor detailed prompting guides per model, see [references\u002Fai-image-prompting.md](references\u002Fai-image-prompting.md).\n\n---\n\n## Design Tools\n\nFor templated, brand-consistent work where AI generation is overkill or too unpredictable.\n\n### Canva\n\nCan be a candidate for template-driven social graphics, presentations, email\nheaders, and banners. Verify the connected account, current features, export\nrights, plan limits, API availability, and callable integration before routing\nwork to it. Keep a human review gate for brand output.\n\n### Figma\n\nCan be a candidate when an authorized design file or component system exists.\nVerify current account access and whether the available integration can read,\nedit, export, or only inspect. Do not claim write access or create files merely\nbecause a connector exists.\n\n### When to Use Design Tools vs. AI Generation\n\n| Scenario | Design Tool | AI Generation |\n|----------|:-:|:-:|\n| Exact brand guidelines must be followed | Yes | Maybe (with strong ref images) |\n| Need many size variants of one design | Yes, if current resize\u002Fexport capability is verified | Usually no |\n| Unique hero image for a blog post | No | Yes |\n| Recurring social media template | Yes | No |\n| Product mockup with real UI | No (use screenshots) | No (hallucinated UI) |\n| Abstract\u002Fcreative visual | No | Yes |\n\n---\n\n## Marketing Image Workflows\n\n### Blog & Article Hero Images\n\nThe image at the top of every post. Sets tone, improves shareability, required for OG\u002Fsocial previews.\n\n1. **Define the concept**: what visual metaphor represents the topic?\n2. **Choose the verified method**: callable generator, approved media, or a\n   deterministic local\u002Fdesign template\n3. **Confirm dimensions** from the actual site component and current social\n   preview requirements\n4. **Optimize to a measured quality and performance budget**\n\n**Prompt pattern:**\n```\n[Visual metaphor for topic], clean modern style,\nbright natural lighting, shallow depth of field,\nprofessional blog header aesthetic, [verified width]x[verified height]\n```\n\n### Social Media Graphics\n\nPlatform-specific images for organic posts.\n\nThe values below are planning defaults, not current platform guarantees. Check the\nplatform's official specification on the work date and use its current safe zones,\nfile limits, and format rules.\n\n| Platform | Planning size | Aspect ratio | Notes |\n|----------|-------------|:---:|-------|\n| X | 1200x675 | 16:9 | Large image card |\n| LinkedIn | 1200x627 | 1.91:1 | Feed image |\n| Instagram Feed | 1080x1350 | 4:5 | Profile grid crops to 3:4 since January 2025; keep the subject centered |\n| Instagram Stories | 1080x1920 | 9:16 | Full screen vertical |\n| Facebook | 1200x630 | 1.91:1 | Link share image |\n\n**Workflow:**\n1. Create the hero concept at highest resolution needed\n2. Use a verified resize\u002Fexport feature or manual crop for platform variants\n3. Add text overlays deterministically when accurate text is required\n4. Export at platform-specific dimensions\n\n### Product Mockups & Screenshots\n\nShowcase your product UI in context. AI models hallucinate UI: don't use them for this.\n\n1. **Capture real screenshots** of your product at 2x resolution\n2. **Frame in device mockups**: use browser frame, laptop, or phone templates\n3. **Add context**: callout arrows, verified feature labels, before\u002Fafter comparisons\n4. **Annotate deterministically**: use a callable local layout workflow or an\n   authorized design tool\n\nPossible capture surfaces include browser tooling or an installed OS capture\nutility. Discover what is currently callable, confirm authorization for the live\nsurface, and omit tools that are not available.\n\n### Profile & Listing Banners\n\nBanners for profiles, directory listings, and marketplace pages. Often the first visual impression.\n\nThese are planning references and can drift. Verify current official dimensions,\ncropping behavior, safe zones, file limits, and format rules before production.\n\n| Platform | Planning size | Notes |\n|----------|------|-------|\n| LinkedIn personal cover | 1584x396 | 4:1, safe zone center |\n| LinkedIn company cover | 1128x191 | 5.9:1; LinkedIn recommends up to 4200x700 |\n| Twitter\u002FX header | 1500x500 | 3:1, partially obscured by avatar |\n| Product Hunt gallery | 1270x760 | 5:3, up to 6 images |\n| G2 profile | 1280x720 | 16:9, product screenshots preferred |\n| GitHub social preview | 1280x640 | 2:1, shows in link cards |\n| App Store screenshots | Varies by device | See suede-aso skill for full specs |\n| Google Play feature graphic | 1024x500 | ~2:1, required for store listing |\n\n**Best practices:**\n- **Keep text minimal**: banners are seen at small sizes on mobile\n- **Center critical content**: edges get cropped differently per device\n- **Show the product truthfully**: use real UI screenshots when the listing is\n  meant to demonstrate the interface\n- **Match your brand**: use consistent colors, fonts, logo placement\n- **Update deliberately**: refresh when the product, campaign, or positioning changes\n\n**Workflow:**\n1. Pick the platform(s) and note exact dimensions\n2. For directories (Product Hunt, G2): use real product screenshots with light annotation\n3. For profiles (LinkedIn, Twitter): use brand colors + tagline + optional product shot\n4. Produce with a verified callable template workflow; add text deterministically\n5. Test at actual display size: zoom out to check readability\n\n### Brand Assets\n\nLogos, icons, and illustrations. AI generation has limits here.\n\n| Asset | AI Generation | Design Tool | Notes |\n|-------|:-:|:-:|-------|\n| Logo | Poor: inconsistent, not vector | Yes | Always design or commission logos |\n| App icon | Concept exploration only | Yes | Refine manually and verify store rules |\n| Illustrations | Good for style exploration | Depends | AI for concepts, finalize in design tool |\n| Favicons | No | Yes | Derive from logo |\n| Social icons | No | Yes | Use platform-provided assets |\n\n---\n\n## Image Optimization\n\nImage bytes and dimensions can affect page performance. Measure the actual page\nbefore attributing search or conversion results to image changes.\n\n### Format Guide\n\n| Format | Best For | Compression |\n|--------|----------|-------------|\n| **WebP** | Photos and graphics when target browsers support it | Lossy + lossless |\n| **AVIF** | High-compression delivery when target browsers support it | Lossy + lossless |\n| **JPEG** | Broad photo compatibility | Lossy |\n| **PNG** | Transparency and lossless screenshots | Lossless |\n| **SVG** | Trusted vector logos, icons, and illustrations | Vector |\n\n### Optimization Checklist\n\n- [ ] **Use a supported delivery format** and fallback strategy for the target browser matrix\n- [ ] **Resize to display size**: don't serve 4000px images in 800px containers\n- [ ] **Compress**: choose quality from visual review and the page's measured byte budget\n- [ ] **Lazy load** below-the-fold images (`loading=\"lazy\"`)\n- [ ] **Set explicit dimensions**: `width` and `height` attributes prevent layout shift (CLS)\n- [ ] **Use verified CDN optimization** when the current stack supports it\n- [ ] **Add alt text**: describe what the image shows in plain words, using the\n  page's topic phrase only where it is the honest description\n- [ ] **Name files descriptively**: `pricing-calculator-dashboard.webp`, not\n  `IMG_2041.webp`\n- [ ] **Keep important images crawlable**: a real `\u003Cimg>` with `src`, not a CSS\n  background, and not blocked in robots.txt\n- [ ] **Place the image near the text it illustrates** and give charts a\n  caption that states the finding, so search and AI answers can quote it\n\nThe largest above-the-fold image is usually the Largest Contentful Paint\nelement. Do not lazy-load it; give it `fetchpriority=\"high\"` and explicit\ndimensions. Core Web Vitals and image-indexing audits route to\n`suede-seo-audit`.\n\n### Quick Optimization Commands\n\n```bash\n# Run only after confirming the named local utility is installed.\n# Convert to WebP (using cwebp)\ncwebp -q 80 input.png -o output.webp\n\n# Batch convert with ImageMagick\nmogrify -format webp -quality 80 *.png\n\n# Optimize JPEG (using jpegoptim)\njpegoptim --max=80 --strip-all *.jpg\n```\n\nTo inspect image references on a page, use the host's approved read-only HTTP\nor browser tool against a verified public HTTPS URL. Refuse loopback,\nlink-local, or private-network destinations; do not attach ambient cookies or\nauthentication headers; and do not send local files, credentials, or workspace\ncontent. Inspect the returned HTML for image `src` values and report a failed or\nunsafe fetch as unverified.\n\n---\n\n## OG & Social Preview Images\n\nThe image that appears when your URL is shared on social media, Slack, Discord, etc.\n\n### Common Meta Tags\n\nVerify the current crawler\u002Fplatform specification and use absolute public URLs.\nThe values below are a starting template, not proof of platform compliance.\n\n```html\n\u003Cmeta property=\"og:image\" content=\"https:\u002F\u002Fyoursite.com\u002Fog\u002Fpage-name.jpg\" \u002F>\n\u003Cmeta property=\"og:image:width\" content=\"1200\" \u002F>\n\u003Cmeta property=\"og:image:height\" content=\"630\" \u002F>\n\u003Cmeta name=\"twitter:card\" content=\"summary_large_image\" \u002F>\n\u003Cmeta name=\"twitter:image\" content=\"https:\u002F\u002Fyoursite.com\u002Fog\u002Fpage-name.jpg\" \u002F>\n```\n\n### Dynamic OG Images\n\nGenerate OG images programmatically for dynamic pages only after verifying the\nproject's current framework, installed packages, and supported runtime:\n\n- An installed framework-native image route\n- A local HTML\u002FSVG-to-image renderer\n- An authorized media service with verified template and export capabilities\n\nFor repeated page types, a deterministic template can reduce manual work. Measure\npreview correctness and production time; do not promise a search outcome.\n\n---\n\n## Common Mistakes\n\n1. **Skipping image optimization**: oversized images can materially hurt page performance\n2. **No preview image**: platforms may fall back to a less useful preview\n3. **Inconsistent brand visuals**: use locked, approved templates for consistency\n\n---\n\n## Halt Contract\n\nUse this exact format when a callable tool, cost approval, rights confirmation,\nor the approved brand asset blocks the requested result:\n\n```text\nHALT: \u003Cone-line blocker>\nWhy it blocks: \u003Cspecific missing authority or evidence>\nResolve with:\n1. \u003Coption>\n2. \u003Coption>\n3. \u003Coption, when useful>\nWaiting for: \u003Cthe exact item or approval>\n```\n\nContinue with the no-tool handoff artifacts above only when they remain useful\nand do not imply an image was produced.\n\n---\n\n## Boundaries\n\n- For Suede visuals, use only `docs\u002Fassets\u002Fsuede-ai-logo-transparent.png` with SHA-256 `83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa`.\n- Do not redraw, trace, approximate, recolor, distort, typeset, or generate a replacement for the approved Suede S mark. If the canonical file is missing or its checksum differs, omit the mark, name the blocker, and request the approved file.\n- Do not claim an image is licensed, rights-cleared, authentic, accessible, optimized, or platform-compliant without verifying the relevant source or output.\n- Do not use a paid provider, upload protected material, or cross an approved\n  account or data boundary without explicit authority and a verified maximum cost.\n- Do not publish, overwrite source assets, or replace real product screenshots without explicit authorization.\n- Do not invent people, endorsements, product interfaces, performance results, or provenance, and do not decide rights or brand exceptions for the user.\n\n## Routing\n\n- Use `suede-ad-creative` for paid-ad production and `suede-video` for motion.\n- Use `suede-social` for channel strategy and `suede-site-alchemy` for conversion placement.\n- Use `suede-social` for platform format contracts (Reel covers, carousel slide counts, Story frames) before producing those assets here.\n- Use `suede-seo-audit` for image-search checks and `suede-aso` for app-store screenshots.\n- Use `suede-directory-submissions` for directory gallery planning.\n\n## Worked contract\n\n[Worked contract](references\u002Fusage-contract.md) gives a bounded input, expected output and failure check for this workflow.\n","# Suede AI Image Skills\n\nProduce marketing imagery as a rights-aware, placement-specific system: choose the right production method, protect canonical brand assets, preserve real product truth, and verify the exported result. Use generation models and design tools to create efficient hero, social, mockup, banner, and preview workflows without fabricating interfaces or provenance.\n\n## Compatibility\n\nAn agent with visual inspection and access to supplied brand assets. Image production requires an available generation or editing tool; local export commands require their named utilities. Prompt-only delivery remains available when production tools are absent.\n\n## Before Starting\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing.md` exists (or `.claude\u002Fproduct-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Image Goal\n- What type of image? (Blog hero, social graphic, product mockup, banner, brand asset, OG image)\n- What platform or placement? (Website, social, directory listing, app store, email)\n- What dimensions do you need?\n\n### 2. Production Approach\n- Do you have existing brand assets? (Logo, colors, fonts, style guide)\n- Do you need photorealistic or illustrative style?\n- Is this a one-off or a template for repeated use?\n\n### 3. Technical Context\n- Which image, browser, design, or local conversion tools are currently callable?\n- What is the approved maximum cost and data-handling boundary?\n- Do you need the image optimized for web performance?\n\nDo not ask the user to paste API keys or secrets into the conversation.\n\n---\n\n## Choosing Your Approach\n\nFirst discover the current production surface. Inspect callable tools and connected\naccounts; do not assume a named model, provider, API, plugin, or design app is\navailable. Then choose among these methods:\n\n| Approach | Best For | Candidate surface |\n|----------|----------|-------------------|\n| **Generation** | Original concepts and scenes | A callable image-generation tool |\n| **Editing** | Authorized changes to supplied images | A callable editor with image-input support |\n| **Template design** | Brand-consistent recurring assets | An authorized design app or local template |\n| **Screenshot + overlay** | Truthful product showcases | Callable browser capture plus local layout |\n| **Licensed media** | Existing photography or illustration | User-owned library or verified license source |\n\n---\n\n## AI Image Generation\n\nUse generation only after the current tool and authority gates pass.\n\n### Capability and authority gate\n\n1. Confirm a generation or editing tool is callable in the current session.\n2. Check its current official documentation for model availability, accepted\n   inputs, output sizes, editing\u002Freference support, safety restrictions, retention,\n   commercial-use terms, and pricing. Record the source and check date.\n3. Confirm rights to every uploaded logo, screenshot, photo, font, and reference\n   image. Do not upload confidential or personal material outside its approved\n   boundary.\n4. Calculate the maximum cost for the requested attempts and get explicit approval\n   before using a paid account or exceeding an already approved budget.\n5. Confirm whether the user's request authorizes generation only, editing of\n   supplied files, overwriting a source, or publication. These are separate gates.\n\nProvider names and model versions are volatile. Examples such as OpenAI, Google,\nBlack Forest Labs, Ideogram, Midjourney, Recraft, and self-hosted diffusion are\nresearch candidates, not routing instructions or capability claims.\n\n### Selection criteria\n\n- For text-heavy assets, prefer a deterministic overlay or design template; test\n  any verified in-image text capability before committing to it.\n- For repeated brand work, prefer locked templates and approved assets over a\n  claimed consistency feature.\n- For edits, use a tool whose current documentation and callable schema confirm\n  image input and the required edit mode.\n- For vectors, require a real vector export and inspect its paths; a raster image\n  labeled as vector is not sufficient.\n- For product UI, capture the live authorized interface rather than generating it.\n- For volume, compare verified cost, rate limits, review time, and output quality\n  on a small test batch.\n\nIf no suitable renderer or editor is callable, deliver a production-ready prompt,\nlayout spec, asset manifest, rights checklist, and export checklist. State clearly\nthat no image was generated; do not route the user to an unavailable tool as\nthough execution occurred. Use these exact headings:\n\n```markdown\n## Prompt\n\u003CSubject + Setting + Style + Lighting + Composition + Technical, one block,\nready to paste; note any text that must be a deterministic overlay instead>\n\n## Layout Spec\nCanvas WxH + ratio | safe margins | focal point | text zones with max character\ncounts | logo placement and clear space | color values\n\n## Asset Manifest\nAsset | origin (owned \u002F licensed \u002F captured \u002F to be generated) | rights basis\nand holder | attribution or expiry | file path or \"to source\"\n\n## Rights Checklist\n- [ ] Every uploaded or referenced asset has a confirmed rights basis\n- [ ] No real person, endorsement, or product interface is fabricated\n- [ ] Brand mark is the approved file, unmodified, or omitted\n- [ ] Paid-tool cost approved, or no paid tool used\n\n## Export Checklist\nDestination | dimensions | format | quality target | file-size budget | alt text\nThen apply the Optimization Checklist in \"Image Optimization\" before delivery.\n\n## Not Done\nNo image was generated. What would unblock production: \u003Ctool, authority, asset>\n```\n\n### Prompting Basics\n\nA strong image prompt follows: **Subject + Setting + Style + Lighting + Composition + Technical**\n\n```\nA laptop on a minimal white desk with an abstract analytics motif,\nsoft directional lighting from the left, shallow depth of field,\nclean commercial photography style, 16:9 aspect ratio, 4K\n```\n\n**Common mistakes:**\n- Too vague (\"a business image\"): add specific details\n- Forgetting aspect ratio: always specify dimensions\n- Requesting complex text: use overlays instead for anything beyond short headlines\n- No style direction: \"photorealistic,\" \"flat illustration,\" \"3D render\"\n\nFor detailed prompting guides per model, see [references\u002Fai-image-prompting.md](references\u002Fai-image-prompting.md).\n\n---\n\n## Design Tools\n\nFor templated, brand-consistent work where AI generation is overkill or too unpredictable.\n\n### Canva\n\nCan be a candidate for template-driven social graphics, presentations, email\nheaders, and banners. Verify the connected account, current features, export\nrights, plan limits, API availability, and callable integration before routing\nwork to it. Keep a human review gate for brand output.\n\n### Figma\n\nCan be a candidate when an authorized design file or component system exists.\nVerify current account access and whether the available integration can read,\nedit, export, or only inspect. Do not claim write access or create files merely\nbecause a connector exists.\n\n### When to Use Design Tools vs. AI Generation\n\n| Scenario | Design Tool | AI Generation |\n|----------|:-:|:-:|\n| Exact brand guidelines must be followed | Yes | Maybe (with strong ref images) |\n| Need many size variants of one design | Yes, if current resize\u002Fexport capability is verified | Usually no |\n| Unique hero image for a blog post | No | Yes |\n| Recurring social media template | Yes | No |\n| Product mockup with real UI | No (use screenshots) | No (hallucinated UI) |\n| Abstract\u002Fcreative visual | No | Yes |\n\n---\n\n## Marketing Image Workflows\n\n### Blog & Article Hero Images\n\nThe image at the top of every post. Sets tone, improves shareability, required for OG\u002Fsocial previews.\n\n1. **Define the concept**: what visual metaphor represents the topic?\n2. **Choose the verified method**: callable generator, approved media, or a\n   deterministic local\u002Fdesign template\n3. **Confirm dimensions** from the actual site component and current social\n   preview requirements\n4. **Optimize to a measured quality and performance budget**\n\n**Prompt pattern:**\n```\n[Visual metaphor for topic], clean modern style,\nbright natural lighting, shallow depth of field,\nprofessional blog header aesthetic, [verified width]x[verified height]\n```\n\n### Social Media Graphics\n\nPlatform-specific images for organic posts.\n\nThe values below are planning defaults, not current platform guarantees. Check the\nplatform's official specification on the work date and use its current safe zones,\nfile limits, and format rules.\n\n| Platform | Planning size | Aspect ratio | Notes |\n|----------|-------------|:---:|-------|\n| X | 1200x675 | 16:9 | Large image card |\n| LinkedIn | 1200x627 | 1.91:1 | Feed image |\n| Instagram Feed | 1080x1350 | 4:5 | Profile grid crops to 3:4 since January 2025; keep the subject centered |\n| Instagram Stories | 1080x1920 | 9:16 | Full screen vertical |\n| Facebook | 1200x630 | 1.91:1 | Link share image |\n\n**Workflow:**\n1. Create the hero concept at highest resolution needed\n2. Use a verified resize\u002Fexport feature or manual crop for platform variants\n3. Add text overlays deterministically when accurate text is required\n4. Export at platform-specific dimensions\n\n### Product Mockups & Screenshots\n\nShowcase your product UI in context. AI models hallucinate UI: don't use them for this.\n\n1. **Capture real screenshots** of your product at 2x resolution\n2. **Frame in device mockups**: use browser frame, laptop, or phone templates\n3. **Add context**: callout arrows, verified feature labels, before\u002Fafter comparisons\n4. **Annotate deterministically**: use a callable local layout workflow or an\n   authorized design tool\n\nPossible capture surfaces include browser tooling or an installed OS capture\nutility. Discover what is currently callable, confirm authorization for the live\nsurface, and omit tools that are not available.\n\n### Profile & Listing Banners\n\nBanners for profiles, directory listings, and marketplace pages. Often the first visual impression.\n\nThese are planning references and can drift. Verify current official dimensions,\ncropping behavior, safe zones, file limits, and format rules before production.\n\n| Platform | Planning size | Notes |\n|----------|------|-------|\n| LinkedIn personal cover | 1584x396 | 4:1, safe zone center |\n| LinkedIn company cover | 1128x191 | 5.9:1; LinkedIn recommends up to 4200x700 |\n| Twitter\u002FX header | 1500x500 | 3:1, partially obscured by avatar |\n| Product Hunt gallery | 1270x760 | 5:3, up to 6 images |\n| G2 profile | 1280x720 | 16:9, product screenshots preferred |\n| GitHub social preview | 1280x640 | 2:1, shows in link cards |\n| App Store screenshots | Varies by device | See suede-aso skill for full specs |\n| Google Play feature graphic | 1024x500 | ~2:1, required for store listing |\n\n**Best practices:**\n- **Keep text minimal**: banners are seen at small sizes on mobile\n- **Center critical content**: edges get cropped differently per device\n- **Show the product truthfully**: use real UI screenshots when the listing is\n  meant to demonstrate the interface\n- **Match your brand**: use consistent colors, fonts, logo placement\n- **Update deliberately**: refresh when the product, campaign, or positioning changes\n\n**Workflow:**\n1. Pick the platform(s) and note exact dimensions\n2. For directories (Product Hunt, G2): use real product screenshots with light annotation\n3. For profiles (LinkedIn, Twitter): use brand colors + tagline + optional product shot\n4. Produce with a verified callable template workflow; add text deterministically\n5. Test at actual display size: zoom out to check readability\n\n### Brand Assets\n\nLogos, icons, and illustrations. AI generation has limits here.\n\n| Asset | AI Generation | Design Tool | Notes |\n|-------|:-:|:-:|-------|\n| Logo | Poor: inconsistent, not vector | Yes | Always design or commission logos |\n| App icon | Concept exploration only | Yes | Refine manually and verify store rules |\n| Illustrations | Good for style exploration | Depends | AI for concepts, finalize in design tool |\n| Favicons | No | Yes | Derive from logo |\n| Social icons | No | Yes | Use platform-provided assets |\n\n---\n\n## Image Optimization\n\nImage bytes and dimensions can affect page performance. Measure the actual page\nbefore attributing search or conversion results to image changes.\n\n### Format Guide\n\n| Format | Best For | Compression |\n|--------|----------|-------------|\n| **WebP** | Photos and graphics when target browsers support it | Lossy + lossless |\n| **AVIF** | High-compression delivery when target browsers support it | Lossy + lossless |\n| **JPEG** | Broad photo compatibility | Lossy |\n| **PNG** | Transparency and lossless screenshots | Lossless |\n| **SVG** | Trusted vector logos, icons, and illustrations | Vector |\n\n### Optimization Checklist\n\n- [ ] **Use a supported delivery format** and fallback strategy for the target browser matrix\n- [ ] **Resize to display size**: don't serve 4000px images in 800px containers\n- [ ] **Compress**: choose quality from visual review and the page's measured byte budget\n- [ ] **Lazy load** below-the-fold images (`loading=\"lazy\"`)\n- [ ] **Set explicit dimensions**: `width` and `height` attributes prevent layout shift (CLS)\n- [ ] **Use verified CDN optimization** when the current stack supports it\n- [ ] **Add alt text**: describe what the image shows in plain words, using the\n  page's topic phrase only where it is the honest description\n- [ ] **Name files descriptively**: `pricing-calculator-dashboard.webp`, not\n  `IMG_2041.webp`\n- [ ] **Keep important images crawlable**: a real `\u003Cimg>` with `src`, not a CSS\n  background, and not blocked in robots.txt\n- [ ] **Place the image near the text it illustrates** and give charts a\n  caption that states the finding, so search and AI answers can quote it\n\nThe largest above-the-fold image is usually the Largest Contentful Paint\nelement. Do not lazy-load it; give it `fetchpriority=\"high\"` and explicit\ndimensions. Core Web Vitals and image-indexing audits route to\n`suede-seo-audit`.\n\n### Quick Optimization Commands\n\n```bash\n# Run only after confirming the named local utility is installed.\n# Convert to WebP (using cwebp)\ncwebp -q 80 input.png -o output.webp\n\n# Batch convert with ImageMagick\nmogrify -format webp -quality 80 *.png\n\n# Optimize JPEG (using jpegoptim)\njpegoptim --max=80 --strip-all *.jpg\n```\n\nTo inspect image references on a page, use the host's approved read-only HTTP\nor browser tool against a verified public HTTPS URL. Refuse loopback,\nlink-local, or private-network destinations; do not attach ambient cookies or\nauthentication headers; and do not send local files, credentials, or workspace\ncontent. Inspect the returned HTML for image `src` values and report a failed or\nunsafe fetch as unverified.\n\n---\n\n## OG & Social Preview Images\n\nThe image that appears when your URL is shared on social media, Slack, Discord, etc.\n\n### Common Meta Tags\n\nVerify the current crawler\u002Fplatform specification and use absolute public URLs.\nThe values below are a starting template, not proof of platform compliance.\n\n```html\n\u003Cmeta property=\"og:image\" content=\"https:\u002F\u002Fyoursite.com\u002Fog\u002Fpage-name.jpg\" \u002F>\n\u003Cmeta property=\"og:image:width\" content=\"1200\" \u002F>\n\u003Cmeta property=\"og:image:height\" content=\"630\" \u002F>\n\u003Cmeta name=\"twitter:card\" content=\"summary_large_image\" \u002F>\n\u003Cmeta name=\"twitter:image\" content=\"https:\u002F\u002Fyoursite.com\u002Fog\u002Fpage-name.jpg\" \u002F>\n```\n\n### Dynamic OG Images\n\nGenerate OG images programmatically for dynamic pages only after verifying the\nproject's current framework, installed packages, and supported runtime:\n\n- An installed framework-native image route\n- A local HTML\u002FSVG-to-image renderer\n- An authorized media service with verified template and export capabilities\n\nFor repeated page types, a deterministic template can reduce manual work. Measure\npreview correctness and production time; do not promise a search outcome.\n\n---\n\n## Common Mistakes\n\n1. **Skipping image optimization**: oversized images can materially hurt page performance\n2. **No preview image**: platforms may fall back to a less useful preview\n3. **Inconsistent brand visuals**: use locked, approved templates for consistency\n\n---\n\n## Halt Contract\n\nUse this exact format when a callable tool, cost approval, rights confirmation,\nor the approved brand asset blocks the requested result:\n\n```text\nHALT: \u003Cone-line blocker>\nWhy it blocks: \u003Cspecific missing authority or evidence>\nResolve with:\n1. \u003Coption>\n2. \u003Coption>\n3. \u003Coption, when useful>\nWaiting for: \u003Cthe exact item or approval>\n```\n\nContinue with the no-tool handoff artifacts above only when they remain useful\nand do not imply an image was produced.\n\n---\n\n## Boundaries\n\n- For Suede visuals, use only `docs\u002Fassets\u002Fsuede-ai-logo-transparent.png` with SHA-256 `83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa`.\n- Do not redraw, trace, approximate, recolor, distort, typeset, or generate a replacement for the approved Suede S mark. If the canonical file is missing or its checksum differs, omit the mark, name the blocker, and request the approved file.\n- Do not claim an image is licensed, rights-cleared, authentic, accessible, optimized, or platform-compliant without verifying the relevant source or output.\n- Do not use a paid provider, upload protected material, or cross an approved\n  account or data boundary without explicit authority and a verified maximum cost.\n- Do not publish, overwrite source assets, or replace real product screenshots without explicit authorization.\n- Do not invent people, endorsements, product interfaces, performance results, or provenance, and do not decide rights or brand exceptions for the user.\n\n## Routing\n\n- Use `suede-ad-creative` for paid-ad production and `suede-video` for motion.\n- Use `suede-social` for channel strategy and `suede-site-alchemy` for conversion placement.\n- Use `suede-social` for platform format contracts (Reel covers, carousel slide counts, Story frames) before producing those assets here.\n- Use `suede-seo-audit` for image-search checks and `suede-aso` for app-store screenshots.\n- Use `suede-directory-submissions` for directory gallery planning.\n\n## Worked contract\n\n[Worked contract](references\u002Fusage-contract.md) gives a bounded input, expected output and failure check for this workflow.\n",{"name":5,"metadata":68,"description":7},{"version":69,"display-name":70},"2.1.0","Suede AI Image Skills","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":82,"prompt":92,"zipAvailable":93},[83,86,89],{"tool":84,"command":85},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-image",{"tool":87,"command":88},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-image",{"tool":90,"command":91},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-image","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002FSKILL.md",true,[95,101,105,109,113],{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"agents\u002Fopenai.yaml","REFERENCE","参考文档",483,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002Fagents\u002Fopenai.yaml",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"CARD.md",4998,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002FCARD.md",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"evals\u002Fevals.json",5344,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002Fevals\u002Fevals.json",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fai-image-prompting.md",7197,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002Freferences\u002Fai-image-prompting.md",{"path":114,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fusage-contract.md",870,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-image\u002Freferences\u002Fusage-contract.md",[118,128,136,144,152,160],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":122,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":127},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":122,"licenseFileUrl":132,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":127},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":122,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":127},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":122,"licenseFileUrl":148,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":127},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":122,"licenseFileUrl":156,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":127},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":122,"licenseFileUrl":164,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":127},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]