{"id":"fd19abad-df91-4482-848c-40a129b3c45b","entityType":"agent","slug":"clawhub-leooooooow-ecommerce-image-asset-generator","name":"Ecommerce Image Asset Generator","canonicalUrl":"https://www.xpersona.co/agent/clawhub-leooooooow-ecommerce-image-asset-generator","canonicalPath":"/agent/clawhub-leooooooow-ecommerce-image-asset-generator","generatedAt":"2026-10-09T19:55:30.033Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":null},"description":"Plan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images...","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.3K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:ecommerce-image-asset-generator","sourceUrl":"https://clawhub.ai/leooooooow/ecommerce-image-asset-generator","homepage":"https://clawhub.ai/leooooooow/skills/ecommerce-image-asset-generator","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/leooooooow/ecommerce-image-asset-generator","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/leooooooow/skills/ecommerce-image-asset-generator","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":58,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Ecommerce Image Asset Generator technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":null},"stars":null,"forks":null,"downloads":2334,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"2.3K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T16:14:22.616Z","lastCrawledAt":"2026-10-09T16:14:22.616Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T16:14:22.616Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-03-26T07:46:53.347Z","changelog":"Upgrade internals with stronger asset-planning workflow, provider modes, and commercial framing","fileCount":7,"zipByteSize":8655},{"version":"1.0.0","createdAt":"2026-03-13T17:10:18.781Z","changelog":"Initial release","fileCount":3,"zipByteSize":1437}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:ecommerce-image-asset-generator","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:ecommerce-image-asset-generator` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/leooooooow/ecommerce-image-asset-generator before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T19:55:30.033Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-ecommerce-image-asset-generator/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":null},"readme":"Skill: Ecommerce Image Asset Generator\n\nOwner: leooooooow\n\nSummary: Plan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images...\n\nTags: latest:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-03-26T07:46:53.347Z | user\n\nUpgrade internals with stronger asset-planning workflow, provider modes, and commercial framing\n\nv1.0.0 | 2026-03-13T17:10:18.781Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.0.1: 7 files, 8655 bytes\n\nFiles: references/output-template.md (1129b), references/provider-jimeng-v4.md (1856b), references/provider-nano-banana.md (1367b), references/provider-seedream-5.md (1310b), skill-card.md (2509b), SKILL.md (8259b), _meta.json (150b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: ecommerce-image-asset-generator\ndescription: Plan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images to create first, turn product context into clear visual briefs, or route asset generation/editing through an available image provider.\n---\n\n# Ecommerce Image Asset Generator\n\nPlan the right ecommerce image assets before design starts, then generate or edit them when an image provider is available.\n\nThis skill is not for producing random “pretty images.”\n\nIt helps answer the higher-value questions first:\n- **Which image assets matter most for this product or campaign?**\n- **What should each image do in the funnel?**\n- **What message should the image communicate?**\n- **What should stay fixed vs change when editing an existing image?**\n- **How do we turn business context into a usable visual brief or provider-ready prompt?**\n\n## Solves\n\nEcommerce teams often fail visually in predictable ways:\n- they make assets in the wrong order;\n- they create hero images when trust images are the bottleneck;\n- they generate attractive images that do not help CTR, CVR, or buyer understanding;\n- design briefs are vague, so output quality becomes inconsistent;\n- teams do not separate awareness images from conversion images;\n- image edits drift too far from the original and break brand or listing consistency.\n\nGoal:\n**First identify the highest-value image assets for the business objective, then generate or edit only what is worth making.**\n\n## Use when\n\nUse when the user needs ecommerce visuals that serve a real commercial purpose, not just general inspiration.\n\nTypical cases:\n- launching a new product and deciding which visuals to create first;\n- building a PDP, TikTok Shop, Shopify, Amazon, or marketplace image set;\n- turning product notes into image briefs for design or AI generation;\n- planning promo assets, offer visuals, or sale banners;\n- generating new product or campaign images from prompts;\n- editing existing images while preserving important elements;\n- prioritizing a smaller, conversion-focused visual system instead of random one-off assets.\n\n## Do not use when\n\nDo not use this skill when:\n- the user only wants a broad brand moodboard with no business goal;\n- the task is video generation rather than image planning/editing;\n- there is too little product context to define useful asset priorities;\n- the user wants a full brand identity system instead of ecommerce assets;\n- provider execution is requested but auth / endpoint / runtime details are unavailable.\n\n## Core principle\n\n**Plan before generate.**\n\nThe strongest ecommerce image work does not start with the model.\nIt starts with the conversion job.\n\nEvery asset should map to one of these jobs:\n- stop the scroll\n- explain the product faster\n- reduce doubt\n- make the value clearer\n- increase trust\n- improve click-through or conversion\n- support an offer, launch, or promo moment\n\n## Working modes\n\n### Mode 1: Plan-only\nUse when no provider is configured, or when the user wants to approve direction first.\n\nReturn:\n- asset priority list\n- brief for each asset\n- overlay / copy suggestions\n- prompt drafts for later generation\n\n### Mode 2: Plan + Generate\nUse when a supported provider is available and the user wants images created.\n\nReturn:\n- asset plan\n- provider-ready prompts\n- generated outputs or saved paths / URLs\n- notes on what to improve next\n\n### Mode 3: Edit Existing Image\nUse when the user already has source images and wants controlled changes.\n\nReturn:\n- what must stay fixed\n- what should change\n- edit brief / prompt / payload plan\n- edited outputs or saved paths / URLs\n\n### Mode 4: Batch Asset Set\nUse when the user needs a coordinated visual set for a PDP, campaign, listing, or launch.\n\nReturn:\n- prioritized asset set\n- image-by-image brief\n- generation order\n- prompt set / payload guidance\n\n## Inputs\n\nAsk for the minimum useful business context:\n- product name and category\n- target audience\n- platform / channel\n- business goal (CTR, CVR, education, trust, promo, launch, retargeting)\n- key selling points\n- strongest proof points\n- offer / promo context, if relevant\n- existing assets, if any\n- compliance boundaries or prohibited claims\n- provider choice, if generation/editing is requested\n- source image(s), if editing is requested\n\n## Workflow\n\n### Phase 1: Clarify the visual job\n1. Restate the product, audience, and commercial objective.\n2. Identify what buyers still do not understand or trust.\n3. Decide which image types would solve that fastest.\n4. Prioritize the assets instead of listing everything.\n\n### Phase 2: Recommend the right asset mix\nChoose only the most commercially useful image types, such as:\n- hero image\n- feature / benefit image\n- comparison image\n- problem-solution explainer\n- trust / review image\n- offer / promo image\n- lifestyle / use-case image\n- marketplace infographic image\n- UGC-style image concept\n\n### Phase 3: Brief each asset clearly\nFor each asset, define:\n- asset type\n- business objective\n- key message\n- visual direction\n- on-image text / overlay guidance\n- must-show product elements\n- compliance / avoid notes\n\n### Phase 4: Generate or edit if supported\nIf a provider is configured:\n1. Convert the brief into provider-ready prompts or payload logic.\n2. Generate or edit the asset(s).\n3. Review whether the output actually matches the commercial job.\n4. Suggest the next iteration.\n\nIf provider details are missing:\n- stop at the planning + prompt layer;\n- do not fake execution.\n\n## Provider model\n\nTreat generation as **provider-pluggable**.\n\nPreferred flow:\n1. Plan assets first.\n2. If execution is requested, ask which provider should be used.\n3. Ask only for the minimum provider-specific info.\n4. Route generation/editing through that provider.\n\nRecommended provider order:\n- **Seedream 5.0 via ARK API** for a modern API-first image flow\n- **Nano Banana Pro / Nano Banana 2** for strong text-to-image and image edit workflows\n- **Jimeng 4.0** for Chinese-first prompting, grouped outputs, and multi-image workflows\n- **Other compatible image APIs** when the user provides endpoint + auth + required parameter mapping\n\nIf provider details are missing, remain in **Plan-only** mode.\n\n## What to ask when execution is requested\n\nAsk the smallest useful set, not a giant questionnaire.\n\n### Universal questions\n- Which provider should be used?\n- Is this text-to-image, image edit, or batch asset generation?\n- How is access configured? (env var, API key, token, script, existing runtime)\n\n### Provider-specific minimums\n#### Seedream 5.0 / ARK\nAsk for:\n- whether `ARK_API_KEY` is configured;\n- preferred model, if not default;\n- desired output size, if important.\n\nDefault assumptions when not specified:\n- model: `doubao-seedream-5-0-260128`\n- size: `2K`\n- response format: `url`\n- watermark: `false`\n\n#### Nano Banana\nAsk for:\n- which version / workflow to use;\n- whether key/runtime is configured;\n- whether there is an input image for edits.\n\n#### Jimeng 4.0\nAsk for:\n- auth/signing method;\n- whether this is text-to-image, edit, or grouped generation;\n- whether grouped outputs or `force_single` are needed;\n- whether input image URLs are already available.\n\n## Output\n\nReturn a practical asset package:\n\n1. **Asset priority list**\n2. **Per-asset commercial brief**\n3. **Visual direction + overlay guidance**\n4. **Provider-ready prompt or edit plan**\n5. **If execution runs:** file paths, URLs, or iteration notes\n\n## Quality bar\n\nA strong output should:\n- plan before generating;\n- map each image to a business objective;\n- distinguish awareness images from conversion images;\n- prioritize a smaller, better asset set over a generic long list;\n- avoid misleading or non-compliant claims;\n- preserve critical elements during edits;\n- stop honestly at the planning layer if provider execution is unavailable.\n\n## What “better” looks like\n\nGood output should make it obvious:\n- which image to make first;\n- why that image matters;\n- what that image should say visually;\n- how to brief or generate it without ambiguity;\n- what to improve next if the first version is weak.\n\n## Resource\n\nSee `references/output-template.md` and the provider notes in `references/`.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"ecommerce-image-asset-generator\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1774511213347\n}\n\nFile v1.0.1:references/output-template.md\n\n# Ecommerce Image Asset Generator — Output Template\n\n## 1. Commercial Context\n- Product:\n- Category:\n- Goal:\n- Audience:\n- Platform / channel:\n- Compliance constraints:\n\n## 2. Asset Priority List\n1. Asset type:\n   - Why this matters:\n   - Funnel role:\n2. Asset type:\n   - Why this matters:\n   - Funnel role:\n3. Asset type:\n   - Why this matters:\n   - Funnel role:\n\n## 3. Per-Asset Briefs\n### Asset A\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n### Asset B\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n### Asset C\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n## 4. Execution Mode\n- Mode: plan-only / plan+generate / edit existing image / batch asset set\n- Provider:\n- Resolution / size target:\n- Number of outputs:\n\n## 5. Provider-Ready Prompt / Payload Plan\n- Prompt or edit instruction:\n- Required input images:\n- Parameters / notes:\n\n## 6. Generation / Edit Output\n- Output path(s) or URL(s):\n- What looks strong:\n- What to iterate next:\n\nFile v1.0.1:references/provider-jimeng-v4.md\n\n# Provider Notes — Jimeng 4.0\n\nUse this provider when the user wants Chinese-first prompting, grouped image outputs, multi-image reference input, or high-resolution ecommerce image generation and editing.\n\n## Best for\n- Chinese ecommerce prompting\n- Multi-image input and composite generation\n- Batch asset generation\n- PDP, campaign, or grouped marketplace image sets\n- High-resolution outputs up to 4K\n\n## Key request model\nJimeng 4.0 works as an async task API.\nTypical flow:\n1. Submit task\n2. Receive task_id\n3. Poll result endpoint\n4. Return output URLs or decoded images when done\n\n## Best-fit scenarios\n- Generate a coordinated asset set instead of a single image\n- Edit existing product images with multiple references\n- Produce Chinese-friendly ecommerce visuals with better prompt fidelity\n\n## Ask before running\n- Is this text-to-image, image edit, or grouped asset generation?\n- Does the user want one image or multiple related outputs?\n- Should `force_single=true` be used to control latency and cost?\n- Are there input image URLs available?\n- Is a target ratio / size / width-height specified?\n\n## Important parameter guidance\n- `prompt`: keep direct, concrete, commerce-focused\n- `image_urls`: use when editing or providing references\n- `size` or `width` + `height`: set resolution expectations explicitly when consistency matters\n- `scale`: raise if text instruction should dominate more than reference images\n- `force_single`: use when latency, price, or consistency matter more than variety\n\n## Failure handling\nIf auth, signing, provider config, or required image URLs are missing:\n- do not pretend generation succeeded;\n- fall back to plan-only mode and return the exact prompt + payload draft the user can run later.\n\n## Output note\nBecause Jimeng is async, always separate:\n- submit step\n- task status check\n- final output delivery\n\nFile v1.0.1:references/provider-nano-banana.md\n\n# Provider Notes — Nano Banana Pro / Nano Banana 2\n\nUse this provider when the user wants strong text-to-image or image-to-image generation and has access to a Nano Banana-compatible workflow.\n\n## Best for\n- Single-image generation\n- Controlled edits to an existing image\n- Fast draft → iterate → final workflow\n- 1K / 2K / 4K generation requests\n\n## Ask before running\n- Which Nano Banana provider/version should be used?\n- Is an API key or local execution environment already configured?\n- Is this text-to-image or image-to-image?\n- What output filename or directory should be used?\n\n## Recommended flow\n1. Plan the asset first.\n2. Create a provider-ready prompt.\n3. If editing, define exactly what must stay fixed.\n4. Start at lower resolution for drafts.\n5. Move to higher resolution only after direction is approved.\n\n## Prompt guidance\n### Generation\nUse a concrete, commercial prompt structure:\n- subject\n- product angle\n- composition\n- lighting\n- background\n- text safety / avoid list\n\n### Editing\nUse a constrained edit instruction:\n- Change ONLY: <requested change>\n- Keep identical: subject, crop, lighting, palette, text placement, and overall style unless user requests otherwise.\n\n## Failure handling\nIf the provider environment, API key, or input image is missing:\n- stop execution;\n- return the prompt package and tell the user what is missing.\n\nFile v1.0.1:references/provider-seedream-5.md\n\n# Provider Notes — Seedream 5.0 (ARK API)\n\nUse this provider when the user wants a simple, modern image generation path through the ARK API.\n\n## Best for\n- Fast text-to-image generation\n- Simple image API setup with one API key\n- Chinese or mixed-language prompting\n- Ecommerce hero images, promotional visuals, cover images, and campaign concepts\n\n## Minimum required info\nAsk only for:\n- whether `ARK_API_KEY` is already configured;\n- whether the user wants text-to-image or image editing;\n- output size only if they care.\n\n## Recommended defaults\nIf the user does not specify otherwise:\n- model: `doubao-seedream-5-0-260128`\n- size: `2K`\n- response format: `url`\n- watermark: `false`\n\n## Best flow\n1. Plan the asset first.\n2. Convert the winning asset brief into a compact commercial prompt.\n3. Use defaults unless the user asks for different size or model behavior.\n4. Return the generated URL and suggest the next iteration if needed.\n\n## Prompt guidance\nUse prompts that specify:\n- product or subject\n- key selling angle\n- composition\n- lighting\n- background\n- style direction\n- avoid notes\n\n## Failure handling\nIf `ARK_API_KEY` is missing or provider execution is unavailable:\n- fall back to plan-only mode;\n- return the exact Seedream-ready prompt package instead of pretending generation succeeded.\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nPlan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images to create first, turn product context into clear visual briefs, or route asset generation/editing through an available image provider.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[leooooooow](https://clawhub.ai/user/leooooooow)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal ecommerce teams, marketers, designers, and agent operators use this skill to prioritize conversion-focused product, PDP, marketplace, promotional, and ad image assets before generating or editing them through an available provider.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Generation or editing workflows may send prompts or source images to a selected provider.\n\nMitigation: Confirm the provider and approval status before uploading confidential product, listing, or campaign assets.\n\nRisk: Credentials can be exposed if raw API keys or tokens are pasted into chat.\n\nMitigation: Use environment variables or a secret manager, and confirm required provider access without sharing secrets.\n\nRisk: Generated ecommerce visuals or copy may imply unsupported product claims.\n\nMitigation: Capture compliance boundaries in the asset brief and review outputs for misleading or prohibited claims before use.\n\n## Reference(s):\n\n- [Output Template](references/output-template.md)\n- [Provider Notes - Seedream 5.0](references/provider-seedream-5.md)\n- [Provider Notes - Nano Banana Pro / Nano Banana 2](references/provider-nano-banana.md)\n- [Provider Notes - Jimeng 4.0](references/provider-jimeng-v4.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, files]\n\n**Output Format:** [Markdown asset plans, commercial briefs, provider-ready prompts or edit plans, and optional generated file paths or URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May stop at planning and prompt guidance when provider credentials, endpoints, source images, or runtime details are unavailable.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.0: 3 files, 1437 bytes\n\nFiles: references/output-template.md (170b), SKILL.md (1489b), _meta.json (150b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: ecommerce-image-asset-generator\ndescription: Generate ecommerce-ready visual assets (cover, comparison card, infographic, product explainer) from a product brief. Use when teams need fast visual production for TikTok Shop, PDP, and social distribution.\n---\n\n# Ecommerce Image Asset Generator\n\n## Skill Card\n\n- **Category:** Image & Media Tools\n- **Core problem:** Ecommerce teams have product info but no repeatable visual asset production framework.\n- **Best for:** TikTok Shop creatives, PDP explainers, campaign visuals.\n- **Expected input:** Product brief, key selling points, audience, platform specs, compliance boundaries.\n- **Expected output:** Asset plan + copy skeleton + visual directions + adaptation matrix.\n\n## Workflow\n\n1. Extract conversion-critical points.\n2. Match points with asset formats.\n3. Define per-asset composition and copy structure.\n4. Adapt for channel dimensions and constraints.\n\n## Output format\n\n1. Asset plan\n2. Per-asset copy skeleton\n3. Visual directions\n4. Adaptation matrix\n\n## Quality and safety rules\n\n- Conversion clarity first.\n- No exaggerated claims.\n- Each visual must map to a concrete objective.\n\n## License\n\nCopyright (c) 2026 **Razestar**.\n\nThis skill is provided under **CC BY-NC-SA 4.0** for non-commercial use.\nYou may reuse and adapt it with attribution to Razestar, and share derivatives\nunder the same license.\n\nCommercial use requires a separate paid commercial license from **Razestar**.\nNo trademark rights are granted.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"ecommerce-image-asset-generator\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773421818781\n}\n\nFile v1.0.0:references/output-template.md\n\n# Output Template\n\n## 1) Asset plan\n- \n\n## 2) Per-asset copy skeleton\n- \n\n## 3) Visual directions\n- \n\n## 4) Adaptation matrix\n| Platform | Size | Variant |\n|---|---|---|","readmeExcerpt":"Skill: Ecommerce Image Asset Generator Owner: leooooooow Summary: Plan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-26T07:46:53.347Z | user Upgrade internals with stronger asset-planning workflow, provider modes, and commercial framing v1.0.0 | 2026-03-13T","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ecommerce-image-asset-generator\ndescription: Plan and generate ecommerce image assets that actually support conversion. Use when teams need to decide which product, PDP, marketplace, promo, or ad images to create first, turn product context into clear visual briefs, or route asset generation/editing through an available image provider.\n---\n\n# Ecommerce Image Asset Generator\n\nPlan the right ecommerce image assets before design starts, then generate or edit them when an image provider is available.\n\nThis skill is not for producing random “pretty images.”\n\nIt helps answer the higher-value questions first:\n- **Which image assets matter most for this product or campaign?**\n- **What should each image do in the funnel?**\n- **What message should the image communicate?**\n- **What should stay fixed vs change when editing an existing image?**\n- **How do we turn business context into a usable visual brief or provider-ready prompt?**\n\n## Solves\n\nEcommerce teams often fail visually in predictable ways:\n- they make assets in the wrong order;\n- they create hero images when trust images are the bottleneck;\n- they generate attractive images that do not help CTR, CVR, or buyer understanding;\n- design briefs are vague, so output quality becomes inconsistent;\n- teams do not separate awareness images from conversion images;\n- image edits drift too far from the original and break brand or listing consistency.\n\nGoal:\n**First identify the highest-value image assets for the business objective, then generate or edit only what is worth making.**\n\n## Use when\n\nUse when the user needs ecommerce visuals that serve a real commercial purpose, not just general inspiration.\n\nTypical cases:\n- launching a new product and deciding which visuals to create first;\n- building a PDP, TikTok Shop, Shopify, Amazon, or marketplace image set;\n- turning product notes into image briefs for design or AI generation;\n- planning promo assets, offer visuals, or sale banners;\n- generating new product or campaign images from prompts;\n- editing existing images while preserving important elements;\n- prioritizing a smaller, conversion-focused visual system instead of random one-off assets.\n\n## Do not use when\n\nDo not use this skill when:\n- the user only wants a broad brand moodboard with no business goal;\n- the task is video generation rather than image planning/editing;\n- there is too little product context to define useful asset priorities;\n- the user wants a full brand identity system instead of ecommerce assets;\n- provider execution is requested but auth / endpoint / runtime details are unavailable.\n\n## Core principle\n\n**Plan before generate.**\n\nThe strongest ecommerce image work does not start with the model.\nIt starts with the conversion job.\n\nEvery asset should map to one of these jobs:\n- stop the scroll\n- explain the product faster\n- reduce doubt\n- make the value clearer\n- increase trust\n- improve click-through or conversion\n- support an offer, launch, or promo moment\n\n## Working modes\n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"ecommerce-image-asset-generator\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1774511213347\n}"},{"path":"references/output-template.md","content":"# Ecommerce Image Asset Generator — Output Template\n\n## 1. Commercial Context\n- Product:\n- Category:\n- Goal:\n- Audience:\n- Platform / channel:\n- Compliance constraints:\n\n## 2. Asset Priority List\n1. Asset type:\n   - Why this matters:\n   - Funnel role:\n2. Asset type:\n   - Why this matters:\n   - Funnel role:\n3. Asset type:\n   - Why this matters:\n   - Funnel role:\n\n## 3. Per-Asset Briefs\n### Asset A\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n### Asset B\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n### Asset C\n- Asset type:\n- Objective:\n- Key message:\n- Visual direction:\n- Text overlay suggestion:\n- What to avoid:\n\n## 4. Execution Mode\n- Mode: plan-only / plan+generate / edit existing image / batch asset set\n- Provider:\n- Resolution / size target:\n- Number of outputs:\n\n## 5. Provider-Ready Prompt / Payload Plan\n- Prompt or edit instruction:\n- Required input images:\n- Parameters / notes:\n\n## 6. Generation / Edit Output\n- Output path(s) or URL(s):\n- What looks strong:\n- What to iterate next:"},{"path":"references/provider-jimeng-v4.md","content":"# Provider Notes — Jimeng 4.0\n\nUse this provider when the user wants Chinese-first prompting, grouped image outputs, multi-image reference input, or high-resolution ecommerce image generation and editing.\n\n## Best for\n- Chinese ecommerce prompting\n- Multi-image input and composite generation\n- Batch asset generation\n- PDP, campaign, or grouped marketplace image sets\n- High-resolution outputs up to 4K\n\n## Key request model\nJimeng 4.0 works as an async task API.\nTypical flow:\n1. Submit task\n2. Receive task_id\n3. Poll result endpoint\n4. Return output URLs or decoded images when done\n\n## Best-fit scenarios\n- Generate a coordinated asset set instead of a single image\n- Edit existing product images with multiple references\n- Produce Chinese-friendly ecommerce visuals with better prompt fidelity\n\n## Ask before running\n- Is this text-to-image, image edit, or grouped asset generation?\n- Does the user want one image or multiple related outputs?\n- Should `force_single=true` be used to control latency and cost?\n- Are there input image URLs available?\n- Is a target ratio / size / width-height specified?\n\n## Important parameter guidance\n- `prompt`: keep direct, concrete, commerce-focused\n- `image_urls`: use when editing or providing references\n- `size` or `width` + `height`: set resolution expectations explicitly when consistency matters\n- `scale`: raise if text instruction should dominate more than reference images\n- `force_single`: use when latency, price, or consistency matter more than variety\n\n## Failure handling\nIf auth, signing, provider config, or required image URLs are missing:\n- do not pretend generation succeeded;\n- fall back to plan-only mode and return the exact prompt + payload draft the user can run later.\n\n## Output note\nBecause Jimeng is async, always separate:\n- submit step\n- task status check\n- final output delivery"},{"path":"references/provider-nano-banana.md","content":"# Provider Notes — Nano Banana Pro / Nano Banana 2\n\nUse this provider when the user wants strong text-to-image or image-to-image generation and has access to a Nano Banana-compatible workflow.\n\n## Best for\n- Single-image generation\n- Controlled edits to an existing image\n- Fast draft → iterate → final workflow\n- 1K / 2K / 4K generation requests\n\n## Ask before running\n- Which Nano Banana provider/version should be used?\n- Is an API key or local execution environment already configured?\n- Is this text-to-image or image-to-image?\n- What output filename or directory should be used?\n\n## Recommended flow\n1. Plan the asset first.\n2. Create a provider-ready prompt.\n3. If editing, define exactly what must stay fixed.\n4. Start at lower resolution for drafts.\n5. Move to higher resolution only after direction is approved.\n\n## Prompt guidance\n### Generation\nUse a concrete, commercial prompt structure:\n- subject\n- product angle\n- composition\n- lighting\n- background\n- text safety / avoid list\n\n### Editing\nUse a constrained edit instruction:\n- Change ONLY: <requested change>\n- Keep identical: subject, crop, lighting, palette, text placement, and overall style unless user requests otherwise.\n\n## Failure handling\nIf the provider environment, API key, or input image is missing:\n- stop execution;\n- return the prompt package and tell the user what is missing."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1461,"uniquenessScore":44,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T16:14:22.616Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:55:30.033Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}