{"id":"14a719f8-6e51-4232-8c85-59b739bbdab5","entityType":"agent","slug":"clawhub-cellcog-3d-model-generation-cellcog","name":"3D Model Generation","canonicalUrl":"https://www.xpersona.co/agent/clawhub-cellcog-3d-model-generation-cellcog","canonicalPath":"/agent/clawhub-cellcog-3d-model-generation-cellcog","generatedAt":"2026-10-09T12:58:17.219Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T05:23:14.725Z","emptyReason":null},"description":"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation. Skill: 3D Model Generation Owner: cellcog Summary: AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation. Tags: latest:1.0.15 Version history: v1.0.15 | 2026-08-24T02:02:47.474Z | user Content updated. v1.0.14 | 2026-08-24T01:47:30.035Z | us","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.5K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s176q1btpn094ats9b4f9hgfwx83knpk:3d-model-generation-cellcog","sourceUrl":"https://clawhub.ai/cellcog/3d-model-generation-cellcog","homepage":"https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/cellcog/3d-model-generation-cellcog","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":73,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, prod"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:23:14.725Z","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":"2026-10-09T05:23:14.725Z","emptyReason":null},"stars":null,"forks":null,"downloads":4454,"packageName":null,"latestVersion":"1.0.15","tractionLabel":"4.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:23:14.725Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T05:23:14.725Z","lastCrawledAt":"2026-10-09T05:23:14.725Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T05:23:14.725Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.15","createdAt":"2026-08-24T02:02:47.474Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5317},{"version":"1.0.14","createdAt":"2026-08-24T01:47:30.035Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5312},{"version":"1.0.13","createdAt":"2026-08-03T06:07:32.814Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5153},{"version":"1.0.12","createdAt":"2026-08-02T22:04:25.778Z","changelog":"Display title updated.","fileCount":3,"zipByteSize":5256},{"version":"1.0.11","createdAt":"2026-07-17T03:40:20.681Z","changelog":"- Skill renamed to \"3d-model-generation-cellcog\" for consistency. - Removed the redundant skill-card.md file. - Documentation update: clarified skill name and description; no functional changes.","fileCount":3,"zipByteSize":5343},{"version":"1.0.10","createdAt":"2026-04-23T06:18:20.624Z","changelog":"- Added explicit declaration of required runtime dependencies for the skill: Python 3 executable and the CELLCOG_API_KEY environment variable. - These requirements are reflected in the OpenClaw metadata section to ensure proper installation and configuration across supported operating systems. - No other content changes or feature updates.","fileCount":3,"zipByteSize":5382},{"version":"1.0.9","createdAt":"2026-04-14T17:31:26.623Z","changelog":"- Updated SKILL.md for improved clarity and brevity in installation instructions. - Clarified agent usage examples, changing \"Cursor / Claude Code / Other agents\" to \"All agents except OpenClaw.\" - Revised installation guidance section to include command variants based on the tool in use. - No changes to core functionality or code; documentation only.","fileCount":2,"zipByteSize":4010},{"version":"1.0.8","createdAt":"2026-04-13T01:00:08.553Z","changelog":"- Improved and clarified the skill description to highlight AI-powered 3D model generation from text, images, or sketches. - Updated usage instructions with improved code samples, including more explicit import and initialization guidance for various agents. - Enhanced the description of capabilities (text-to-3D, image-to-3D, batch generation) and areas of application. - No changes to core functionality or API; documentation and onboarding are now clearer and more informative.","fileCount":2,"zipByteSize":4014}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176q1btpn094ats9b4f9hgfwx83knpk:3d-model-generation-cellcog","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-cellcog-3d-model-generation-cellcog/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T12:58:17.216Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-3d-model-generation-cellcog/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":"high","updatedAt":"2026-10-09T05:23:14.725Z","emptyReason":null},"readme":"Skill: 3D Model Generation\n\nOwner: cellcog\n\nSummary: AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\n\nTags: latest:1.0.15\n\nVersion history:\n\nv1.0.15 | 2026-08-24T02:02:47.474Z | user\n\nContent updated.\n\nv1.0.14 | 2026-08-24T01:47:30.035Z | user\n\nContent updated.\n\nv1.0.13 | 2026-08-03T06:07:32.814Z | user\n\nContent updated.\n\nv1.0.12 | 2026-08-02T22:04:25.778Z | user\n\nDisplay title updated.\n\nv1.0.11 | 2026-07-17T03:40:20.681Z | auto\n\n- Skill renamed to \"3d-model-generation-cellcog\" for consistency.\n- Removed the redundant skill-card.md file.\n- Documentation update: clarified skill name and description; no functional changes.\n\nv1.0.10 | 2026-04-23T06:18:20.624Z | auto\n\n- Added explicit declaration of required runtime dependencies for the skill: Python 3 executable and the CELLCOG_API_KEY environment variable.\n- These requirements are reflected in the OpenClaw metadata section to ensure proper installation and configuration across supported operating systems.\n- No other content changes or feature updates.\n\nv1.0.9 | 2026-04-14T17:31:26.623Z | auto\n\n- Updated SKILL.md for improved clarity and brevity in installation instructions.\n- Clarified agent usage examples, changing \"Cursor / Claude Code / Other agents\" to \"All agents except OpenClaw.\"\n- Revised installation guidance section to include command variants based on the tool in use.\n- No changes to core functionality or code; documentation only.\n\nv1.0.8 | 2026-04-13T01:00:08.553Z | auto\n\n- Improved and clarified the skill description to highlight AI-powered 3D model generation from text, images, or sketches.\n- Updated usage instructions with improved code samples, including more explicit import and initialization guidance for various agents.\n- Enhanced the description of capabilities (text-to-3D, image-to-3D, batch generation) and areas of application.\n- No changes to core functionality or API; documentation and onboarding are now clearer and more informative.\n\nv1.0.7 | 2026-04-12T23:34:42.190Z | auto\n\n- Simplified and shortened the skill description for clarity and focus.\n- Consolidated and clarified setup instructions, specifying usage in different agent environments.\n- Added a new section explaining what to do if CellCog is not installed, with setup steps for Cursor, OpenClaw, and other agents.\n- Removed some repeated intro and guidance, making the readme more concise while retaining all example prompts and key feature explanations.\n- General content tightening for readability and easier onboarding.\n\nv1.0.6 | 2026-04-08T05:57:21.619Z | auto\n\n- Expanded the documentation to cover new use cases, including batch generation, education/training, and asset pipelines.\n- Clarified the advantages of CellCog’s \"any-input to 3D\" workflow, emphasizing support for text, sketches, product photos, and batch prompts.\n- Added usage tips and detailed example prompts for a wider range of 3D asset needs.\n- Improved explanations for recommended chat modes and how to maximize model quality for various applications.\n- Updated output format section with compatibility details and editing guidance.\n\nv1.0.5 | 2026-04-06T05:06:33.584Z | auto\n\nVersion 1.0.5\n\n- Rewrote and condensed SKILL.md for clarity and brevity.\n- Streamlined feature summaries and removed repetitive marketing/comparison content.\n- Simplified instructions and descriptions for faster onboarding.\n- Added a \"Related Skills\" section for easier skill discovery.\n- Preserved essential usage details, supported input/output types, and example agent setup.\n\nv1.0.4 | 2026-04-03T01:42:44.978Z | auto\n\n- Updated OpenClaw integration instructions for prompt handling and task notification.\n- Clarified SDK setup requirements and usage for different agent types.\n- Added examples distinguishing OpenClaw's fire-and-forget mode from blocking modes.\n- Streamlined references to SDK documentation and API usage.\n\nv1.0.3 | 2026-04-03T00:07:11.761Z | auto\n\n- Updated Quick Start instructions in the Prerequisites section for clarity and brevity.\n- Added a note directing users to the main cellcog skill for full SDK/API documentation, including delivery modes and file handling.\n- Removed the previous fire-and-forget code snippet and notification explanation to simplify onboarding.\n- No changes to core capabilities, prompts, or output formats.\n\nv1.0.2 | 2026-04-02T03:33:20.916Z | auto\n\n- Updated skill icon emoji from 🧊 to 💎 in metadata.\n- No functional or documentation content changes.\n\nv1.0.1 | 2026-03-27T04:16:54.139Z | auto\n\n- Added supported operating systems (darwin, linux, windows) to metadata.\n- Added homepage link for CellCog (https://cellcog.ai).\n- Improved skill description for clarity and broader coverage.\n- No changes to core features or usage; documentation updated for completeness.\n\nv1.0.0 | 2026-02-14T10:12:38.903Z | user\n\n- Initial release of 3d-cog: Turn sketches, text, or product photos into production-ready 3D GLB models.\n- Supports input via text descriptions, rough sketches, product photos, or item lists.\n- Enables batch generation of multiple 3D models from a single prompt.\n- Integrates with the cellcog skill for streamlined SDK setup and API calls.\n- Outputs GLB files with textures and materials, compatible with major 3D software and engines.\n- Includes detailed examples, prompt patterns, and tips to optimize your 3D model requests.\n\nArchive index:\n\nArchive v1.0.15: 3 files, 5317 bytes\n\nFiles: skill-card.md (2111b), SKILL.md (7990b), _meta.json (147b)\n\nFile v1.0.15:SKILL.md\n\n---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Choosing Mode & Tier\n\n| Scenario | Recommended |\n|----------|-------------|\n| Single models and props | `chat_mode=\"agent\"` (defaults to the `\"flash\"` tier) |\n| Cross-asset consistency across a full set | `chat_mode=\"agent\", chat_tier=\"max\"` |\n\n**The flash tier is the default and handles most 3D generation well** — fast and economical. **Upgrade to `chat_tier=\"max\"`** when quality disappoints or the work is genuinely complex: just re-run the same prompt with `chat_tier=\"max\"`.\n\nAgent Team (`chat_mode=\"team\"`) is reserved for deep research — don't use it for 3D generation.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `openclaw skills install @cellcog/cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.15:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.15\",\n \"publishedAt\": 1787536967474\n}\n\nFile v1.0.15:skill-card.md\n\n## Description:\n\n3D Model Generation helps agents use CellCog to create production-ready GLB models from text descriptions, images, sketches, product photos, and batch item lists.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, designers, and content teams use this skill to prompt CellCog for text-to-3D, image-to-3D, and batch generation workflows that produce GLB assets for games, AR/VR, e-commerce, 3D printing, education, and visualization.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Uploads may include confidential product photos, regulated data, customer information, secrets, or proprietary sketches.\n\nMitigation: Only share those inputs with CellCog when your organization has approved that use.\n\nRisk: The workflow depends on the third-party CellCog package and service.\n\nMitigation: Confirm trust in the CellCog publisher before installing and pin package versions where your environment supports it.\n\nRisk: The skill requires a CELLCOG_API_KEY credential.\n\nMitigation: Store the API key in the environment and avoid placing it in prompts, generated files, or shared artifacts.\n\n## Reference(s):\n\n- [CellCog Homepage](https://cellcog.ai)\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Code, Shell commands, Configuration instructions, Files]\n\n**Output Format:** [Markdown guidance with Python code examples and shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires python3, the cellcog dependency, and CELLCOG_API_KEY; generated 3D assets are described as GLB files.]\n\n## Skill Version(s):\n\n1.0.15 (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 v1.0.14: 3 files, 5312 bytes\n\nFiles: skill-card.md (2081b), SKILL.md (7973b), _meta.json (147b)\n\nFile v1.0.14:SKILL.md\n\n---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Choosing Mode & Tier\n\n| Scenario | Recommended |\n|----------|-------------|\n| Single models and props | `chat_mode=\"agent\"` (defaults to the `\"flash\"` tier) |\n| Cross-asset consistency across a full set | `chat_mode=\"agent\", chat_tier=\"max\"` |\n\n**The flash tier is the default and handles most 3D generation well** — fast and economical. **Upgrade to `chat_tier=\"max\"`** when quality disappoints or the work is genuinely complex: just re-run the same prompt with `chat_tier=\"max\"`.\n\nAgent Team (`chat_mode=\"team\"`) is reserved for deep research — don't use it for 3D generation.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `clawhub install cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.14:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.14\",\n \"publishedAt\": 1787536050035\n}\n\nFile v1.0.14:skill-card.md\n\n## Description:\n\nAI 3D model generation powered by CellCog for text-to-3D, image-to-3D, and production-ready GLB files for games, AR/VR, e-commerce, and 3D printing.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, designers, and technical content teams use this skill to ask CellCog to create single or batched 3D assets from text prompts, sketches, reference images, product photos, or item lists. It is intended for workflows such as game assets, product visualization, AR/VR objects, 3D printing, education, and training.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, referenced images, sketches, product photos, and batch lists should be treated as content sent to CellCog's external service.\n\nMitigation: Do not upload secrets, private customer data, unreleased product assets, or regulated information unless your organization permits it.\n\nRisk: The skill requires a CellCog API key for cloud-service access.\n\nMitigation: Store CELLCOG_API_KEY in the environment or a managed secret store, and avoid placing credentials in prompts, files, logs, or generated examples.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog)\n- [CellCog Homepage](https://cellcog.ai)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Code, Shell commands, Configuration, Files]\n\n**Output Format:** [Markdown guidance with Python and shell examples; CellCog task results may include GLB files.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires python3, CELLCOG_API_KEY, and the CellCog package/cloud service.]\n\n## Skill Version(s):\n\n1.0.14 (source: server release metadata)\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 v1.0.13: 3 files, 5153 bytes\n\nFiles: skill-card.md (1917b), SKILL.md (7991b), _meta.json (147b)\n\nFile v1.0.13:SKILL.md\n\n---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `clawhub install cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.13:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.13\",\n \"publishedAt\": 1785737252814\n}\n\nFile v1.0.13:skill-card.md\n\n## Description:
\nAI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[cellcog](https://clawhub.ai/user/cellcog)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers, designers, and content teams use this skill to ask an agent to generate GLB 3D models from text prompts, reference images, sketches, product photos, or item lists for games, AR/VR, e-commerce, visualization, and 3D printing workflows.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Prompts, sketches, product photos, spreadsheets, and other reference assets may be sent to the external CellCog service for processing.
\nMitigation: Only upload assets that are approved for use with CellCog, and avoid secrets, regulated personal data, or confidential materials unless external processing is authorized.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog)
\n- [CellCog homepage](https://cellcog.ai)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]
\n**Output Format:** [Markdown guidance with Python and shell command examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Can initiate CellCog API calls that return GLB 3D model files through the CellCog service.]
\n\n## Skill Version(s):
\n1.0.13 (source: server release metadata)
\n\n## Ethical Considerations:
\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 v1.0.12: 3 files, 5256 bytes\n\nFiles: skill-card.md (2294b), SKILL.md (7916b), _meta.json (147b)\n\nFile v1.0.12:SKILL.md\n\n---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.12:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.12\",\n \"publishedAt\": 1785708265778\n}\n\nFile v1.0.12:skill-card.md\n\n## Description:
\nAI 3D model generation powered by CellCog for text-to-3D and image-to-3D workflows that produce production-ready GLB files for games, AR/VR, e-commerce, and 3D printing.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[cellcog](https://clawhub.ai/user/cellcog)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers, artists, and product teams use this skill to ask an agent to create single or batch 3D assets from text descriptions, sketches, photos, or item lists. It is intended for GLB asset workflows for games, AR/VR, e-commerce, product visualization, education, and 3D printing.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Generation prompts and referenced images or files may be sent to CellCog's external service.
\nMitigation: Use only data your organization permits for external processing, and avoid uploading secrets, regulated data, private customer information, or confidential designs.
\nRisk: The skill requires CELLCOG_API_KEY for authenticated CellCog access.
\nMitigation: Store the API key in the environment or approved secret storage and avoid including it in prompts, generated files, or logs.
\n\n\n## Reference(s):
\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog)
\n- [CellCog Homepage](https://cellcog.ai)
\n- [CellCog Publisher Profile](https://clawhub.ai/user/cellcog)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, code, shell commands, configuration, files]
\n**Output Format:** [Markdown guidance with Python examples, setup commands, and references to generated GLB files.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Generated assets are described as GLB files with textures and materials; use requires python3, the cellcog package, and CELLCOG_API_KEY.]
\n\n## Skill Version(s):
\n1.0.12 (source: server release evidence)
\n\n## Ethical Considerations:
\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 v1.0.11: 3 files, 5343 bytes\n\nFiles: skill-card.md (2482b), SKILL.md (7916b), _meta.json (147b)\n\nFile v1.0.11:SKILL.md\n\n---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.11:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.11\",\n \"publishedAt\": 1784259620681\n}\n\nFile v1.0.11:skill-card.md\n\n## Description:
\nAI 3D model generation powered by CellCog for text-to-3D and image-to-3D workflows that produce production-ready GLB files for games, AR/VR, e-commerce, 3D printing, and batch asset generation.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[nitishgargiitd](https://clawhub.ai/user/nitishgargiitd)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers, designers, and creative production teams use this skill to ask CellCog to create GLB 3D models from text prompts, reference images, sketches, product photos, or batch item lists.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Prompts and reference files selected by the user may be sent to CellCog for processing.
\nMitigation: Use only content approved for external processing, and avoid confidential, regulated, or proprietary designs unless organizational policy permits it.
\nRisk: CELLCOG_API_KEY could be exposed if copied into source files, logs, or chat messages.
\nMitigation: Store CELLCOG_API_KEY in an environment variable or secrets manager and avoid embedding it in prompts, code snippets, or committed files.
\nRisk: Generated GLB assets may not meet production, safety, performance, or brand requirements without review.
\nMitigation: Inspect generated models, textures, polygon counts, and licensing or usage constraints before deployment in games, AR/VR, e-commerce, or 3D printing workflows.
\n\n\n## Reference(s):
\n- [CellCog Homepage](https://cellcog.ai)
\n- [ClawHub Skill Page](https://clawhub.ai/nitishgargiitd/skills/3d-model-generation-cellcog)
\n- [ClawHub Publisher Profile](https://clawhub.ai/user/nitishgargiitd)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Code, API Calls, Configuration, Files]
\n**Output Format:** [Markdown guidance with Python code examples and CellCog-generated GLB files]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Requires python3, the cellcog dependency, and CELLCOG_API_KEY for CellCog API access.]
\n\n## Skill Version(s):
\n1.0.11 (source: server release metadata)
\n\n## Ethical Considerations:
\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 v1.0.10: 3 files, 5382 bytes\n\nFiles: skill-card.md (2567b), SKILL.md (7882b), _meta.json (147b)\n\nFile v1.0.10:SKILL.md\n\n---\nname: 3d-cog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Cog - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.10:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.10\",\n \"publishedAt\": 1776925100624\n}\n\nFile v1.0.10:skill-card.md\n\n## Description:
\nAI 3D model generation powered by CellCog for text-to-3D, image-to-3D, game assets, product visualization, characters, props, environments, and batch generation.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[nitishgargiitd](https://clawhub.ai/user/nitishgargiitd)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers, designers, and content teams use this skill to ask an agent to create GLB 3D models from text descriptions, reference images, sketches, product photos, or batch item lists for games, AR/VR, e-commerce, 3D printing, education, and training.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill sends prompts, images, sketches, product photos, or design inputs to CellCog as an external service.
\nMitigation: Avoid sending confidential designs, regulated data, private images, or third-party content unless you have permission and the service terms meet your requirements.
\nRisk: The skill requires CELLCOG_API_KEY, which could expose account access if copied into logs, commits, or shared transcripts.
\nMitigation: Store the API key in the agent environment or secret manager and keep it out of source files, chat transcripts, and command output.
\nRisk: Generated GLB assets may need review for geometry quality, material fidelity, platform performance, and rights suitability before use.
\nMitigation: Inspect and test generated models in the target engine or 3D tool, and confirm asset rights and content suitability before publishing or manufacturing.
\n\n\n## Reference(s):
\n- [CellCog](https://cellcog.ai)
\n- [ClawHub 3d Cog release](https://clawhub.ai/nitishgargiitd/3d-cog)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, code, shell commands, configuration, files]
\n**Output Format:** [Markdown guidance with Python examples, setup commands, and generated GLB files from the CellCog service.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Requires Python 3 and CELLCOG_API_KEY; generated 3D assets should be reviewed in the target toolchain before production use.]
\n\n## Skill Version(s):
\n1.0.10 (source: server release evidence)
\n\n## Ethical Considerations:
\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 v1.0.9: 2 files, 4010 bytes\n\nFiles: SKILL.md (7817b), _meta.json (146b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: 3d-cog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Cog - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.9:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.9\",\n \"publishedAt\": 1776187886623\n}\n\nArchive v1.0.8: 2 files, 4014 bytes\n\nFiles: SKILL.md (7834b), _meta.json (146b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: 3d-cog\ndescription: \"AI 3D model generation powered by CellCog. Create 3D models from text, images, or sketches — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Text-to-3D, image-to-3D, batch generation. Game assets, product visualization, characters, props, and environments.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Cog - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**Cursor / Claude Code / Other agents (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\n**Cursor:** Run `/cellcog-setup` to install and authenticate.\n**OpenClaw:** Run `clawhub install cellcog` for SDK setup.\n**Other agents:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.8:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.8\",\n \"publishedAt\": 1776042008553\n}\n\nArchive v1.0.7: 2 files, 3935 bytes\n\nFiles: SKILL.md (7628b), _meta.json (146b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: 3d-cog\ndescription: \"Powered by CellCog. 3D model generation from text or images. GLB output for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, and environments.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Cog - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**Cursor / Claude Code / Other agents (blocks until done):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\n---\n\n## If CellCog is not installed\n\n**Cursor:** Run `/cellcog-setup` to install and authenticate.\n**OpenClaw:** Run `clawhub install cellcog` for SDK setup.\n**Other agents:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.7:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.7\",\n \"publishedAt\": 1776036882190\n}\n\nArchive v1.0.6: 2 files, 3933 bytes\n\nFiles: SKILL.md (7681b), _meta.json (146b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: 3d-cog\ndescription: \"AI 3D model generation powered by CellCog. Create 3D models from text, images, or sketches — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Text-to-3D, image-to-3D, batch generation. Game assets, product visualization, characters, props, and environments.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n\n# 3D Cog - Turn Ideas Into 3D Models\n\n**Other tools need perfect images. CellCog turns ideas into 3D models.**\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n---\n\n## Prerequisites\n\nThis skill requires the `cellcog` skill for SDK setup and API calls.\n\n```bash\nclawhub install cellcog\n```\n\n**Read the cellcog skill first** for SDK setup. This skill shows you what's possible.\n\n**OpenClaw agents (fire-and-forget — recommended for long tasks):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\", # OpenClaw only\n task_label=\"my-task\",\n chat_mode=\"agent\", # See cellcog skill for all modes\n)\n```\n\n**All other agents (blocks until done):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\nSee the **cellcog** mothership skill for complete SDK API reference — delivery modes, timeouts, file handling, and more.\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\"\n```\n\n---\n\n## What You Can Create\n\n### Game Assets\n- **Characters**: Heroes, NPCs, enemies, bosses\n- **Weapons**: Swords, bows, staffs, shields, guns\n- **Props**: Furniture, treasure chests, potions, tools\n- **Vehicles**: Cars, spaceships, boats, mounts\n- **Environment pieces**: Trees, rocks, buildings, bridges\n\n### Product Visualization\n- **E-commerce 3D viewers**: Let customers rotate and inspect products\n- **Product prototypes**: Visualize designs before manufacturing\n- **Packaging mockups**: 3D packaging for marketing materials\n\n### AR/VR Objects\n- **AR filters and objects**: Place 3D objects in real environments\n- **VR environments**: Furnish virtual spaces with custom objects\n- **Interactive experiences**: Objects users can inspect and interact with\n\n### 3D Printing\n- **Figurines and miniatures**: Tabletop gaming pieces, collectibles\n- **Functional objects**: Custom tools, brackets, cases\n- **Architectural models**: Building miniatures, terrain pieces\n\n### Education & Training\n- **Anatomical models**: Organs, skeletal systems, molecular structures\n- **Historical artifacts**: Museum-quality digital replicas\n- **Engineering models**: Mechanical parts, assembly visualizations\n\n---\n\n## Output Format\n\nAll 3D models are delivered as **GLB files** (binary glTF) — the universal web standard for 3D:\n- Supported by Unity, Unreal, Godot, Three.js, Babylon.js\n- Works in web browsers via `` or Three.js\n- Compatible with Blender, Maya, 3ds Max for further editing\n- Includes textures and materials in a single file\n\n---\n\n## Chat Mode for 3D\n\n| Scenario | Recommended Mode |\n|----------|------------------|\n| Single 3D object from a clear description or image | `\"agent\"` |\n| Batch generation (5-20 objects from a list) | `\"agent\"` |\n| Complex game asset pipeline with style consistency | `\"agent team\"` |\n\n**Use `\"agent\"` for most 3D work.** It handles everything from single objects to batch generation.\n\n**Use `\"agent team\"` when you need cross-asset consistency** — like generating a full set of fantasy weapons that all share the same art style, or building a complete room of furniture that matches a design language.\n\n---\n\n## Example Prompts\n\n**Single object from description:**\n> \"Create a 3D model of a steampunk pocket watch with exposed brass gears, an etched glass face, and a chain attachment. GLB format, high detail.\"\n\n**From a reference image:**\n> \"Convert this product photo into a 3D model for our online store:\n> `/photos/sneaker_product.png`\n> \n> Output as GLB, enable PBR materials for realistic rendering.\"\n\n**Batch generation:**\n> \"Generate 3D models for these 8 pieces of modern furniture:\n> 1. Minimalist sofa (3-seater, light gray)\n> 2. Round coffee table (walnut wood, glass top)\n> 3. Floor lamp (arc style, brass finish)\n> 4. Bookshelf (5 tiers, oak wood)\n> 5. Dining chair (Scandinavian, white)\n> 6. Side table (concrete, cylindrical)\n> 7. Desk (standing desk, white with birch legs)\n> 8. TV console (low profile, dark walnut)\n> \n> All low-poly (~15,000 polygons), with PBR materials. GLB format.\"\n\n**From a rough sketch:**\n> \"Here's my rough sketch of a robot character:\n> `/sketches/robot_concept.jpg`\n> \n> Turn this into a polished 3D model. It's a friendly service robot — round body, simple limbs, LED face display. Style: Overwatch/Pixar clean 3D. Output as GLB.\"\n\n**Game asset set:**\n> \"I'm building a dungeon crawler. Create 3D models for these dungeon props:\n> - Wooden treasure chest (open and closed variants)\n> - Iron torch holder with flame\n> - Stone altar with carved runes\n> - Wooden barrel (intact and broken)\n> - Skull pile\n> \n> Style: Dark fantasy, hand-painted textures. Low poly for mobile game (~8,000 polygons each).\"\n\n---\n\n## Tips for Better 3D Models\n\n1. **Be specific about materials**: \"brushed aluminum\", \"aged leather\", \"polished marble\" — CellCog uses these to generate better reference images and textures.\n\n2. **Specify your target platform**: \"low-poly for mobile game\" vs \"high-detail for cinematic render\" changes the approach completely.\n\n3. **Send reference images when possible**: Even imperfect references give CellCog a head start over pure text descriptions.\n\n4. **For batch jobs, describe style once**: \"All in a cohesive hand-painted fantasy style\" keeps your assets consistent.\n\n5. **Request PBR materials for realism**: If you need metallic, roughness, and normal maps — say so. Essential for game engines and realistic rendering.\n\nFile v1.0.6:_meta.json\n\n{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.6\",\n \"publishedAt\": 1775627841619\n}","readmeExcerpt":"Skill: 3D Model Generation Owner: cellcog Summary: AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation. Tags: latest:1.0.15 Version history: v1.0.15 | 2026-08-24T02:02:47.474Z | user Content updated. v1.0.14 | 2026-08-24T01:47:30.035Z | us","codeSnippets":[],"executableExamples":[{"language":"python","snippet":"result = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)"},{"language":"python","snippet":"from cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])"},{"language":"python","snippet":"prompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\""},{"language":"python","snippet":"result = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)"},{"language":"python","snippet":"from cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])"},{"language":"python","snippet":"prompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golden sunburst head\n\nLow poly (~10,000 polygons each), game-ready, with PBR materials.\n\"\"\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: 3d-model-generation-cellcog\ndescription: \"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation.\"\nmetadata:\n openclaw:\n emoji: \"💎\"\n os: [darwin, linux, windows]\n requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# 3D Model Generation - Turn Ideas Into 3D Models\n\n3D model generation from text descriptions or reference images.\n\nMost 3D generation tools need a single, perfectly composed reference image. CellCog takes *anything* — a text description, a rough sketch, a product photo, even a spreadsheet of 50 items — and handles the entire pipeline: reasoning about what you need, generating optimized reference images, and converting them into production-ready GLB files.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n notify_session_key=\"agent:main:main\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n prompt=\"[your task prompt]\",\n task_label=\"my-task\",\n chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Makes This Different\n\n### Any Input → 3D\n\nThe power of CellCog isn't image-to-3D — everyone does that. The power is **any-to-any**.\n\n| What You Send | What CellCog Does | What You Get |\n|--------------|-------------------|--------------|\n| Text description | Reasons about the object → generates optimized reference image → converts to 3D | Production-ready GLB |\n| Rough sketch | Enhances into a clean, detailed reference → converts to 3D | Production-ready GLB |\n| Product photo | Assesses quality, enhances if needed → converts to 3D | Production-ready GLB |\n| High-quality concept art | Converts directly to 3D | Production-ready GLB |\n| List of 10 items | Generates 10 reference images → converts all to 3D | 10 GLB files |\n\n### Batch Generation\n\nNeed 10 low-poly weapons for your RPG? 20 furniture models for your room designer? 50 product models for your e-commerce catalog?\n\nOne prompt. Multiple 3D models. CellCog's agents generate each reference image with the right composition, angle, and detail level — then convert each to a textured 3D model.\n\n```python\nprompt = \"\"\"\nCreate 3D models (GLB format) for these 5 fantasy weapons:\n1. Enchanted longsword with blue crystal blade\n2. Dwarven war hammer with rune inscriptions\n3. Elven bow with living vine decorations\n4. Shadow dagger with smoke effects on the blade\n5. Holy mace with golde"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n \"slug\": \"3d-model-generation-cellcog\",\n \"version\": \"1.0.15\",\n \"publishedAt\": 1787536967474\n}"},{"path":"skill-card.md","content":"## Description:\n\n3D Model Generation helps agents use CellCog to create production-ready GLB models from text descriptions, images, sketches, product photos, and batch item lists.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, designers, and content teams use this skill to prompt CellCog for text-to-3D, image-to-3D, and batch generation workflows that produce GLB assets for games, AR/VR, e-commerce, 3D printing, education, and visualization.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Uploads may include confidential product photos, regulated data, customer information, secrets, or proprietary sketches.\n\nMitigation: Only share those inputs with CellCog when your organization has approved that use.\n\nRisk: The workflow depends on the third-party CellCog package and service.\n\nMitigation: Confirm trust in the CellCog publisher before installing and pin package versions where your environment supports it.\n\nRisk: The skill requires a CELLCOG_API_KEY credential.\n\nMitigation: Store the API key in the environment and avoid placing it in prompts, generated files, or shared artifacts.\n\n## Reference(s):\n\n- [CellCog Homepage](https://cellcog.ai)\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/3d-model-generation-cellcog)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Code, Shell commands, Configuration instructions, Files]\n\n**Output Format:** [Markdown guidance with Python code examples and shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires python3, the cellcog dependency, and CELLCOG_API_KEY; generated 3D assets are described as GLB files.]\n\n## Skill Version(s):\n\n1.0.15 (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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation. Skill: 3D Model Generation Owner: cellcog Summary: AI 3D model generation powered by CellCog. Text-to-3D, image-to-3D — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing. Game assets, product visualization, characters, props, environments, and batch generation. Tags: latest:1.0.15 Version history: v1.0.15 | 2026-08-24T02:02:47.474Z | user Content updated. v1.0.14 | 2026-08-24T01:47:30.035Z | us","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1262,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T05:23:14.725Z","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":"2026-10-09T05:23:14.725Z","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":"2026-10-09T12:58:17.219Z","emptyReason":null},"items":[{"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":"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":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","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"}]}}}