[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77H6775ZPQG2NETD5A83V2E":3,"skill-same:01M77H6775ZPQG2NETD5A83V2E":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M77H6775ZPQG2NETD5A83V2E","gradient-inference",null,"Community skill (unofficial) for DigitalOcean Gradient AI Serverless Inference. Discover available models and pricing, run chat completions or the Responses API with prompt caching, and generate images. OpenAI-compatible.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fg\u002Fgradient-inference\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gradient-inference\ndescription: >\n  Community skill (unofficial) for DigitalOcean Gradient AI Serverless Inference.\n  Discover available models and pricing, run chat completions or the Responses API\n  with prompt caching, and generate images. OpenAI-compatible.\nfiles: [\"scripts\u002F*\"]\nhomepage: https:\u002F\u002Fgithub.com\u002FRogue-Iteration\u002FTheBigClaw\nmetadata:\n  clawdbot:\n    emoji: \"🧠\"\n    primaryEnv: GRADIENT_API_KEY\n    requires:\n      env:\n        - GRADIENT_API_KEY\n      bins:\n        - python3\n      pip:\n        - requests>=2.31.0\n        - beautifulsoup4>=4.12.0\n  author: Rogue Iteration\n  version: \"0.1.3\"\n  tags: [\"digitalocean\", \"gradient-ai\", \"inferencing\", \"llm\", \"chat-completions\", \"image-generation\"]\n---\n\n# 🦞 Gradient AI — Serverless Inference\n\n> ⚠️ **This is an unofficial community skill**, not maintained by DigitalOcean. Use at your own risk.\n\n> *\"Why manage GPUs when the ocean provides?\" — ancient lobster proverb*\n\nUse DigitalOcean's [Gradient Serverless Inference](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F) to call large language models without managing infrastructure. The API is **OpenAI-compatible**, so standard SDKs and patterns work — just point at `https:\u002F\u002Finference.do-ai.run\u002Fv1` and swim.\n\n## Authentication\n\nAll requests need a **Model Access Key** in the `Authorization: Bearer` header.\n\n```bash\nexport GRADIENT_API_KEY=\"your-model-access-key\"\n```\n\n**Where to get one:** [DigitalOcean Console](https:\u002F\u002Fcloud.digitalocean.com) → Gradient AI → Model Access Keys → Create Key.\n\n📖 *[Full auth docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#create-a-model-access-key)*\n\n---\n\n## Tools\n\n### 🔍 List Available Models\n\nWindow-shop for LLMs before you swipe the card.\n\n```bash\npython3 gradient_models.py                    # Pretty table\npython3 gradient_models.py --json             # Machine-readable\npython3 gradient_models.py --filter \"llama\"   # Search by name\n```\n\nUse this before hardcoding model IDs — models are added and deprecated over time.\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fmodels \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" | python3 -m json.tool\n```\n\n📖 *[Models reference](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fmodels\u002F)*\n\n---\n\n### 💬 Chat Completions\n\nThe classic. Send structured messages (system\u002Fuser\u002Fassistant roles), get a response. OpenAI-compatible, so you probably already know how this works.\n\n```bash\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --system \"You are a helpful assistant.\" \\\n  --prompt \"Explain serverless inference in one paragraph.\"\n\n# Different model\npython3 gradient_chat.py \\\n  --model \"llama3.3-70b-instruct\" \\\n  --prompt \"Write a haiku about cloud computing.\"\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"openai-gpt-oss-120b\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n      {\"role\": \"user\", \"content\": \"Hello!\"}\n    ],\n    \"temperature\": 0.7,\n    \"max_tokens\": 1000\n  }'\n```\n\n📖 *[Chat Completions docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#chat-completions)*\n\n---\n\n### ⚡ Responses API (Recommended)\n\nDigitalOcean's [recommended endpoint](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#responses-api) for new integrations. Simpler request format and supports **prompt caching** — a.k.a. \"stop paying twice for the same context.\"\n\n```bash\n# Basic usage\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --prompt \"Summarize this earnings report.\" \\\n  --responses-api\n\n# With prompt caching (saves cost on follow-up queries)\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --prompt \"Now compare it to last quarter.\" \\\n  --responses-api --cache\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fresponses \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"openai-gpt-oss-120b\",\n    \"input\": \"Explain prompt caching.\",\n    \"store\": true\n  }'\n```\n\n**When to use which:**\n| | Chat Completions | Responses API |\n|---|---|---|\n| **Request format** | Array of messages with roles | Single `input` string |\n| **Prompt caching** | ❌ | ✅ via `store: true` |\n| **Multi-step tool use** | Manual | Built-in |\n| **Best for** | Structured conversations | Simple queries, cost savings |\n\n📖 *[Responses API docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#responses-api)*\n\n---\n\n### 🖼️ Generate Images\n\nTurn text prompts into images. Because sometimes a chart isn't enough.\n\n```bash\npython3 gradient_image.py --prompt \"A lobster trading stocks on Wall Street\"\npython3 gradient_image.py --prompt \"Sunset over the NYSE\" --output sunset.png\npython3 gradient_image.py --prompt \"Fintech logo\" --json\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"dall-e-3\",\n    \"prompt\": \"A lobster analyzing candlestick charts\",\n    \"n\": 1\n  }'\n```\n\n📖 *[Image generation docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#image-generation)*\n\n---\n\n## 🧠 Model Selection Guide\n\nNot all models are created equal. Choose wisely, young crustacean:\n\n| Model | Best For | Speed | Quality | Context |\n|-------|----------|-------|---------|---------|\n| `openai-gpt-oss-120b` | Complex reasoning, analysis, writing | Medium | ★★★★★ | 128K |\n| `llama3.3-70b-instruct` | General tasks, instruction following | Fast | ★★★★ | 128K |\n| `deepseek-r1-distill-llama-70b` | Math, code, step-by-step reasoning | Slow | ★★★★★ | 128K |\n| `qwen3-32b` | Quick triage, short tasks | Fastest | ★★★ | 32K |\n\n> **🦞 Pro tip: Cost-aware routing.** Use a fast model (e.g., `qwen3-32b`) to score or triage, then only escalate to a strong model (e.g., `openai-gpt-oss-120b`) when depth is needed. Enable prompt caching for repeated context.\n\nAlways run `python3 gradient_models.py` to check what's currently available — the menu changes.\n\n📖 *[Available models](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fmodels\u002F)*\n\n---\n\n### 💰 Model Pricing Lookup\n\nCheck what models cost *before* you rack up a bill. Scrapes the official [DigitalOcean pricing page](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fpricing\u002F) — no API key needed.\n\n```bash\npython3 gradient_pricing.py                    # Pretty table\npython3 gradient_pricing.py --json             # Machine-readable\npython3 gradient_pricing.py --model \"llama\"    # Filter by model name\npython3 gradient_pricing.py --no-cache         # Skip cache, fetch live\n```\n\n**How it works:**\n- Fetches live pricing from DigitalOcean's docs (public page, no auth)\n- Caches results for 24 hours in `\u002Ftmp\u002Fgradient_pricing_cache.json`\n- Falls back to a bundled snapshot if the live fetch fails\n\n> **🦞 Pro tip:** Run `python3 gradient_pricing.py --model \"gpt-oss\"` before choosing a model to see the cost difference between `gpt-oss-120b` ($0.10\u002F$0.70) and `gpt-oss-20b` ($0.05\u002F$0.45) per 1M tokens.\n\n📖 *[Pricing docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fpricing\u002F)*\n\n---\n\n## CLI Reference\n\nAll scripts accept `--json` for machine-readable output.\n\n```\ngradient_models.py   [--json] [--filter QUERY]\ngradient_chat.py     --prompt TEXT [--model ID] [--system TEXT]\n                     [--responses-api] [--cache] [--temperature F]\n                     [--max-tokens N] [--json]\ngradient_image.py    --prompt TEXT [--model ID] [--output PATH]\n                     [--size WxH] [--json]\ngradient_pricing.py  [--json] [--model QUERY] [--no-cache]\n```\n\n## External Endpoints\n\n| Endpoint | Purpose |\n|----------|---------|\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fmodels` | List available models |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fchat\u002Fcompletions` | Chat Completions API |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fresponses` | Responses API (recommended) |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fimages\u002Fgenerations` | Image generation |\n| `https:\u002F\u002Fdocs.digitalocean.com\u002F...\u002Fpricing\u002F` | Pricing page (scraped, public) |\n\n## Security & Privacy\n\n- All requests go to `inference.do-ai.run` — DigitalOcean's own endpoint\n- Your `GRADIENT_API_KEY` is sent as a Bearer token in the Authorization header\n- No other credentials or local data leave the machine\n- Model Access Keys are scoped to inference only — they can't manage your DO account\n- Prompt caching entries are scoped to your account and automatically expire\n\n## Trust Statement\n\n> By using this skill, prompts and data are sent to DigitalOcean's Gradient Inference API.\n> Only install if you trust DigitalOcean with the content you send to their LLMs.\n\n## Important Notes\n\n- Run `python3 gradient_models.py` before assuming a model exists — they rotate\n- All scripts exit with code 1 and print errors to stderr on failure\n","# 🦞 Gradient AI — Serverless Inference\n\n> ⚠️ **This is an unofficial community skill**, not maintained by DigitalOcean. Use at your own risk.\n\n> *\"Why manage GPUs when the ocean provides?\" — ancient lobster proverb*\n\nUse DigitalOcean's [Gradient Serverless Inference](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F) to call large language models without managing infrastructure. The API is **OpenAI-compatible**, so standard SDKs and patterns work — just point at `https:\u002F\u002Finference.do-ai.run\u002Fv1` and swim.\n\n## Authentication\n\nAll requests need a **Model Access Key** in the `Authorization: Bearer` header.\n\n```bash\nexport GRADIENT_API_KEY=\"your-model-access-key\"\n```\n\n**Where to get one:** [DigitalOcean Console](https:\u002F\u002Fcloud.digitalocean.com) → Gradient AI → Model Access Keys → Create Key.\n\n📖 *[Full auth docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#create-a-model-access-key)*\n\n---\n\n## Tools\n\n### 🔍 List Available Models\n\nWindow-shop for LLMs before you swipe the card.\n\n```bash\npython3 gradient_models.py                    # Pretty table\npython3 gradient_models.py --json             # Machine-readable\npython3 gradient_models.py --filter \"llama\"   # Search by name\n```\n\nUse this before hardcoding model IDs — models are added and deprecated over time.\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fmodels \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" | python3 -m json.tool\n```\n\n📖 *[Models reference](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fmodels\u002F)*\n\n---\n\n### 💬 Chat Completions\n\nThe classic. Send structured messages (system\u002Fuser\u002Fassistant roles), get a response. OpenAI-compatible, so you probably already know how this works.\n\n```bash\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --system \"You are a helpful assistant.\" \\\n  --prompt \"Explain serverless inference in one paragraph.\"\n\n# Different model\npython3 gradient_chat.py \\\n  --model \"llama3.3-70b-instruct\" \\\n  --prompt \"Write a haiku about cloud computing.\"\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"openai-gpt-oss-120b\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n      {\"role\": \"user\", \"content\": \"Hello!\"}\n    ],\n    \"temperature\": 0.7,\n    \"max_tokens\": 1000\n  }'\n```\n\n📖 *[Chat Completions docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#chat-completions)*\n\n---\n\n### ⚡ Responses API (Recommended)\n\nDigitalOcean's [recommended endpoint](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#responses-api) for new integrations. Simpler request format and supports **prompt caching** — a.k.a. \"stop paying twice for the same context.\"\n\n```bash\n# Basic usage\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --prompt \"Summarize this earnings report.\" \\\n  --responses-api\n\n# With prompt caching (saves cost on follow-up queries)\npython3 gradient_chat.py \\\n  --model \"openai-gpt-oss-120b\" \\\n  --prompt \"Now compare it to last quarter.\" \\\n  --responses-api --cache\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fresponses \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"openai-gpt-oss-120b\",\n    \"input\": \"Explain prompt caching.\",\n    \"store\": true\n  }'\n```\n\n**When to use which:**\n| | Chat Completions | Responses API |\n|---|---|---|\n| **Request format** | Array of messages with roles | Single `input` string |\n| **Prompt caching** | ❌ | ✅ via `store: true` |\n| **Multi-step tool use** | Manual | Built-in |\n| **Best for** | Structured conversations | Simple queries, cost savings |\n\n📖 *[Responses API docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#responses-api)*\n\n---\n\n### 🖼️ Generate Images\n\nTurn text prompts into images. Because sometimes a chart isn't enough.\n\n```bash\npython3 gradient_image.py --prompt \"A lobster trading stocks on Wall Street\"\npython3 gradient_image.py --prompt \"Sunset over the NYSE\" --output sunset.png\npython3 gradient_image.py --prompt \"Fintech logo\" --json\n```\n\n**Direct API call:**\n```bash\ncurl -s https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $GRADIENT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"dall-e-3\",\n    \"prompt\": \"A lobster analyzing candlestick charts\",\n    \"n\": 1\n  }'\n```\n\n📖 *[Image generation docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fhow-to\u002Fuse-serverless-inference\u002F#image-generation)*\n\n---\n\n## 🧠 Model Selection Guide\n\nNot all models are created equal. Choose wisely, young crustacean:\n\n| Model | Best For | Speed | Quality | Context |\n|-------|----------|-------|---------|---------|\n| `openai-gpt-oss-120b` | Complex reasoning, analysis, writing | Medium | ★★★★★ | 128K |\n| `llama3.3-70b-instruct` | General tasks, instruction following | Fast | ★★★★ | 128K |\n| `deepseek-r1-distill-llama-70b` | Math, code, step-by-step reasoning | Slow | ★★★★★ | 128K |\n| `qwen3-32b` | Quick triage, short tasks | Fastest | ★★★ | 32K |\n\n> **🦞 Pro tip: Cost-aware routing.** Use a fast model (e.g., `qwen3-32b`) to score or triage, then only escalate to a strong model (e.g., `openai-gpt-oss-120b`) when depth is needed. Enable prompt caching for repeated context.\n\nAlways run `python3 gradient_models.py` to check what's currently available — the menu changes.\n\n📖 *[Available models](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fmodels\u002F)*\n\n---\n\n### 💰 Model Pricing Lookup\n\nCheck what models cost *before* you rack up a bill. Scrapes the official [DigitalOcean pricing page](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fpricing\u002F) — no API key needed.\n\n```bash\npython3 gradient_pricing.py                    # Pretty table\npython3 gradient_pricing.py --json             # Machine-readable\npython3 gradient_pricing.py --model \"llama\"    # Filter by model name\npython3 gradient_pricing.py --no-cache         # Skip cache, fetch live\n```\n\n**How it works:**\n- Fetches live pricing from DigitalOcean's docs (public page, no auth)\n- Caches results for 24 hours in `\u002Ftmp\u002Fgradient_pricing_cache.json`\n- Falls back to a bundled snapshot if the live fetch fails\n\n> **🦞 Pro tip:** Run `python3 gradient_pricing.py --model \"gpt-oss\"` before choosing a model to see the cost difference between `gpt-oss-120b` ($0.10\u002F$0.70) and `gpt-oss-20b` ($0.05\u002F$0.45) per 1M tokens.\n\n📖 *[Pricing docs](https:\u002F\u002Fdocs.digitalocean.com\u002Fproducts\u002Fgradient-ai-platform\u002Fdetails\u002Fpricing\u002F)*\n\n---\n\n## CLI Reference\n\nAll scripts accept `--json` for machine-readable output.\n\n```\ngradient_models.py   [--json] [--filter QUERY]\ngradient_chat.py     --prompt TEXT [--model ID] [--system TEXT]\n                     [--responses-api] [--cache] [--temperature F]\n                     [--max-tokens N] [--json]\ngradient_image.py    --prompt TEXT [--model ID] [--output PATH]\n                     [--size WxH] [--json]\ngradient_pricing.py  [--json] [--model QUERY] [--no-cache]\n```\n\n## External Endpoints\n\n| Endpoint | Purpose |\n|----------|---------|\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fmodels` | List available models |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fchat\u002Fcompletions` | Chat Completions API |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fresponses` | Responses API (recommended) |\n| `https:\u002F\u002Finference.do-ai.run\u002Fv1\u002Fimages\u002Fgenerations` | Image generation |\n| `https:\u002F\u002Fdocs.digitalocean.com\u002F...\u002Fpricing\u002F` | Pricing page (scraped, public) |\n\n## Security & Privacy\n\n- All requests go to `inference.do-ai.run` — DigitalOcean's own endpoint\n- Your `GRADIENT_API_KEY` is sent as a Bearer token in the Authorization header\n- No other credentials or local data leave the machine\n- Model Access Keys are scoped to inference only — they can't manage your DO account\n- Prompt caching entries are scoped to your account and automatically expire\n\n## Trust Statement\n\n> By using this skill, prompts and data are sent to DigitalOcean's Gradient Inference API.\n> Only install if you trust DigitalOcean with the content you send to their LLMs.\n\n## Important Notes\n\n- Run `python3 gradient_models.py` before assuming a model exists — they rotate\n- All scripts exit with code 1 and print errors to stderr on failure\n",{"name":5,"files":24,"homepage":26,"metadata":27,"description":47},[25],"scripts\u002F*","https:\u002F\u002Fgithub.com\u002FRogue-Iteration\u002FTheBigClaw",{"tags":28,"author":35,"version":36,"clawdbot":37},[29,30,31,32,33,34],"digitalocean","gradient-ai","inferencing","llm","chat-completions","image-generation","Rogue Iteration","0.1.3",{"emoji":38,"requires":39,"primaryEnv":41},"🧠",{"env":40,"pip":42,"bins":45},[41],"GRADIENT_API_KEY",[43,44],"requests>=2.31.0","beautifulsoup4>=4.12.0",[46],"python3","Community skill (unofficial) for DigitalOcean Gradient AI Serverless Inference. Discover available models and pricing, run chat completions or the Responses API with prompt caching, and generate images. OpenAI-compatible.\n","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fg\u002Fgradient-inference",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill gradient-inference",{"tool":63,"command":64},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill gradient-inference",{"tool":66,"command":67},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill gradient-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fg\u002Fgradient-inference\u002FSKILL.md",true,[],[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]