[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FT79EWQHMHS4M2SV2CB0GV":3,"skill-same:01M6FT79EWQHMHS4M2SV2CB0GV":126},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":69,"commitSha":70,"skillDirectory":71,"forksCount":72,"repositoryHtmlUrl":73,"repositoryHomepageUrl":6,"ownerHtmlUrl":74,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":75,"install":76,"resources":89},"01M6FT79EWQHMHS4M2SV2CB0GV","venice-ai",null,"Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"venice ai","python3","complete","creation","platform","full","images","install","brew","editing","image","text","web search","Audio","Video","api","AI Platform","embeddings","search","speech","2026-11-10 10:12:30",false,"---\nname: venice-ai\ndescription: Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything.\nhomepage: https:\u002F\u002Fvenice.ai\nmetadata:\n  {\n    \"clawdbot\":\n      {\n        \"emoji\": \"?️\",\n        \"requires\": { \"bins\": [\"python3\"], \"env\": [\"VENICE_API_KEY\"] },\n        \"primaryEnv\": \"VENICE_API_KEY\",\n        \"notes\": \"Full Venice AI platform — text, images, video, audio, embeddings. One skill for everything.\",\n        \"install\":\n          [\n            {\n              \"id\": \"python-brew\",\n              \"kind\": \"brew\",\n              \"formula\": \"python\",\n              \"bins\": [\"python3\"],\n              \"label\": \"Install Python (brew)\",\n            },\n          ],\n      },\n  }\n---\n\n# Venice AI — Complete Platform Skill\n\n## What is Venice AI?\n\n**Venice AI is the AI platform for people who don't want Big Tech watching over their shoulder.** Unlike OpenAI, Anthropic, and Google — where every prompt is logged, analyzed, and potentially used to train future models — Venice offers **true privacy** with zero data retention on private models. Your conversations stay yours.\n\nVenice is also **uncensored**: no content filters, no refusals, no \"I can't help with that.\" The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.\n\n**Why agents should care:**\n- **Private inference** — Models marked \"Private\" have zero data retention. Process sensitive data without it leaking into training sets.\n- **Uncensored responses** — No guardrails blocking legitimate use cases. Generate any content your workflow needs.\n- **OpenAI-compatible API** — Drop-in replacement. Same API format, just change the base URL.\n- **30+ models** — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.\n- **Built-in web search** — LLMs can search the web and cite sources in a single API call.\n- **Image & video generation** — Flux, Sora, Runway, WAN models for visual content.\n\nThis skill gives you the **complete Venice platform**: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.\n\n> **⚠️ API changes:** If something doesn't work as expected, check [docs.venice.ai](https:\u002F\u002Fdocs.venice.ai) — the API specs may have been updated since this skill was written.\n\n## Prerequisites\n\n- **Python 3.10+**\n- **Venice API key** (free tier available at [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi))\n\n## Setup\n\n### Get Your API Key\n\n1. Create account at [venice.ai](https:\u002F\u002Fvenice.ai)\n2. Go to [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi)\n3. Click \"Create API Key\" → copy the key (starts with `vn_...`)\n\n### Configure\n\n**Option A: Environment variable**\n```bash\nexport VENICE_API_KEY=\"vn_your_key_here\"\n```\n\n**Option B: Clawdbot config** (recommended)\n```json5\n\u002F\u002F ~\u002F.clawdbot\u002Fclawdbot.json\n{\n  skills: {\n    entries: {\n      \"venice-ai\": {\n        env: { VENICE_API_KEY: \"vn_your_key_here\" }\n      }\n    }\n  }\n}\n```\n\n### Verify\n```bash\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text\n```\n\n## Scripts Overview\n\n| Script | Purpose |\n|--------|---------|\n| `venice.py` | Text generation, models, embeddings, TTS, transcription |\n| `venice-image.py` | Image generation (Flux, etc.) |\n| `venice-video.py` | Video generation (Sora, WAN, Runway) |\n| `venice-upscale.py` | Image upscaling |\n| `venice-edit.py` | AI image editing |\n\n---\n\n# Part 1: Text & Audio\n\n## Model Discovery & Selection\n\nVenice has a huge model catalog spanning text, image, video, audio, and embeddings.\n\n### Browse Models\n```bash\n# List all text models\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text\n\n# List image models\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type image\n\n# List all model types\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text,image,video,audio,embedding\n\n# Get details on a specific model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --filter llama\n```\n\n### Model Selection Guide\n\n| Need | Recommended Model | Why |\n|------|------------------|-----|\n| **Cheapest text** | `qwen3-4b` ($0.05\u002FM in) | Tiny, fast, efficient |\n| **Best uncensored** | `venice-uncensored` ($0.20\u002FM in) | Venice's own uncensored model |\n| **Best private + smart** | `deepseek-v3.2` ($0.40\u002FM in) | Great reasoning, efficient |\n| **Vision\u002Fmultimodal** | `qwen3-vl-235b-a22b` ($0.25\u002FM in) | Sees images |\n| **Best coding** | `qwen3-coder-480b-a35b-instruct` ($0.75\u002FM in) | Massive coder model |\n| **Frontier (budget)** | `grok-41-fast` ($0.50\u002FM in) | Fast, 262K context |\n| **Frontier (max quality)** | `claude-opus-4-6` ($6\u002FM in) | Best overall quality |\n| **Reasoning** | `kimi-k2-5` ($0.75\u002FM in) | Strong chain-of-thought |\n| **Web search** | Any model + `enable_web_search` | Built-in web search |\n\n---\n\n## Text Generation (Chat Completions)\n\n### Basic Generation\n```bash\n# Simple prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"What is the meaning of life?\"\n\n# Choose a model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Explain quantum computing\" --model deepseek-v3.2\n\n# System prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Review this code\" --system \"You are a senior engineer.\"\n\n# Read from stdin\necho \"Summarize this\" | python3 {baseDir}\u002Fscripts\u002Fvenice.py chat --model qwen3-4b\n\n# Stream output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Write a story\" --stream\n```\n\n### Web Search Integration\n```bash\n# Auto web search (model decides when to search)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"What happened in tech news today?\" --web-search auto\n\n# Force web search with citations\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Current Bitcoin price\" --web-search on --web-citations\n\n# Web scraping (extracts content from URLs in prompt)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Summarize: https:\u002F\u002Fexample.com\u002Farticle\" --web-scrape\n```\n\n### Uncensored Mode\n```bash\n# Use Venice's own uncensored model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Your question\" --model venice-uncensored\n\n# Disable Venice system prompts for raw model output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Your prompt\" --no-venice-system-prompt\n```\n\n### Reasoning Models\n```bash\n# Use a reasoning model with effort control\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Solve this math problem...\" --model kimi-k2-5 --reasoning-effort high\n\n# Strip thinking from output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Debug this code\" --model qwen3-4b --strip-thinking\n```\n\n### Advanced Options\n```bash\n# Temperature and token control\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Be creative\" --temperature 1.2 --max-tokens 4000\n\n# JSON output mode\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"List 5 colors as JSON\" --json\n\n# Prompt caching (for repeated context)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Question\" --cache-key my-session-123\n\n# Show usage stats\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Hello\" --show-usage\n```\n\n---\n\n## Embeddings\n\nGenerate vector embeddings for semantic search, RAG, and recommendations:\n\n```bash\n# Single text\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"Venice is a private AI platform\"\n\n# Multiple texts (batch)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"first text\" \"second text\" \"third text\"\n\n# From file (one text per line)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed --file texts.txt\n\n# Output as JSON\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"some text\" --output json\n```\n\nModel: `text-embedding-bge-m3` (private, $0.15\u002FM tokens)\n\n---\n\n## Text-to-Speech (TTS)\n\nConvert text to speech with 60+ multilingual voices:\n\n```bash\n# Default voice\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Hello, welcome to Venice AI\"\n\n# Choose a voice\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Exciting news!\" --voice af_nova\n\n# List available voices\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts --list-voices\n\n# Custom output path\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Some text\" --output \u002Ftmp\u002Fspeech.mp3\n\n# Adjust speed\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Speaking slowly\" --speed 0.8\n```\n\n**Popular voices:** `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` (Chinese), `jm_kumo` (Japanese)\n\nModel: `tts-kokoro` (private, $3.50\u002FM characters)\n\n---\n\n## Speech-to-Text (Transcription)\n\nTranscribe audio files to text:\n\n```bash\n# Transcribe a file\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe audio.wav\n\n# With timestamps\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe recording.mp3 --timestamps\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe --url https:\u002F\u002Fexample.com\u002Faudio.wav\n```\n\nSupported formats: WAV, FLAC, MP3, M4A, AAC, MP4\n\nModel: `nvidia\u002Fparakeet-tdt-0.6b-v3` (private, $0.0001\u002Faudio second)\n\n---\n\n## Check Balance\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fvenice.py balance\n```\n\n---\n\n# Part 2: Images & Video\n\n## Pricing Overview\n\n| Feature | Cost |\n|---------|------|\n| Image generation | ~$0.01-0.03 per image |\n| Image upscale | ~$0.02-0.04 |\n| Image edit | $0.04 |\n| Video (WAN) | ~$0.10-0.50 |\n| Video (Sora) | ~$0.50-2.00 |\n| Video (Runway) | ~$0.20-1.00 |\n\nUse `--quote` with video commands to check pricing before generation.\n\n---\n\n## Image Generation\n\n```bash\n# Basic generation\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"a serene canal in Venice at sunset\"\n\n# Multiple images\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"cyberpunk city\" --count 4\n\n# Custom dimensions\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"portrait\" --width 768 --height 1024\n\n# List available models and styles\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --list-models\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --list-styles\n\n# Use specific model and style\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"fantasy\" --model flux-2-pro --style-preset \"Cinematic\"\n\n# Reproducible results with seed\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"abstract\" --seed 12345\n```\n\n**Key flags:** `--prompt`, `--model` (default: flux-2-max), `--count`, `--width`, `--height`, `--format` (webp\u002Fpng\u002Fjpeg), `--resolution` (1K\u002F2K\u002F4K), `--aspect-ratio`, `--negative-prompt`, `--style-preset`, `--cfg-scale` (0-20), `--seed`, `--safe-mode`, `--hide-watermark`, `--embed-exif`\n\n---\n\n## Image Upscale\n\n```bash\n# 2x upscale\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --scale 2\n\n# 4x with AI enhancement\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --scale 4 --enhance\n\n# Enhanced with custom prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --enhance --enhance-prompt \"sharpen details\"\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py --url \"https:\u002F\u002Fexample.com\u002Fimage.jpg\" --scale 2\n```\n\n**Key flags:** `--scale` (1-4, default: 2), `--enhance` (AI enhancement), `--enhance-prompt`, `--enhance-creativity` (0.0-1.0), `--url`, `--output`\n\n---\n\n## Image Edit\n\nAI-powered image editing:\n\n```bash\n# Add elements\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"add sunglasses\"\n\n# Modify scene\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"change the sky to sunset\"\n\n# Remove objects\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"remove the person in background\"\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py --url \"https:\u002F\u002Fexample.com\u002Fimage.jpg\" --prompt \"colorize\"\n```\n\n**Note:** The edit endpoint uses Qwen-Image which has some content restrictions.\n\n---\n\n## Video Generation\n\n```bash\n# Get price quote first\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --quote --model wan-2.6-image-to-video --duration 10s\n\n# Image-to-video (WAN - default)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --image photo.jpg --prompt \"camera pans slowly\" --duration 10s\n\n# Image-to-video (Sora)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --image photo.jpg --prompt \"cinematic\" \\\n  --model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param\n\n# Video-to-video (Runway Gen4)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --video input.mp4 --prompt \"anime style\" \\\n  --model runway-gen4-turbo-v2v\n\n# List models with available durations\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --list-models\n```\n\n**Key flags:** `--image` or `--video`, `--prompt`, `--model` (default: wan-2.6-image-to-video), `--duration`, `--resolution` (480p\u002F720p\u002F1080p), `--aspect-ratio`, `--audio`\u002F`--no-audio`, `--quote`, `--timeout`\n\n**Models:**\n- **WAN** — Image-to-video, configurable audio, 5s-21s\n- **Sora** — Requires `--aspect-ratio`, use `--skip-audio-param`\n- **Runway** — Video-to-video transformation\n\n---\n\n# Tips & Ideas\n\n### ? Web Search + LLM = Research Assistant\nUse `--web-search on --web-citations` to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call.\n\n### ? Uncensored Creative Content\nVenice's uncensored models work for both text AND images. No guardrails blocking legitimate creative use cases.\n\n### ? Prompt Caching for Agents\nIf you're running an agent loop that sends the same system prompt repeatedly, use `--cache-key` to get up to 90% cost savings.\n\n### ? Audio Pipeline\nCombine TTS and transcription: generate spoken content with `tts`, process audio with `transcribe`. Both are private inference.\n\n### ? Video Workflow\n1. Generate or find a base image\n2. Use `--quote` to estimate video cost\n3. Generate with appropriate duration\u002Fmodel\n4. Videos take 1-5 minutes depending on settings\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| `VENICE_API_KEY not set` | Set env var or configure in `~\u002F.clawdbot\u002Fclawdbot.json` |\n| `Invalid API key` | Verify at [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi) |\n| `Model not found` | Run `--list-models` to see available; use `--no-validate` for new models |\n| Rate limited | Check `--show-usage` output |\n| Video stuck | Videos can take 1-5 min; use `--timeout 600` for long ones |\n\n## Resources\n\n- **API Docs**: [docs.venice.ai](https:\u002F\u002Fdocs.venice.ai)\n- **Status**: [veniceai-status.com](https:\u002F\u002Fveniceai-status.com)\n- **Discord**: [discord.gg\u002Faskvenice](https:\u002F\u002Fdiscord.gg\u002Faskvenice)\n","# Venice AI — Complete Platform Skill\n\n## What is Venice AI?\n\n**Venice AI is the AI platform for people who don't want Big Tech watching over their shoulder.** Unlike OpenAI, Anthropic, and Google — where every prompt is logged, analyzed, and potentially used to train future models — Venice offers **true privacy** with zero data retention on private models. Your conversations stay yours.\n\nVenice is also **uncensored**: no content filters, no refusals, no \"I can't help with that.\" The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.\n\n**Why agents should care:**\n- **Private inference** — Models marked \"Private\" have zero data retention. Process sensitive data without it leaking into training sets.\n- **Uncensored responses** — No guardrails blocking legitimate use cases. Generate any content your workflow needs.\n- **OpenAI-compatible API** — Drop-in replacement. Same API format, just change the base URL.\n- **30+ models** — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.\n- **Built-in web search** — LLMs can search the web and cite sources in a single API call.\n- **Image & video generation** — Flux, Sora, Runway, WAN models for visual content.\n\nThis skill gives you the **complete Venice platform**: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.\n\n> **⚠️ API changes:** If something doesn't work as expected, check [docs.venice.ai](https:\u002F\u002Fdocs.venice.ai) — the API specs may have been updated since this skill was written.\n\n## Prerequisites\n\n- **Python 3.10+**\n- **Venice API key** (free tier available at [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi))\n\n## Setup\n\n### Get Your API Key\n\n1. Create account at [venice.ai](https:\u002F\u002Fvenice.ai)\n2. Go to [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi)\n3. Click \"Create API Key\" → copy the key (starts with `vn_...`)\n\n### Configure\n\n**Option A: Environment variable**\n```bash\nexport VENICE_API_KEY=\"vn_your_key_here\"\n```\n\n**Option B: Clawdbot config** (recommended)\n```json5\n\u002F\u002F ~\u002F.clawdbot\u002Fclawdbot.json\n{\n  skills: {\n    entries: {\n      \"venice-ai\": {\n        env: { VENICE_API_KEY: \"vn_your_key_here\" }\n      }\n    }\n  }\n}\n```\n\n### Verify\n```bash\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text\n```\n\n## Scripts Overview\n\n| Script | Purpose |\n|--------|---------|\n| `venice.py` | Text generation, models, embeddings, TTS, transcription |\n| `venice-image.py` | Image generation (Flux, etc.) |\n| `venice-video.py` | Video generation (Sora, WAN, Runway) |\n| `venice-upscale.py` | Image upscaling |\n| `venice-edit.py` | AI image editing |\n\n---\n\n# Part 1: Text & Audio\n\n## Model Discovery & Selection\n\nVenice has a huge model catalog spanning text, image, video, audio, and embeddings.\n\n### Browse Models\n```bash\n# List all text models\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text\n\n# List image models\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type image\n\n# List all model types\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --type text,image,video,audio,embedding\n\n# Get details on a specific model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py models --filter llama\n```\n\n### Model Selection Guide\n\n| Need | Recommended Model | Why |\n|------|------------------|-----|\n| **Cheapest text** | `qwen3-4b` ($0.05\u002FM in) | Tiny, fast, efficient |\n| **Best uncensored** | `venice-uncensored` ($0.20\u002FM in) | Venice's own uncensored model |\n| **Best private + smart** | `deepseek-v3.2` ($0.40\u002FM in) | Great reasoning, efficient |\n| **Vision\u002Fmultimodal** | `qwen3-vl-235b-a22b` ($0.25\u002FM in) | Sees images |\n| **Best coding** | `qwen3-coder-480b-a35b-instruct` ($0.75\u002FM in) | Massive coder model |\n| **Frontier (budget)** | `grok-41-fast` ($0.50\u002FM in) | Fast, 262K context |\n| **Frontier (max quality)** | `claude-opus-4-6` ($6\u002FM in) | Best overall quality |\n| **Reasoning** | `kimi-k2-5` ($0.75\u002FM in) | Strong chain-of-thought |\n| **Web search** | Any model + `enable_web_search` | Built-in web search |\n\n---\n\n## Text Generation (Chat Completions)\n\n### Basic Generation\n```bash\n# Simple prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"What is the meaning of life?\"\n\n# Choose a model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Explain quantum computing\" --model deepseek-v3.2\n\n# System prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Review this code\" --system \"You are a senior engineer.\"\n\n# Read from stdin\necho \"Summarize this\" | python3 {baseDir}\u002Fscripts\u002Fvenice.py chat --model qwen3-4b\n\n# Stream output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Write a story\" --stream\n```\n\n### Web Search Integration\n```bash\n# Auto web search (model decides when to search)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"What happened in tech news today?\" --web-search auto\n\n# Force web search with citations\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Current Bitcoin price\" --web-search on --web-citations\n\n# Web scraping (extracts content from URLs in prompt)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Summarize: https:\u002F\u002Fexample.com\u002Farticle\" --web-scrape\n```\n\n### Uncensored Mode\n```bash\n# Use Venice's own uncensored model\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Your question\" --model venice-uncensored\n\n# Disable Venice system prompts for raw model output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Your prompt\" --no-venice-system-prompt\n```\n\n### Reasoning Models\n```bash\n# Use a reasoning model with effort control\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Solve this math problem...\" --model kimi-k2-5 --reasoning-effort high\n\n# Strip thinking from output\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Debug this code\" --model qwen3-4b --strip-thinking\n```\n\n### Advanced Options\n```bash\n# Temperature and token control\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Be creative\" --temperature 1.2 --max-tokens 4000\n\n# JSON output mode\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"List 5 colors as JSON\" --json\n\n# Prompt caching (for repeated context)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Question\" --cache-key my-session-123\n\n# Show usage stats\npython3 {baseDir}\u002Fscripts\u002Fvenice.py chat \"Hello\" --show-usage\n```\n\n---\n\n## Embeddings\n\nGenerate vector embeddings for semantic search, RAG, and recommendations:\n\n```bash\n# Single text\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"Venice is a private AI platform\"\n\n# Multiple texts (batch)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"first text\" \"second text\" \"third text\"\n\n# From file (one text per line)\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed --file texts.txt\n\n# Output as JSON\npython3 {baseDir}\u002Fscripts\u002Fvenice.py embed \"some text\" --output json\n```\n\nModel: `text-embedding-bge-m3` (private, $0.15\u002FM tokens)\n\n---\n\n## Text-to-Speech (TTS)\n\nConvert text to speech with 60+ multilingual voices:\n\n```bash\n# Default voice\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Hello, welcome to Venice AI\"\n\n# Choose a voice\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Exciting news!\" --voice af_nova\n\n# List available voices\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts --list-voices\n\n# Custom output path\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Some text\" --output \u002Ftmp\u002Fspeech.mp3\n\n# Adjust speed\npython3 {baseDir}\u002Fscripts\u002Fvenice.py tts \"Speaking slowly\" --speed 0.8\n```\n\n**Popular voices:** `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` (Chinese), `jm_kumo` (Japanese)\n\nModel: `tts-kokoro` (private, $3.50\u002FM characters)\n\n---\n\n## Speech-to-Text (Transcription)\n\nTranscribe audio files to text:\n\n```bash\n# Transcribe a file\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe audio.wav\n\n# With timestamps\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe recording.mp3 --timestamps\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice.py transcribe --url https:\u002F\u002Fexample.com\u002Faudio.wav\n```\n\nSupported formats: WAV, FLAC, MP3, M4A, AAC, MP4\n\nModel: `nvidia\u002Fparakeet-tdt-0.6b-v3` (private, $0.0001\u002Faudio second)\n\n---\n\n## Check Balance\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fvenice.py balance\n```\n\n---\n\n# Part 2: Images & Video\n\n## Pricing Overview\n\n| Feature | Cost |\n|---------|------|\n| Image generation | ~$0.01-0.03 per image |\n| Image upscale | ~$0.02-0.04 |\n| Image edit | $0.04 |\n| Video (WAN) | ~$0.10-0.50 |\n| Video (Sora) | ~$0.50-2.00 |\n| Video (Runway) | ~$0.20-1.00 |\n\nUse `--quote` with video commands to check pricing before generation.\n\n---\n\n## Image Generation\n\n```bash\n# Basic generation\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"a serene canal in Venice at sunset\"\n\n# Multiple images\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"cyberpunk city\" --count 4\n\n# Custom dimensions\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"portrait\" --width 768 --height 1024\n\n# List available models and styles\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --list-models\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --list-styles\n\n# Use specific model and style\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"fantasy\" --model flux-2-pro --style-preset \"Cinematic\"\n\n# Reproducible results with seed\npython3 {baseDir}\u002Fscripts\u002Fvenice-image.py --prompt \"abstract\" --seed 12345\n```\n\n**Key flags:** `--prompt`, `--model` (default: flux-2-max), `--count`, `--width`, `--height`, `--format` (webp\u002Fpng\u002Fjpeg), `--resolution` (1K\u002F2K\u002F4K), `--aspect-ratio`, `--negative-prompt`, `--style-preset`, `--cfg-scale` (0-20), `--seed`, `--safe-mode`, `--hide-watermark`, `--embed-exif`\n\n---\n\n## Image Upscale\n\n```bash\n# 2x upscale\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --scale 2\n\n# 4x with AI enhancement\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --scale 4 --enhance\n\n# Enhanced with custom prompt\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py photo.jpg --enhance --enhance-prompt \"sharpen details\"\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice-upscale.py --url \"https:\u002F\u002Fexample.com\u002Fimage.jpg\" --scale 2\n```\n\n**Key flags:** `--scale` (1-4, default: 2), `--enhance` (AI enhancement), `--enhance-prompt`, `--enhance-creativity` (0.0-1.0), `--url`, `--output`\n\n---\n\n## Image Edit\n\nAI-powered image editing:\n\n```bash\n# Add elements\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"add sunglasses\"\n\n# Modify scene\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"change the sky to sunset\"\n\n# Remove objects\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py photo.jpg --prompt \"remove the person in background\"\n\n# From URL\npython3 {baseDir}\u002Fscripts\u002Fvenice-edit.py --url \"https:\u002F\u002Fexample.com\u002Fimage.jpg\" --prompt \"colorize\"\n```\n\n**Note:** The edit endpoint uses Qwen-Image which has some content restrictions.\n\n---\n\n## Video Generation\n\n```bash\n# Get price quote first\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --quote --model wan-2.6-image-to-video --duration 10s\n\n# Image-to-video (WAN - default)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --image photo.jpg --prompt \"camera pans slowly\" --duration 10s\n\n# Image-to-video (Sora)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --image photo.jpg --prompt \"cinematic\" \\\n  --model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param\n\n# Video-to-video (Runway Gen4)\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --video input.mp4 --prompt \"anime style\" \\\n  --model runway-gen4-turbo-v2v\n\n# List models with available durations\npython3 {baseDir}\u002Fscripts\u002Fvenice-video.py --list-models\n```\n\n**Key flags:** `--image` or `--video`, `--prompt`, `--model` (default: wan-2.6-image-to-video), `--duration`, `--resolution` (480p\u002F720p\u002F1080p), `--aspect-ratio`, `--audio`\u002F`--no-audio`, `--quote`, `--timeout`\n\n**Models:**\n- **WAN** — Image-to-video, configurable audio, 5s-21s\n- **Sora** — Requires `--aspect-ratio`, use `--skip-audio-param`\n- **Runway** — Video-to-video transformation\n\n---\n\n# Tips & Ideas\n\n### ? Web Search + LLM = Research Assistant\nUse `--web-search on --web-citations` to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call.\n\n### ? Uncensored Creative Content\nVenice's uncensored models work for both text AND images. No guardrails blocking legitimate creative use cases.\n\n### ? Prompt Caching for Agents\nIf you're running an agent loop that sends the same system prompt repeatedly, use `--cache-key` to get up to 90% cost savings.\n\n### ? Audio Pipeline\nCombine TTS and transcription: generate spoken content with `tts`, process audio with `transcribe`. Both are private inference.\n\n### ? Video Workflow\n1. Generate or find a base image\n2. Use `--quote` to estimate video cost\n3. Generate with appropriate duration\u002Fmodel\n4. Videos take 1-5 minutes depending on settings\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| `VENICE_API_KEY not set` | Set env var or configure in `~\u002F.clawdbot\u002Fclawdbot.json` |\n| `Invalid API key` | Verify at [venice.ai\u002Fsettings\u002Fapi](https:\u002F\u002Fvenice.ai\u002Fsettings\u002Fapi) |\n| `Model not found` | Run `--list-models` to see available; use `--no-validate` for new models |\n| Rate limited | Check `--show-usage` output |\n| Video stuck | Videos can take 1-5 min; use `--timeout 600` for long ones |\n\n## Resources\n\n- **API Docs**: [docs.venice.ai](https:\u002F\u002Fdocs.venice.ai)\n- **Status**: [veniceai-status.com](https:\u002F\u002Fveniceai-status.com)\n- **Discord**: [discord.gg\u002Faskvenice](https:\u002F\u002Fdiscord.gg\u002Faskvenice)\n",{"name":5,"homepage":54,"metadata":55,"description":7},"https:\u002F\u002Fvenice.ai",{"clawdbot":56},{"emoji":57,"notes":58,"install":59,"requires":65,"primaryEnv":67},"?️","Full Venice AI platform — text, images, video, audio, embeddings. One skill for everything.",[60],{"id":61,"bins":62,"kind":37,"label":63,"formula":64},"python-brew",[30],"Install Python (brew)","python",{"env":66,"bins":68},[67],"VENICE_API_KEY",[30],"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fjonisjongithub\u002Fvenice-ai",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":77,"prompt":87,"zipAvailable":88},[78,81,84],{"tool":79,"command":80},"npx","npx skills add kbarbel640-del\u002Fskills --skill venice-ai",{"tool":82,"command":83},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill venice-ai",{"tool":85,"command":86},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill venice-ai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002FSKILL.md",true,[90,96,100,106,110,114,118,122],{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"_meta.json","REFERENCE","参考文档",632,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002F_meta.json",{"path":97,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fapi.md",7106,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Freferences\u002Fapi.md",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fvenice_common.py","SCRIPT","脚本",7463,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice_common.py",{"path":107,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fvenice-edit.py",6527,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice-edit.py",{"path":111,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fvenice-image.py",14862,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice-image.py",{"path":115,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Fvenice-upscale.py",9651,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice-upscale.py",{"path":119,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fvenice-video.py",16858,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice-video.py",{"path":123,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fvenice.py",22146,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjonisjongithub\u002Fvenice-ai\u002Fscripts\u002Fvenice.py",[127,156,181,202,208,228],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":138,"publishedAt":49},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[139,140,44,141,142,143,144,145,146,147,40,148,149,150,151,152,153,154,155],"crowd prompting","prompting","with","tokens","domain","world","prompts","operations","instructions","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":49},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[162],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[164,44,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,145,180],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":190,"publishedAt":49},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[187],{"categoryNo":188,"categoryName":189,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[191,192,193,194,195,196,197,141,198,178,180,199,44,200,201],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":203,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":49},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[206],{"categoryNo":188,"categoryName":189,"taxonomyType":20,"taxonomyTypeDesc":21},[194,193,192,191,201,196,197,141,195,178,180,198,199,44,200],{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":214,"publishedAt":49},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[215,216,217,218,219,220,221,222,223,224,225,226,227],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":238,"publishedAt":49},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[234,235],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":236,"categoryName":237,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000037","律师与法务",[239,240,241,242,141,243,244,69,245,199,246,247,248,249,250,153,251,252,253],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]