{"id":"afa3a6c7-d290-4817-9232-5037f741dfb1","entityType":"agent","slug":"clawhub-guorui999-vision-2","name":"Vision","canonicalUrl":"https://www.xpersona.co/agent/clawhub-guorui999-vision-2","canonicalPath":"/agent/clawhub-guorui999-vision-2","generatedAt":"2026-10-15T03:22:01.889Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T21:43:28.903Z","emptyReason":null},"description":"让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中... Skill: Vision Owner: guorui999 Summary: 让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中... Tags: latest:0.1.0 Version history: v0.1.0 | 2026-06-09T07:50:59.006Z | auto vision-2 0.1.0 初始发布 - 为无原生视觉能力的模型（如 DeepSeek）提供自动识图功能，支持图片内容分析、描述与对比。 - 自动识别图片来源（本地/网络），支持多图模式。 - 集成多种视觉服务（含阿里云百炼、OpenAI 及兼容模型），支持 jpg/png/gif","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 989 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s173sx6fj1e86s4wqz5pd8ayqh88a110:vision-2","sourceUrl":"https://clawhub.ai/guorui999/vision-2","homepage":"https://clawhub.ai/guorui999/skills/vision-2","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/guorui999/vision-2","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/guorui999/skills/vision-2","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:43:28.903Z","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":"2026-10-11T21:43:28.903Z","emptyReason":null},"stars":null,"forks":null,"downloads":989,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"0.1.0","tractionLabel":"989 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:43:28.891Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T21:43:28.903Z","lastCrawledAt":"2026-10-11T21:43:28.891Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T21:43:28.891Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.0","createdAt":"2026-06-09T07:50:59.006Z","changelog":"vision-2 0.1.0 初始发布 - 为无原生视觉能力的模型（如 DeepSeek）提供自动识图功能，支持图片内容分析、描述与对比。 - 自动识别图片来源（本地/网络），支持多图模式。 - 集成多种视觉服务（含阿里云百炼、OpenAI 及兼容模型），支持 jpg/png/gif/webp/bmp 等主流格式。 - 命令行配置简单，首次使用引导设置。 - 详细文档覆盖触发场景、不适用场景及 API 配置说明。","fileCount":9,"zipByteSize":9456}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s173sx6fj1e86s4wqz5pd8ayqh88a110:vision-2","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-guorui999-vision-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-15T03:22:01.889Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guorui999-vision-2/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":"2026-10-11T21:43:28.903Z","emptyReason":null},"readme":"Skill: Vision\n\nOwner: guorui999\n\nSummary: 让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中...\n\nTags: latest:0.1.0\n\nVersion history:\n\nv0.1.0 | 2026-06-09T07:50:59.006Z | auto\n\nvision-2 0.1.0 初始发布\n\n- 为无原生视觉能力的模型（如 DeepSeek）提供自动识图功能，支持图片内容分析、描述与对比。\n- 自动识别图片来源（本地/网络），支持多图模式。\n- 集成多种视觉服务（含阿里云百炼、OpenAI 及兼容模型），支持 jpg/png/gif/webp/bmp 等主流格式。\n- 命令行配置简单，首次使用引导设置。\n- 详细文档覆盖触发场景、不适用场景及 API 配置说明。\n\nArchive index:\n\nArchive v0.1.0: 9 files, 9456 bytes\n\nFiles: config.json (118b), evals/evals.json (984b), evals/trigger_eval.json (2013b), install.sh (1206b), README.md (543b), scripts/vision.js (10013b), skill-card.md (2540b), SKILL.md (2609b), _meta.json (127b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: vision\ndescription: |\n  让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。\n  触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中的文字/内容时。\n  多图支持：当用户一次发送多张图片或要求比较/对比图片时，使用多图模式。\n  不触发场景：用户只是讨论图片处理技术、询问图片格式、要求生成图片、或编写图片处理代码时，不要使用此 skill。\n---\n\n# Vision Skill\n\n让没有原生识图能力的模型（如 DeepSeek）也能\"看图\"——通过调用外部视觉 API 获取图片的文字描述。\n\n## 快速配置\n\n```bash\nnode scripts/vision.js --setup\n```\n\n按提示输入 API Key、API 地址、模型名称。\n\n### 查看当前配置\n\n```bash\nnode scripts/vision.js --config\n```\n\n## 使用方法\n\n### 自动触发（推荐）\n\n当用户发送图片或要求分析图片时，自动调用：\n\n```bash\nnode scripts/vision.js \"<图片路径>\" \"用中文描述这张图片\"\n```\n\n### 单张图片\n\n```bash\n# 本地图片\nnode scripts/vision.js /path/to/image.jpg \"描述图片内容\"\n\n# 网络图片\nnode scripts/vision.js --url https://example.com/image.png \"这是什么？\"\n```\n\n### 多张图片\n\n```bash\n# 多张本地图片\nnode scripts/vision.js image1.jpg image2.jpg image3.jpg \"比较这些图片的异同\"\n\n# 混合本地和网络图片\nnode scripts/vision.js local.jpg --url https://example.com/online.png \"这两张图有什么关系？\"\n```\n\n## 支持的图片格式\n\njpg, jpeg, png, gif, webp, bmp\n\n## 支持的视觉服务\n\n| 服务 | 模型 | 备注 |\n|------|------|------|\n| **阿里云百炼（推荐）** | `qwen3.5-omni-plus` | 新用户 100 万 token 免费 |\n| 阿里云百炼 | `qwen-vl-max` | 同上 |\n| OpenAI | `gpt-4o-mini` | 需海外支付 |\n| 其他 | 任何 OpenAI 兼容格式 | 改 `BASE_URL` 和模型名即可 |\n\n## 配置文件说明\n\n配置文件：`~/.claude/skills/vision/config.json`\n\n```json\n{\n  \"base_url\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n  \"api_key\": \"你的API Key\",\n  \"model\": \"qwen3.5-omni-plus\"\n}\n```\n\n## 工作原理\n\n1. 读取图片文件 → 转换为 base64\n2. 调用视觉 API（OpenAI 兼容格式）\n3. 返回文字描述\n\n## 注意事项\n\n- 需要 Node.js 环境\n- 首次使用需配置 API Key\n- 网络图片需要能访问对应 URL\n\nFile v0.1.0:README.md\n\n# Vision Skill\n\n让没有原生识图能力的 Claude Code 模型也能\"看图\"。\n\n## 一键安装\n\n```bash\nnpx skills add guorui999/vision\n```\n\n## 配置\n\n```bash\nnode ~/.claude/skills/vision/scripts/vision.js --setup\n```\n\n按提示输入 API Key、API 地址、模型名称。\n\n或直接编辑配置文件：`~/.claude/skills/vision/config.json`\n\n## 使用\n\n配置完成后，直接发送图片或说\"看这张图\"即可自动识别。\n\n## 文档\n\n- [SKILL.md](SKILL.md) - 完整使用说明\n- [install.sh](install.sh) - 一键安装脚本\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7dc4ex4jy1gw1sj6g538xqrh88bh84\",\n  \"slug\": \"vision-2\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1780991459006\n}\n\nFile v0.1.0:skill-card.md\n\n## Description:\n\nVision lets agents without native vision support analyze, describe, compare, and extract text from local or remote images through a configured OpenAI-compatible vision API.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[guorui999](https://clawhub.ai/user/guorui999)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to add image understanding workflows to agents that otherwise cannot inspect images, including screenshot analysis, OCR-style text extraction, image description, and multi-image comparison.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Image content, OCR text, screenshots, prompts, and API credentials may be sent to the configured external vision provider.\n\nMitigation: Use only approved providers and HTTPS endpoints, avoid submitting sensitive images unless permitted, and review provider data-handling terms before deployment.\n\nRisk: The installer supports remote URL downloads and the documented install path includes command-line installation flows that may introduce supply-chain risk.\n\nMitigation: Install from a pinned, reviewed release or local artifact rather than remote curl-pipe-to-bash flows, and verify file hashes before deployment.\n\nRisk: The API key can be stored in a plaintext config file.\n\nMitigation: Prefer environment-based secret handling where available or restrict config file permissions when local storage is required.\n\n## Reference(s):\n\n- [Server-resolved GitHub repository](https://github.com/guorui999/vision)\n- [ClawHub skill page](https://clawhub.ai/guorui999/skills/vision-2)\n- [Aliyun Bailian console](https://bailian.console.aliyun.com/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text or Markdown returned from the configured vision model, with setup and usage guidance expressed as shell commands and configuration values.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports local image files and remote image URLs; sends image content and prompts to the configured vision provider and requests up to 1024 output tokens.]\n\n## Skill Version(s):\n\n0.1.0 (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\nFile v0.1.0:config.json\n\n{\n  \"base_url\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n  \"api_key\": \"\",\n  \"model\": \"qwen3.5-omni-plus\"\n}\n\nFile v0.1.0:evals/evals.json\n\n{\n  \"skill_name\": \"vision\",\n  \"evals\": [\n    {\n      \"id\": 1,\n      \"prompt\": \"帮我看看这张图片是什么内容：/tmp/test.jpg\",\n      \"expected_output\": \"AI 应该调用 vision.js 识别图片并返回文字描述\",\n      \"files\": []\n    },\n    {\n      \"id\": 2,\n      \"prompt\": \"我发了一张图片，帮我分析一下里面的文字\",\n      \"expected_output\": \"AI 应该识别图片中的文字内容\",\n      \"files\": []\n    },\n    {\n      \"id\": 3,\n      \"prompt\": \"看看这个截图有什么问题：https://example.com/screenshot.png\",\n      \"expected_output\": \"AI 应该下载并识别网络图片\",\n      \"files\": []\n    },\n    {\n      \"id\": 4,\n      \"prompt\": \"描述一下这张照片的场景\",\n      \"expected_output\": \"AI 应该描述照片中的场景和元素\",\n      \"files\": []\n    },\n    {\n      \"id\": 5,\n      \"prompt\": \"这张图片里有几个人？\",\n      \"expected_output\": \"AI 应该识图并回答图片中的人数\",\n      \"files\": []\n    }\n  ]\n}\n\nFile v0.1.0:evals/trigger_eval.json\n\n[\n  {\n    \"query\": \"帮我看看这个截图里的报错是什么意思：/tmp/error-screenshot.png\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"我发了两张产品设计图，帮我对比一下哪个更好看\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"看看这张照片里的文字，我需要提取出来\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"分析一下这张数据可视化的图表，趋势怎么样\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"我上传了几张图片，帮我描述一下每张的内容\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"这个 logo 设计怎么样？有什么可以改进的地方\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"帮我识别一下这张身份证上的信息\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"看看这个 UI 界面有什么问题\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"我拍了张菜单的照片，帮我翻译一下\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"这两张图片有什么区别？我找不同\",\n    \"should_trigger\": true\n  },\n  {\n    \"query\": \"帮我写一个 Python 脚本处理图片\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"怎么用 PIL 库调整图片大小\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"介绍一下计算机视觉的发展历史\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"帮我生成一张猫咪的图片\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"这个图片格式怎么转换成 PDF\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"解释一下 JPEG 和 PNG 的区别\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"帮我设计一个图片处理的算法\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"这个 CSS 样式怎么让图片居中\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"怎么用 ffmpeg 从视频里截取图片\",\n    \"should_trigger\": false\n  },\n  {\n    \"query\": \"帮我优化一下这个图片的加载速度\",\n    \"should_trigger\": false\n  }\n]","readmeExcerpt":"Skill: Vision Owner: guorui999 Summary: 让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中... Tags: latest:0.1.0 Version history: v0.1.0 | 2026-06-09T07:50:59.006Z | auto vision-2 0.1.0 初始发布 - 为无原生视觉能力的模型（如 DeepSeek）提供自动识图功能，支持图片内容分析、描述与对比。 - 自动识别图片来源（本地/网络），支持多图模式。 - 集成多种视觉服务（含阿里云百炼、OpenAI 及兼容模型），支持 jpg/png/gif","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"node scripts/vision.js --setup"},{"language":"bash","snippet":"node scripts/vision.js --config"},{"language":"bash","snippet":"node scripts/vision.js \"<图片路径>\" \"用中文描述这张图片\""},{"language":"bash","snippet":"# 本地图片\nnode scripts/vision.js /path/to/image.jpg \"描述图片内容\"\n\n# 网络图片\nnode scripts/vision.js --url https://example.com/image.png \"这是什么？\""},{"language":"bash","snippet":"# 多张本地图片\nnode scripts/vision.js image1.jpg image2.jpg image3.jpg \"比较这些图片的异同\"\n\n# 混合本地和网络图片\nnode scripts/vision.js local.jpg --url https://example.com/online.png \"这两张图有什么关系？\""},{"language":"json","snippet":"{\n  \"base_url\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n  \"api_key\": \"你的API Key\",\n  \"model\": \"qwen3.5-omni-plus\"\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: vision\ndescription: |\n  让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。\n  触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中的文字/内容时。\n  多图支持：当用户一次发送多张图片或要求比较/对比图片时，使用多图模式。\n  不触发场景：用户只是讨论图片处理技术、询问图片格式、要求生成图片、或编写图片处理代码时，不要使用此 skill。\n---\n\n# Vision Skill\n\n让没有原生识图能力的模型（如 DeepSeek）也能\"看图\"——通过调用外部视觉 API 获取图片的文字描述。\n\n## 快速配置\n\n```bash\nnode scripts/vision.js --setup\n```\n\n按提示输入 API Key、API 地址、模型名称。\n\n### 查看当前配置\n\n```bash\nnode scripts/vision.js --config\n```\n\n## 使用方法\n\n### 自动触发（推荐）\n\n当用户发送图片或要求分析图片时，自动调用：\n\n```bash\nnode scripts/vision.js \"<图片路径>\" \"用中文描述这张图片\"\n```\n\n### 单张图片\n\n```bash\n# 本地图片\nnode scripts/vision.js /path/to/image.jpg \"描述图片内容\"\n\n# 网络图片\nnode scripts/vision.js --url https://example.com/image.png \"这是什么？\"\n```\n\n### 多张图片\n\n```bash\n# 多张本地图片\nnode scripts/vision.js image1.jpg image2.jpg image3.jpg \"比较这些图片的异同\"\n\n# 混合本地和网络图片\nnode scripts/vision.js local.jpg --url https://example.com/online.png \"这两张图有什么关系？\"\n```\n\n## 支持的图片格式\n\njpg, jpeg, png, gif, webp, bmp\n\n## 支持的视觉服务\n\n| 服务 | 模型 | 备注 |\n|------|------|------|\n| **阿里云百炼（推荐）** | `qwen3.5-omni-plus` | 新用户 100 万 token 免费 |\n| 阿里云百炼 | `qwen-vl-max` | 同上 |\n| OpenAI | `gpt-4o-mini` | 需海外支付 |\n| 其他 | 任何 OpenAI 兼容格式 | 改 `BASE_URL` 和模型名即可 |\n\n## 配置文件说明\n\n配置文件：`~/.claude/skills/vision/config.json`\n\n```json\n{\n  \"base_url\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n  \"api_key\": \"你的API Key\",\n  \"model\": \"qwen3.5-omni-plus\"\n}\n```\n\n## 工作原理\n\n1. 读取图片文件 → 转换为 base64\n2. 调用视觉 API（OpenAI 兼容格式）\n3. 返回文字描述\n\n## 注意事项\n\n- 需要 Node.js 环境\n- 首次使用需配置 API Key\n- 网络图片需要能访问对应 URL"},{"path":"README.md","content":"# Vision Skill\n\n让没有原生识图能力的 Claude Code 模型也能\"看图\"。\n\n## 一键安装\n\n```bash\nnpx skills add guorui999/vision\n```\n\n## 配置\n\n```bash\nnode ~/.claude/skills/vision/scripts/vision.js --setup\n```\n\n按提示输入 API Key、API 地址、模型名称。\n\n或直接编辑配置文件：`~/.claude/skills/vision/config.json`\n\n## 使用\n\n配置完成后，直接发送图片或说\"看这张图\"即可自动识别。\n\n## 文档\n\n- [SKILL.md](SKILL.md) - 完整使用说明\n- [install.sh](install.sh) - 一键安装脚本"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7dc4ex4jy1gw1sj6g538xqrh88bh84\",\n  \"slug\": \"vision-2\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1780991459006\n}"},{"path":"skill-card.md","content":"## Description:\n\nVision lets agents without native vision support analyze, describe, compare, and extract text from local or remote images through a configured OpenAI-compatible vision API.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[guorui999](https://clawhub.ai/user/guorui999)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to add image understanding workflows to agents that otherwise cannot inspect images, including screenshot analysis, OCR-style text extraction, image description, and multi-image comparison.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Image content, OCR text, screenshots, prompts, and API credentials may be sent to the configured external vision provider.\n\nMitigation: Use only approved providers and HTTPS endpoints, avoid submitting sensitive images unless permitted, and review provider data-handling terms before deployment.\n\nRisk: The installer supports remote URL downloads and the documented install path includes command-line installation flows that may introduce supply-chain risk.\n\nMitigation: Install from a pinned, reviewed release or local artifact rather than remote curl-pipe-to-bash flows, and verify file hashes before deployment.\n\nRisk: The API key can be stored in a plaintext config file.\n\nMitigation: Prefer environment-based secret handling where available or restrict config file permissions when local storage is required.\n\n## Reference(s):\n\n- [Server-resolved GitHub repository](https://github.com/guorui999/vision)\n- [ClawHub skill page](https://clawhub.ai/guorui999/skills/vision-2)\n- [Aliyun Bailian console](https://bailian.console.aliyun.com/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text or Markdown returned from the configured vision model, with setup and usage guidance expressed as shell commands and configuration values.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports local image files and remote image URLs; sends image content and prompts to the configured vision provider and requests up to 1024 output tokens.]\n\n## Skill Version(s):\n\n0.1.0 (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."},{"path":"config.json","content":"{\n  \"base_url\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n  \"api_key\": \"\",\n  \"model\": \"qwen3.5-omni-plus\"\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中... Skill: Vision Owner: guorui999 Summary: 让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说\"看这张图\"、\"帮我识别这个图片\"、\"描述一下这张图\"、\"分析这个截图\"、\"比较这些图片\"、发送图片文件路径、消息中出现图片附件、或要求识别图片中... Tags: latest:0.1.0 Version history: v0.1.0 | 2026-06-09T07:50:59.006Z | auto vision-2 0.1.0 初始发布 - 为无原生视觉能力的模型（如 DeepSeek）提供自动识图功能，支持图片内容分析、描述与对比。 - 自动识别图片来源（本地/网络），支持多图模式。 - 集成多种视觉服务（含阿里云百炼、OpenAI 及兼容模型），支持 jpg/png/gif","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":732,"uniquenessScore":63,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:43:28.903Z","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":"2026-10-11T21:43:28.903Z","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":"2026-10-15T03:22:01.889Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}