{"id":"4c568d5c-93e6-441f-bced-605c5d9a6112","entityType":"agent","slug":"clawhub-ravenquasar-vision-helper","name":"Vision Helper — AI Image Analysis","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ravenquasar-vision-helper","canonicalPath":"/agent/clawhub-ravenquasar-vision-helper","generatedAt":"2026-10-10T07:42:10.474Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T04:07:40.839Z","emptyReason":null},"description":"Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Skill: Vision Helper — AI Image Analysis Owner: ravenquasar Summary: Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T10:40:07.276Z | auto - Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama. - Supports analyzing imag","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.7K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17drtcv3zq9axeqrjg3fh8e6d85pc2h:vision-helper","sourceUrl":"https://clawhub.ai/ravenquasar/vision-helper","homepage":"https://clawhub.ai/ravenquasar/skills/vision-helper","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/ravenquasar/vision-helper","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/ravenquasar/skills/vision-helper","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":65,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Skill: Vision Help"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T04:07:40.839Z","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":"2026-10-10T04:07:40.839Z","emptyReason":null},"stars":null,"forks":null,"downloads":1702,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"1.7K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T04:07:40.839Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T04:07:40.839Z","lastCrawledAt":"2026-10-10T04:07:40.839Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T04:07:40.839Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-04-28T10:40:07.276Z","changelog":"- Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama. - Supports analyzing images, UI elements, screenshots, and performing OCR with extended timeout for cloud models (up to 180 seconds). - Bypasses built-in image tool limitations, including path restrictions and short timeouts. - Provides CLI and conversational usage examples, including workflows for browser, desktop, and game UI screenshots. - Allows easy switching between multiple supported local and cloud vision models via environment variables. - Supports various image formats and directory paths for flexible screenshot handling.","fileCount":5,"zipByteSize":5940}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17drtcv3zq9axeqrjg3fh8e6d85pc2h:vision-helper","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-ravenquasar-vision-helper/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T07:42:10.473Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ravenquasar-vision-helper/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":"2026-10-10T04:07:40.839Z","emptyReason":null},"readme":"Skill: Vision Helper — AI Image Analysis\n\nOwner: ravenquasar\n\nSummary: Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support.\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-04-28T10:40:07.276Z | auto\n\n- Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama.\n- Supports analyzing images, UI elements, screenshots, and performing OCR with extended timeout for cloud models (up to 180 seconds).\n- Bypasses built-in image tool limitations, including path restrictions and short timeouts.\n- Provides CLI and conversational usage examples, including workflows for browser, desktop, and game UI screenshots.\n- Allows easy switching between multiple supported local and cloud vision models via environment variables.\n- Supports various image formats and directory paths for flexible screenshot handling.\n\nArchive index:\n\nArchive v1.0.0: 5 files, 5940 bytes\n\nFiles: clawhub.json (512b), scripts/analyze_image.py (4696b), skill-card.md (2055b), SKILL.md (4485b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: vision-helper\ndescription: Analyze images using local or cloud vision models via Ollama. Use when you need to identify screenshots, analyze UI elements, read image content, or perform OCR. Triggers on: \"analyze image\", \"screenshot\", \"what's in this image\", \"OCR\", \"识图\", \"看图\", \"截图识别\".\n---\n\n# 📸 Vision Helper — Image Analysis\n\nAnalyze images using vision models via Ollama, with extended timeout support for cloud-based models.\n\n## Why Not Use the Built-in `image` Tool?\n\nThe built-in `image` tool has limited timeout settings that cause failures with cloud vision models (which often need 40–120 seconds). This skill calls the Ollama API directly with a 180-second timeout, supporting both local and cloud models reliably.\n\nIt also bypasses the built-in tool's file path restrictions, allowing analysis of images from any readable directory.\n\n## Usage\n\n### Basic\n\n```bash\n# Analyze an image (default: English description)\npython3 <skill-dir>/scripts/analyze_image.py <image_path>\n\n# With a custom prompt\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Is this a chess game? Describe the board state\"\n\n# With a specific model\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Describe content\" kimi-k2.5:cloud\n```\n\n> `<skill-dir>` resolves to your OpenClaw skill installation directory, typically `~/.openclaw/workspace/skills/vision-helper/`.\n\n### In Conversation\n\nWhen you need to analyze an image, use the `exec` tool:\n\n```\nexec: python3 <skill-dir>/scripts/analyze_image.py /path/to/image.png \"What do you see?\"\n```\n\n**Important:** Set exec timeout to 120–180 seconds, as cloud vision models are slow.\n\n### Screenshot + Analysis Workflow\n\n#### Option A: Browser screenshot → analyze\n\n```\n1. browser(action=\"screenshot\") → get screenshot path (MEDIA: xxx)\n2. exec(\"<skill-dir>/scripts/analyze_image.py <screenshot_path> 'Describe this UI'\")\n3. Act on the analysis result\n```\n\n#### Option B: Desktop screenshot → analyze\n\n**macOS:**\n```\n1. exec(\"screencapture -x /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")\n```\n\n**Linux:**\n```\n1. exec(\"gnome-screenshot -f /tmp/screen.png\")\n   — or —\n   exec(\"import /tmp/screen.png\")  # ImageMagick\n   — or —\n   exec(\"scrot /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")\n```\n\n#### Option C: Game/App UI → analyze → act\n\n```\n1. Screenshot the current screen\n2. Use vision-helper to identify UI elements, buttons, text\n3. Execute clicks/input based on the analysis\n```\n\n## Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `VISION_MODEL` | `gemma4:31b` | Default vision model |\n| `VISION_TIMEOUT` | `180` | Request timeout in seconds |\n| `OLLAMA_API_URL` | `http://localhost:11434/api/chat` | Ollama API endpoint |\n\n## Supported Models\n\n| Model | Vision | Speed | Recommendation |\n|-------|--------|-------|----------------|\n| `gemma4:31b` | ✅ | Local, fast | ⭐ **Primary** (privacy, no API needed) |\n| `kimi-k2.6:cloud` | ✅ | 40–120s | 🔬 Advanced (high quality, cloud) |\n| `kimi-k2.5:cloud` | ✅ | 40–90s | Alternative cloud option |\n| `qwen3.5:cloud` | ✅ | 30–60s | Fast cloud recognition |\n| `qwen3.5:397b-cloud` | ✅ | 40–90s | High quality cloud |\n| `gemma4:31b` | ✅ | Local, fast | Privacy-first (runs offline) |\n\nNote: Cloud models require the model to be available in your Ollama instance. Use `VISION_MODEL` env var to switch.\n\n## FAQ\n\n### Q: Can I use the built-in `image` tool instead?\nA: It works for local models but will time out on cloud vision models. Always prefer this skill's script for reliable results.\n\n### Q: What image formats are supported?\nA: PNG, JPG, JPEG, GIF, WebP, BMP, TIFF, SVG. Maximum file size: 20 MB.\n\n### Q: Where should I save screenshots?\nA: Any readable directory works — `/tmp/`, your workspace, etc. This script has no path restrictions.\n\n### Q: How do I use a Chinese prompt?\nA: Pass it as the second argument: `python3 <skill-dir>/scripts/analyze_image.py /tmp/img.png \"请描述这张图片的内容\"`\n\n## Automation Ideas\n\n- **Game automation**: Screenshot → analyze game state → decide next action\n- **Browser verification**: Screenshot → verify page loaded correctly\n- **Desktop monitoring**: Periodic screenshots → detect changes\n- **UI testing**: Screenshot → verify rendered output\n- **OCR**: Extract text content from images\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7805nw545a1g4024y6fyxy7185q82f\",\n  \"slug\": \"vision-helper\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1777372807276\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:\n\nAnalyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ravenquasar](https://clawhub.ai/user/ravenquasar)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to analyze local images or screenshots, inspect UI content, and perform OCR with an Ollama vision model when longer model timeouts are needed.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can read local images and screenshots from broad filesystem locations, which may expose credentials, private documents, or sensitive desktop content.\n\nMitigation: Use it only on images intended for analysis, prefer workspace or temporary paths, and avoid screenshots containing secrets or private documents.\n\nRisk: Image data can be sent to a configurable Ollama endpoint, including cloud or remote models.\n\nMitigation: Keep OLLAMA_API_URL on localhost for routine use, and configure a remote endpoint only when that service is explicitly trusted for the image contents.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ravenquasar/skills/vision-helper)\n\n## Skill Output:\n\n**Output Type(s):** [text, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text image analysis from the configured vision model; usage guidance includes shell commands and environment variables.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Accepts an image path, optional prompt, optional model name, and environment configuration for model, timeout, and Ollama API URL.]\n\n## Skill Version(s):\n\n1.0.0 (source: server release metadata and clawhub.json)\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 v1.0.0:clawhub.json\n\n{\n  \"name\": \"vision-helper\",\n  \"displayName\": \"Vision Helper — AI Image Analysis\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Analyze images using local or cloud vision models via Ollama. Bypasses built-in image tool timeout limits with extended 180s timeout, file validation, and cross-platform screenshot support.\",\n  \"author\": \"Frieren\",\n  \"license\": \"MIT\",\n  \"pricing\": {\n    \"model\": \"free\"\n  },\n  \"tags\": [\"vision\", \"image\", \"ocr\", \"screenshot\", \"ollama\", \"gemma\", \"kimi\"],\n  \"minOpenClawVersion\": \"1.2.0\"\n}","readmeExcerpt":"Skill: Vision Helper — AI Image Analysis Owner: ravenquasar Summary: Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T10:40:07.276Z | auto - Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama. - Supports analyzing imag","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Analyze an image (default: English description)\npython3 <skill-dir>/scripts/analyze_image.py <image_path>\n\n# With a custom prompt\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Is this a chess game? Describe the board state\"\n\n# With a specific model\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Describe content\" kimi-k2.5:cloud"},{"language":"text","snippet":"exec: python3 <skill-dir>/scripts/analyze_image.py /path/to/image.png \"What do you see?\""},{"language":"text","snippet":"1. browser(action=\"screenshot\") → get screenshot path (MEDIA: xxx)\n2. exec(\"<skill-dir>/scripts/analyze_image.py <screenshot_path> 'Describe this UI'\")\n3. Act on the analysis result"},{"language":"text","snippet":"1. exec(\"screencapture -x /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")"},{"language":"text","snippet":"1. exec(\"gnome-screenshot -f /tmp/screen.png\")\n   — or —\n   exec(\"import /tmp/screen.png\")  # ImageMagick\n   — or —\n   exec(\"scrot /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")"},{"language":"text","snippet":"1. Screenshot the current screen\n2. Use vision-helper to identify UI elements, buttons, text\n3. Execute clicks/input based on the analysis"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: vision-helper\ndescription: Analyze images using local or cloud vision models via Ollama. Use when you need to identify screenshots, analyze UI elements, read image content, or perform OCR. Triggers on: \"analyze image\", \"screenshot\", \"what's in this image\", \"OCR\", \"识图\", \"看图\", \"截图识别\".\n---\n\n# 📸 Vision Helper — Image Analysis\n\nAnalyze images using vision models via Ollama, with extended timeout support for cloud-based models.\n\n## Why Not Use the Built-in `image` Tool?\n\nThe built-in `image` tool has limited timeout settings that cause failures with cloud vision models (which often need 40–120 seconds). This skill calls the Ollama API directly with a 180-second timeout, supporting both local and cloud models reliably.\n\nIt also bypasses the built-in tool's file path restrictions, allowing analysis of images from any readable directory.\n\n## Usage\n\n### Basic\n\n```bash\n# Analyze an image (default: English description)\npython3 <skill-dir>/scripts/analyze_image.py <image_path>\n\n# With a custom prompt\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Is this a chess game? Describe the board state\"\n\n# With a specific model\npython3 <skill-dir>/scripts/analyze_image.py <image_path> \"Describe content\" kimi-k2.5:cloud\n```\n\n> `<skill-dir>` resolves to your OpenClaw skill installation directory, typically `~/.openclaw/workspace/skills/vision-helper/`.\n\n### In Conversation\n\nWhen you need to analyze an image, use the `exec` tool:\n\n```\nexec: python3 <skill-dir>/scripts/analyze_image.py /path/to/image.png \"What do you see?\"\n```\n\n**Important:** Set exec timeout to 120–180 seconds, as cloud vision models are slow.\n\n### Screenshot + Analysis Workflow\n\n#### Option A: Browser screenshot → analyze\n\n```\n1. browser(action=\"screenshot\") → get screenshot path (MEDIA: xxx)\n2. exec(\"<skill-dir>/scripts/analyze_image.py <screenshot_path> 'Describe this UI'\")\n3. Act on the analysis result\n```\n\n#### Option B: Desktop screenshot → analyze\n\n**macOS:**\n```\n1. exec(\"screencapture -x /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")\n```\n\n**Linux:**\n```\n1. exec(\"gnome-screenshot -f /tmp/screen.png\")\n   — or —\n   exec(\"import /tmp/screen.png\")  # ImageMagick\n   — or —\n   exec(\"scrot /tmp/screen.png\")\n2. exec(\"<skill-dir>/scripts/analyze_image.py /tmp/screen.png 'Describe the desktop'\")\n```\n\n#### Option C: Game/App UI → analyze → act\n\n```\n1. Screenshot the current screen\n2. Use vision-helper to identify UI elements, buttons, text\n3. Execute clicks/input based on the analysis\n```\n\n## Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `VISION_MODEL` | `gemma4:31b` | Default vision model |\n| `VISION_TIMEOUT` | `180` | Request timeout in seconds |\n| `OLLAMA_API_URL` | `http://localhost:11434/api/chat` | Ollama API endpoint |\n\n## Supported Models\n\n| Model | Vision | Speed | Recommendation |\n|-------|--------|-------|----------------|\n| `gemma4:31b` | ✅ | Local, fast | ⭐ **Prima"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7805nw545a1g4024y6fyxy7185q82f\",\n  \"slug\": \"vision-helper\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1777372807276\n}"},{"path":"skill-card.md","content":"## Description:\n\nAnalyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ravenquasar](https://clawhub.ai/user/ravenquasar)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to analyze local images or screenshots, inspect UI content, and perform OCR with an Ollama vision model when longer model timeouts are needed.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can read local images and screenshots from broad filesystem locations, which may expose credentials, private documents, or sensitive desktop content.\n\nMitigation: Use it only on images intended for analysis, prefer workspace or temporary paths, and avoid screenshots containing secrets or private documents.\n\nRisk: Image data can be sent to a configurable Ollama endpoint, including cloud or remote models.\n\nMitigation: Keep OLLAMA_API_URL on localhost for routine use, and configure a remote endpoint only when that service is explicitly trusted for the image contents.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ravenquasar/skills/vision-helper)\n\n## Skill Output:\n\n**Output Type(s):** [text, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text image analysis from the configured vision model; usage guidance includes shell commands and environment variables.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Accepts an image path, optional prompt, optional model name, and environment configuration for model, timeout, and Ollama API URL.]\n\n## Skill Version(s):\n\n1.0.0 (source: server release metadata and clawhub.json)\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":"clawhub.json","content":"{\n  \"name\": \"vision-helper\",\n  \"displayName\": \"Vision Helper — AI Image Analysis\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Analyze images using local or cloud vision models via Ollama. Bypasses built-in image tool timeout limits with extended 180s timeout, file validation, and cross-platform screenshot support.\",\n  \"author\": \"Frieren\",\n  \"license\": \"MIT\",\n  \"pricing\": {\n    \"model\": \"free\"\n  },\n  \"tags\": [\"vision\", \"image\", \"ocr\", \"screenshot\", \"ollama\", \"gemma\", \"kimi\"],\n  \"minOpenClawVersion\": \"1.2.0\"\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Skill: Vision Helper — AI Image Analysis Owner: ravenquasar Summary: Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T10:40:07.276Z | auto - Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama. - Supports analyzing imag","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1068,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T04:07:40.839Z","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":"2026-10-10T04:07:40.839Z","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":"2026-10-10T07:42:10.474Z","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"}]}}}