[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76Z5TRDFND1W1PBAWGA5HS5":3,"skill-same:01M76Z5TRDFND1W1PBAWGA5HS5":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":56},"01M76Z5TRDFND1W1PBAWGA5HS5","facticity-ai",null,"Complete Facticity.AI integration - fact-check claims, extract claims from content, transcribe links, check link reliability, check credits, and monitor task status","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshahruj\u002Ffacticity-ai\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\r\nname: facticity-ai\r\ndescription: Complete Facticity.AI integration - fact-check claims, extract claims from content, transcribe links, check link reliability, check credits, and monitor task status\r\nuser-invocable: true\r\ncommand-dispatch: tool\r\ncommand-tool: http.request\r\ncommand-arg-mode: raw\r\nmetadata:\r\n  {\r\n    \"openclaw\": {\r\n      \"emoji\": \"🔍\",\r\n      \"homepage\": \"https:\u002F\u002Fapp.facticity.ai\",\r\n      \"requires\": {\r\n        \"env\": [\"FACTICITY_API_KEY\"]\r\n      },\r\n      \"primaryEnv\": \"FACTICITY_API_KEY\"\r\n    }\r\n  }\r\n---\r\n\r\n# Facticity.AI Complete Integration\r\n\r\nA comprehensive skill for interacting with the Facticity.AI API. Supports fact-checking claims, extracting claims from text\u002Fvideo, transcribing links, checking link reliability using MediaBias data, checking API credits, and monitoring async task status.\r\n\r\n## API Base URL\r\n\r\n**Base URL:** `https:\u002F\u002Fapi.facticity.ai`\r\n\r\nAll API endpoints use this base URL. References to `{BASE_URL}`.\r\n\r\n## Behavior\r\n\r\n**First, check if `FACTICITY_API_KEY` is set and not empty. If it is missing or empty, return this onboarding message:**\r\n\r\n```\r\n⚠️ API Key Not Configured\r\n\r\nTo use this skill, you need to set up your Facticity.AI API key:\r\n\r\n1. Visit https:\u002F\u002Fapp.facticity.ai\u002Fapi to get your API key\r\n2. Set the key as an environment variable:\r\n   export FACTICITY_API_KEY=your_api_key_here\r\n   \r\n   Or add it to your OpenClaw config (~\u002F.openclaw\u002Fopenclaw.json):\r\n   {\r\n     \"skills\": {\r\n       \"entries\": {\r\n         \"facticity-ai\": {\r\n           \"enabled\": true,\r\n           \"apiKey\": \"your_api_key_here\"\r\n         }\r\n       }\r\n     }\r\n   }\r\n\r\n3. Restart OpenClaw after configuration\r\n\r\nGet your API key at: https:\u002F\u002Fapp.facticity.ai\u002Fapi\r\n```\r\n\r\n**If the API key is present, determine the operation based on the command and proceed:**\r\n\r\n### 1. Fact-Check (`\u002Ffact-check`)\r\n\r\nWhen the command starts with `\u002Ffact-check` or the input is a claim to fact-check:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Ffact-check`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"query\": \"\u003Craw command input (remove \u002Ffact-check prefix if present)>\",\r\n  \"timeout\": 60,\r\n  \"mode\": \"sync\"\r\n}\r\n```\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `Classification`: \"True\" or \"False\"\r\n- `overall_assessment`: Detailed assessment text\r\n- `evidence`: Array of evidence sources\r\n- `sources`: Detailed source assessments\r\n- `bias`: Bias metrics (if available)\r\n- `task_id`: Task ID for async tracking\r\n\r\n**Usage:**\r\n```\r\n\u002Ffact-check \"Vaccines contain microchips\"\r\n\u002Ffact-check \"The unemployment rate dropped in 2023\"\r\n```\r\n\r\n**Async Mode:** For long-running fact-checks, set `mode: \"async\"` in the request body. The API will return a `task_id` that can be checked with `\u002Fcheck-task-status`.\r\n\r\n### 2. Extract Claims (`\u002Fextract-claim`)\r\n\r\nWhen the command starts with `\u002Fextract-claim` or the input is a URL or text to extract claims from:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Fextract-claim`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"input\": \"\u003Craw command input (remove \u002Fextract-claim prefix if present)>\",\r\n  \"content_type\": \"text\",\r\n  \"timestamp\": false,\r\n  \"audio_transcript_enabled\": false,\r\n  \"language_code\": \"en\"\r\n}\r\n```\r\n\r\n**Note:** For video URLs (YouTube, TikTok, Instagram), the API will auto-detect and transcribe. If you need transcription explicitly enabled, set `audio_transcript_enabled: true` in the request body.\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Fextract-claim \"The Earth is flat and NASA is lying about it\"\r\n\u002Fextract-claim https:\u002F\u002Fyoutube.com\u002Fwatch?v=abc123\r\n\u002Fextract-claim https:\u002F\u002Ftiktok.com\u002F@user\u002Fvideo\u002F123\r\n\u002Fextract-claim https:\u002F\u002Finstagram.com\u002Fp\u002Fabc123\r\n```\r\n\r\n**Supported Content Types:**\r\n- **Text**: Direct text input\r\n- **Video URLs**: YouTube, TikTok, Instagram (auto-transcribes)\r\n- **Language**: Set `language_code` for non-English content (default: \"en\")\r\n\r\n**Response Format:**\r\n- `status`: \"ok\" on success\r\n- `transcript`: Transcribed content (for video URLs)\r\n- `title`: Video\u002Farticle title (if available)\r\n- `description`: Content description (if available)\r\n- `claims`: Array of extracted claim strings\r\n- `overall_assessment`: Summary of extraction\r\n\r\n### 3. Get Credits (`\u002Fget-credits`)\r\n\r\nWhen the command is `\u002Fget-credits` or user wants to check API credits:\r\n\r\n**Endpoint:** `GET {BASE_URL}\u002Fget-credits`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n\r\nNo request body required.\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `email`: User email associated with the API key\r\n- `api_key`: The API key (masked)\r\n- `credits_left`: Number of credits remaining\r\n- `duration_seconds`: Duration period (typically 3600 seconds)\r\n\r\n**Usage:**\r\n```\r\n\u002Fget-credits\r\n```\r\n\r\n**Response Format:**\r\n```json\r\n{\r\n  \"email\": \"user@example.com\",\r\n  \"api_key\": \"your_api_key_here\",\r\n  \"credits_left\": 1482,\r\n  \"duration_seconds\": 3600\r\n}\r\n```\r\n\r\n### 4. Check Task Status (`\u002Fcheck-task-status`)\r\n\r\nWhen the command starts with `\u002Fcheck-task-status` or the input is a task ID:\r\n\r\n**Endpoint:** `GET {BASE_URL}\u002Fcheck-task-status?task_id=\u003Ctask_id>`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n\r\nThe raw command input should be the task_id from a previous async fact-check request (remove `\u002Fcheck-task-status` prefix if present).\r\n\r\n**Query Parameter:**\r\n- `task_id`: The unique ID of the task to check (from the raw command input)\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Fcheck-task-status 1234567890abcdef\r\n```\r\n\r\nOr with the task_id from a previous async fact-check:\r\n```\r\n\u002Ffact-check \"Long claim...\" --mode async\r\n# Returns task_id: abc123\r\n\u002Fcheck-task-status abc123\r\n```\r\n\r\n**Response Format:**\r\n\r\nFor completed tasks:\r\n```json\r\n{\r\n  \"status\": \"Completed\",\r\n  \"input_query\": \"Original Input query\",\r\n  \"classification\": \"False\",\r\n  \"overall_assessment\": \"This claim is inaccurate.\",\r\n  \"evidence_sources\": [\"Source 1\", \"Source 2\"],\r\n  \"disambiguation\": \"Clarifies the context...\",\r\n  \"detailed_source_reports\": [\"Detailed source report 1\", \"Detailed source report 2\"],\r\n  \"task_id\": \"1234567...\",\r\n  \"bias_quality_metrics\": [\r\n    {\r\n      \"source\": \"https:\u002F\u002Fwww.politico.com\",\r\n      \"bias\": -5.238666666666666,\r\n      \"quality\": 46.45\r\n    }\r\n  ]\r\n}\r\n```\r\n\r\nFor in-progress tasks, returns current status and progress information.\r\n\r\n### 5. Transcribe Link (`\u002Ftranscribe-link`)\r\n\r\nWhen the command starts with `\u002Ftranscribe-link` or the input is a URL to transcribe:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Ftranscribe-link`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"url\": \"\u003Craw command input (remove \u002Ftranscribe-link prefix if present)>\"\r\n}\r\n```\r\n\r\nThe raw command input should be the URL to transcribe (remove `\u002Ftranscribe-link` prefix if present).\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Ftranscribe-link https:\u002F\u002Fyoutube.com\u002Fwatch?v=abc123\r\n\u002Ftranscribe-link https:\u002F\u002Ftiktok.com\u002F@user\u002Fvideo\u002F123\r\n\u002Ftranscribe-link https:\u002F\u002Finstagram.com\u002Fp\u002Fabc123\r\n```\r\n\r\n**Response Format:**\r\n- `status`: \"ok\" on success\r\n- `transcript`: Transcribed content from the link\r\n- `title`: Video\u002Farticle title (if available)\r\n- `description`: Content description (if available)\r\n- `duration`: Duration of the content (if available)\r\n\r\n### 6. Check Link Reliability (`\u002Flink-reliability\u002Fcheck`)\r\n\r\nWhen the command starts with `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` or the input is a URL to check for source reliability:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Flink-reliability\u002Fcheck`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"url\": \"\u003Craw command input (remove \u002Flink-reliability\u002Fcheck or \u002Fcheck-link-reliability prefix if present)>\"\r\n}\r\n```\r\n\r\nThe raw command input should be the URL to check (remove `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` prefix if present).\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `url`: The processed URL\r\n- `bias`: Bias score (-42 to +42)\r\n- `quality`: Quality score (0 to 64)\r\n- `bias_label`: Human-readable bias category\r\n- `quality_label`: Human-readable quality category\r\n- `found`: Whether the URL was found in MediaBias database\r\n\r\n**Usage:**\r\n```\r\n\u002Flink-reliability\u002Fcheck https:\u002F\u002Fwww.example.com\u002Farticle\r\n\u002Fcheck-link-reliability https:\u002F\u002Fwww.bbc.com\u002Fnews\r\n\u002Flink-reliability\u002Fcheck https:\u002F\u002Fwww.politico.com\u002Fstory\r\n```\r\n\r\n**Response Format:**\r\n```json\r\n{\r\n  \"url\": \"https:\u002F\u002Fwww.example.com\u002Farticle\",\r\n  \"bias\": -5.24,\r\n  \"quality\": 46.45,\r\n  \"bias_label\": \"Left-Center Bias\",\r\n  \"quality_label\": \"High Quality\",\r\n  \"found\": true\r\n}\r\n```\r\n\r\n**Note:** If the URL is not found in the MediaBias database, `found` will be `false` and bias\u002Fquality scores may be null or default values.\r\n\r\n## Command Routing\r\n\r\nDetermine which operation to perform based on the command prefix:\r\n- `\u002Ffact-check` or input looks like a claim → Fact-Check endpoint\r\n- `\u002Fextract-claim` or input is a URL → Extract Claims endpoint\r\n- `\u002Fget-credits` → Get Credits endpoint\r\n- `\u002Fcheck-task-status` or input is a task ID → Check Task Status endpoint\r\n- `\u002Ftranscribe-link` or input is a URL → Transcribe Link endpoint\r\n- `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` or input is a URL → Check Link Reliability endpoint\r\n\r\n## API Token Usage\r\n\r\n- **Fact-Check**: Each request consumes 1 API token\r\n- **Extract Claims**: Consumes 1 API token per 1 million characters processed\r\n- **Get Credits**: Free, does not consume tokens\r\n- **Check Task Status**: Free, does not consume tokens\r\n- **Transcribe Link**: Consumes 1 API token per transcription request\r\n- **Check Link Reliability**: Consumes 1 API token per request\r\n\r\nMonitor usage with `\u002Fget-credits`.\r\n\r\n## Configuration\r\n\r\nSet `FACTICITY_API_KEY` in your OpenClaw config under `skills.entries.facticity-ai.apiKey` or as an environment variable.\r\n\r\n**Example config:**\r\n```json\r\n{\r\n  \"skills\": {\r\n    \"entries\": {\r\n      \"facticity-ai\": {\r\n        \"enabled\": true,\r\n        \"apiKey\": \"YOUR_API_KEY_HERE\"\r\n      }\r\n    }\r\n  }\r\n}\r\n```\r\n\r\nOr set as environment variable:\r\n```bash\r\nexport FACTICITY_API_KEY=your_api_key_here\r\n```\r\n","# Facticity.AI Complete Integration\r\n\r\nA comprehensive skill for interacting with the Facticity.AI API. Supports fact-checking claims, extracting claims from text\u002Fvideo, transcribing links, checking link reliability using MediaBias data, checking API credits, and monitoring async task status.\r\n\r\n## API Base URL\r\n\r\n**Base URL:** `https:\u002F\u002Fapi.facticity.ai`\r\n\r\nAll API endpoints use this base URL. References to `{BASE_URL}`.\r\n\r\n## Behavior\r\n\r\n**First, check if `FACTICITY_API_KEY` is set and not empty. If it is missing or empty, return this onboarding message:**\r\n\r\n```\r\n⚠️ API Key Not Configured\r\n\r\nTo use this skill, you need to set up your Facticity.AI API key:\r\n\r\n1. Visit https:\u002F\u002Fapp.facticity.ai\u002Fapi to get your API key\r\n2. Set the key as an environment variable:\r\n   export FACTICITY_API_KEY=your_api_key_here\r\n   \r\n   Or add it to your OpenClaw config (~\u002F.openclaw\u002Fopenclaw.json):\r\n   {\r\n     \"skills\": {\r\n       \"entries\": {\r\n         \"facticity-ai\": {\r\n           \"enabled\": true,\r\n           \"apiKey\": \"your_api_key_here\"\r\n         }\r\n       }\r\n     }\r\n   }\r\n\r\n3. Restart OpenClaw after configuration\r\n\r\nGet your API key at: https:\u002F\u002Fapp.facticity.ai\u002Fapi\r\n```\r\n\r\n**If the API key is present, determine the operation based on the command and proceed:**\r\n\r\n### 1. Fact-Check (`\u002Ffact-check`)\r\n\r\nWhen the command starts with `\u002Ffact-check` or the input is a claim to fact-check:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Ffact-check`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"query\": \"\u003Craw command input (remove \u002Ffact-check prefix if present)>\",\r\n  \"timeout\": 60,\r\n  \"mode\": \"sync\"\r\n}\r\n```\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `Classification`: \"True\" or \"False\"\r\n- `overall_assessment`: Detailed assessment text\r\n- `evidence`: Array of evidence sources\r\n- `sources`: Detailed source assessments\r\n- `bias`: Bias metrics (if available)\r\n- `task_id`: Task ID for async tracking\r\n\r\n**Usage:**\r\n```\r\n\u002Ffact-check \"Vaccines contain microchips\"\r\n\u002Ffact-check \"The unemployment rate dropped in 2023\"\r\n```\r\n\r\n**Async Mode:** For long-running fact-checks, set `mode: \"async\"` in the request body. The API will return a `task_id` that can be checked with `\u002Fcheck-task-status`.\r\n\r\n### 2. Extract Claims (`\u002Fextract-claim`)\r\n\r\nWhen the command starts with `\u002Fextract-claim` or the input is a URL or text to extract claims from:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Fextract-claim`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"input\": \"\u003Craw command input (remove \u002Fextract-claim prefix if present)>\",\r\n  \"content_type\": \"text\",\r\n  \"timestamp\": false,\r\n  \"audio_transcript_enabled\": false,\r\n  \"language_code\": \"en\"\r\n}\r\n```\r\n\r\n**Note:** For video URLs (YouTube, TikTok, Instagram), the API will auto-detect and transcribe. If you need transcription explicitly enabled, set `audio_transcript_enabled: true` in the request body.\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Fextract-claim \"The Earth is flat and NASA is lying about it\"\r\n\u002Fextract-claim https:\u002F\u002Fyoutube.com\u002Fwatch?v=abc123\r\n\u002Fextract-claim https:\u002F\u002Ftiktok.com\u002F@user\u002Fvideo\u002F123\r\n\u002Fextract-claim https:\u002F\u002Finstagram.com\u002Fp\u002Fabc123\r\n```\r\n\r\n**Supported Content Types:**\r\n- **Text**: Direct text input\r\n- **Video URLs**: YouTube, TikTok, Instagram (auto-transcribes)\r\n- **Language**: Set `language_code` for non-English content (default: \"en\")\r\n\r\n**Response Format:**\r\n- `status`: \"ok\" on success\r\n- `transcript`: Transcribed content (for video URLs)\r\n- `title`: Video\u002Farticle title (if available)\r\n- `description`: Content description (if available)\r\n- `claims`: Array of extracted claim strings\r\n- `overall_assessment`: Summary of extraction\r\n\r\n### 3. Get Credits (`\u002Fget-credits`)\r\n\r\nWhen the command is `\u002Fget-credits` or user wants to check API credits:\r\n\r\n**Endpoint:** `GET {BASE_URL}\u002Fget-credits`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n\r\nNo request body required.\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `email`: User email associated with the API key\r\n- `api_key`: The API key (masked)\r\n- `credits_left`: Number of credits remaining\r\n- `duration_seconds`: Duration period (typically 3600 seconds)\r\n\r\n**Usage:**\r\n```\r\n\u002Fget-credits\r\n```\r\n\r\n**Response Format:**\r\n```json\r\n{\r\n  \"email\": \"user@example.com\",\r\n  \"api_key\": \"your_api_key_here\",\r\n  \"credits_left\": 1482,\r\n  \"duration_seconds\": 3600\r\n}\r\n```\r\n\r\n### 4. Check Task Status (`\u002Fcheck-task-status`)\r\n\r\nWhen the command starts with `\u002Fcheck-task-status` or the input is a task ID:\r\n\r\n**Endpoint:** `GET {BASE_URL}\u002Fcheck-task-status?task_id=\u003Ctask_id>`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n\r\nThe raw command input should be the task_id from a previous async fact-check request (remove `\u002Fcheck-task-status` prefix if present).\r\n\r\n**Query Parameter:**\r\n- `task_id`: The unique ID of the task to check (from the raw command input)\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Fcheck-task-status 1234567890abcdef\r\n```\r\n\r\nOr with the task_id from a previous async fact-check:\r\n```\r\n\u002Ffact-check \"Long claim...\" --mode async\r\n# Returns task_id: abc123\r\n\u002Fcheck-task-status abc123\r\n```\r\n\r\n**Response Format:**\r\n\r\nFor completed tasks:\r\n```json\r\n{\r\n  \"status\": \"Completed\",\r\n  \"input_query\": \"Original Input query\",\r\n  \"classification\": \"False\",\r\n  \"overall_assessment\": \"This claim is inaccurate.\",\r\n  \"evidence_sources\": [\"Source 1\", \"Source 2\"],\r\n  \"disambiguation\": \"Clarifies the context...\",\r\n  \"detailed_source_reports\": [\"Detailed source report 1\", \"Detailed source report 2\"],\r\n  \"task_id\": \"1234567...\",\r\n  \"bias_quality_metrics\": [\r\n    {\r\n      \"source\": \"https:\u002F\u002Fwww.politico.com\",\r\n      \"bias\": -5.238666666666666,\r\n      \"quality\": 46.45\r\n    }\r\n  ]\r\n}\r\n```\r\n\r\nFor in-progress tasks, returns current status and progress information.\r\n\r\n### 5. Transcribe Link (`\u002Ftranscribe-link`)\r\n\r\nWhen the command starts with `\u002Ftranscribe-link` or the input is a URL to transcribe:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Ftranscribe-link`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"url\": \"\u003Craw command input (remove \u002Ftranscribe-link prefix if present)>\"\r\n}\r\n```\r\n\r\nThe raw command input should be the URL to transcribe (remove `\u002Ftranscribe-link` prefix if present).\r\n\r\nReturn the JSON response verbatim.\r\n\r\n**Usage:**\r\n```\r\n\u002Ftranscribe-link https:\u002F\u002Fyoutube.com\u002Fwatch?v=abc123\r\n\u002Ftranscribe-link https:\u002F\u002Ftiktok.com\u002F@user\u002Fvideo\u002F123\r\n\u002Ftranscribe-link https:\u002F\u002Finstagram.com\u002Fp\u002Fabc123\r\n```\r\n\r\n**Response Format:**\r\n- `status`: \"ok\" on success\r\n- `transcript`: Transcribed content from the link\r\n- `title`: Video\u002Farticle title (if available)\r\n- `description`: Content description (if available)\r\n- `duration`: Duration of the content (if available)\r\n\r\n### 6. Check Link Reliability (`\u002Flink-reliability\u002Fcheck`)\r\n\r\nWhen the command starts with `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` or the input is a URL to check for source reliability:\r\n\r\n**Endpoint:** `POST {BASE_URL}\u002Flink-reliability\u002Fcheck`\r\n\r\n**Headers:**\r\n- `X-API-KEY: ${FACTICITY_API_KEY}`\r\n- `Content-Type: application\u002Fjson`\r\n\r\n**Body:**\r\n```json\r\n{\r\n  \"url\": \"\u003Craw command input (remove \u002Flink-reliability\u002Fcheck or \u002Fcheck-link-reliability prefix if present)>\"\r\n}\r\n```\r\n\r\nThe raw command input should be the URL to check (remove `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` prefix if present).\r\n\r\nReturn the JSON response verbatim. The response includes:\r\n- `url`: The processed URL\r\n- `bias`: Bias score (-42 to +42)\r\n- `quality`: Quality score (0 to 64)\r\n- `bias_label`: Human-readable bias category\r\n- `quality_label`: Human-readable quality category\r\n- `found`: Whether the URL was found in MediaBias database\r\n\r\n**Usage:**\r\n```\r\n\u002Flink-reliability\u002Fcheck https:\u002F\u002Fwww.example.com\u002Farticle\r\n\u002Fcheck-link-reliability https:\u002F\u002Fwww.bbc.com\u002Fnews\r\n\u002Flink-reliability\u002Fcheck https:\u002F\u002Fwww.politico.com\u002Fstory\r\n```\r\n\r\n**Response Format:**\r\n```json\r\n{\r\n  \"url\": \"https:\u002F\u002Fwww.example.com\u002Farticle\",\r\n  \"bias\": -5.24,\r\n  \"quality\": 46.45,\r\n  \"bias_label\": \"Left-Center Bias\",\r\n  \"quality_label\": \"High Quality\",\r\n  \"found\": true\r\n}\r\n```\r\n\r\n**Note:** If the URL is not found in the MediaBias database, `found` will be `false` and bias\u002Fquality scores may be null or default values.\r\n\r\n## Command Routing\r\n\r\nDetermine which operation to perform based on the command prefix:\r\n- `\u002Ffact-check` or input looks like a claim → Fact-Check endpoint\r\n- `\u002Fextract-claim` or input is a URL → Extract Claims endpoint\r\n- `\u002Fget-credits` → Get Credits endpoint\r\n- `\u002Fcheck-task-status` or input is a task ID → Check Task Status endpoint\r\n- `\u002Ftranscribe-link` or input is a URL → Transcribe Link endpoint\r\n- `\u002Flink-reliability\u002Fcheck` or `\u002Fcheck-link-reliability` or input is a URL → Check Link Reliability endpoint\r\n\r\n## API Token Usage\r\n\r\n- **Fact-Check**: Each request consumes 1 API token\r\n- **Extract Claims**: Consumes 1 API token per 1 million characters processed\r\n- **Get Credits**: Free, does not consume tokens\r\n- **Check Task Status**: Free, does not consume tokens\r\n- **Transcribe Link**: Consumes 1 API token per transcription request\r\n- **Check Link Reliability**: Consumes 1 API token per request\r\n\r\nMonitor usage with `\u002Fget-credits`.\r\n\r\n## Configuration\r\n\r\nSet `FACTICITY_API_KEY` in your OpenClaw config under `skills.entries.facticity-ai.apiKey` or as an environment variable.\r\n\r\n**Example config:**\r\n```json\r\n{\r\n  \"skills\": {\r\n    \"entries\": {\r\n      \"facticity-ai\": {\r\n        \"enabled\": true,\r\n        \"apiKey\": \"YOUR_API_KEY_HERE\"\r\n      }\r\n    }\r\n  }\r\n}\r\n```\r\n\r\nOr set as environment variable:\r\n```bash\r\nexport FACTICITY_API_KEY=your_api_key_here\r\n```\r\n",{"name":5,"metadata":24,"description":7,"command-tool":31,"user-invocable":32,"command-arg-mode":33,"command-dispatch":34},{"openclaw":25},{"emoji":26,"homepage":27,"requires":28,"primaryEnv":30},"🔍","https:\u002F\u002Fapp.facticity.ai",{"env":29},[30],"FACTICITY_API_KEY","http.request",true,"raw","tool","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fshahruj\u002Ffacticity-ai",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":32},[46,49,52],{"tool":47,"command":48},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill facticity-ai",{"tool":50,"command":51},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill facticity-ai",{"tool":53,"command":54},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill facticity-ai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshahruj\u002Ffacticity-ai\u002FSKILL.md",[],[58,66,73,80,87,94],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"01M778GGXG2VQ0YF31W2MKGMQZ","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":65},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":65},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":65},"01M778FQQNSEYA3HJKZBPQ4M9Z","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":65},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":65},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]