[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BN446G5QXCPRKQWRDNZMPT":3,"skill-same:01M7BN446G5QXCPRKQWRDNZMPT":58},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7BN446G5QXCPRKQWRDNZMPT","paddleocr-text-recognition",null,"Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.","xs3curity\u002Fskillguard-action-test","xs3curity","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F83658112?v=4","01M7BKPAAZ8H0V8MMNN8PVR2PJ","xsec","01M7BKPABJNGD944G93J56FDWS",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fpaddlepaddle-paddleocr-skills-paddleocr-text-recognition-skill-md\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: paddleocr-text-recognition\ndescription: >-\n  Use this skill whenever the user wants text extracted from images, photos, scans, screenshots,\n  or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox\n  coordinates. Strong accuracy for CJK, small print, and handwritten text.\n  Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字,\n  plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan,\n  recognize text.\nlicense: Apache-2.0\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - PADDLEOCR_ACCESS_TOKEN\n      bins:\n        - paddleocr\n    primaryEnv: PADDLEOCR_ACCESS_TOKEN\n    emoji: \"🔤\"\n    install:\n      - kind: uv\n        package: paddleocr\n        bins: [paddleocr]\n---\n\n# PaddleOCR Text Recognition\n\n## When to Use This Skill\n\n**Use this skill for**:\n\n- Extract text from images (screenshots, photos, scans)\n- Extract text from PDFs or document images when the goal is **line\u002Fbox-level text**\n- Extract text from URLs or local files that point to images\u002FPDFs\n\n**Do not use for**:\n\n- Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead\n\n## Usage\n\n### Basic OCR\n\nFrom URL:\n\n```bash\npaddleocr api \\\n  --model_type ocr \\\n  --file_url \"https:\u002F\u002Fexample.com\u002Fimage.png\"\n```\n\nFrom local file:\n\n```bash\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Fdocument.pdf\"\n```\n\n### Common Options\n\n```bash\n# With specific model\npaddleocr api \\\n  --model_type ocr \\\n  --model PP-OCRv5 \\\n  --file_path \".\u002Freport.pdf\"\n\n# Disable preprocessing (faster, for flat\u002Fwell-oriented images)\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Fdocument.pdf\" \\\n  --use_doc_unwarping False \\\n  --use_doc_orientation_classify False\n\n# Save result to file\npaddleocr api \\\n  --model_type ocr \\\n  --file_url \"https:\u002F\u002F...\" \\\n  --output result.json\n\n# Page ranges\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Flarge.pdf\" \\\n  --page_ranges \"1-5,10,15-20\"\n```\n\n### Output Format\n\n```json\n{\n  \"jobId\": \"job-xxx\",\n  \"pages\": [\n    {\n      \"prunedResult\": {\n        \"rec_texts\": [\"Line 1\", \"Line 2\"],\n        \"rec_scores\": [0.98, 0.95]\n      },\n      \"ocrImageUrl\": \"https:\u002F\u002F...\"\n    }\n  ]\n}\n```\n\n## Important Notes\n\n**Preprocessing options**: By default, the API enables document preprocessing (unwarping and orientation classification). For flat, well-oriented images (screenshots, properly scanned documents), you can disable preprocessing for faster results:\n\n```bash\npaddleocr api --model_type ocr --file_path \".\u002Fdocument.pdf\" --use_doc_unwarping False --use_doc_orientation_classify False\n```\n\nKeep preprocessing enabled when:\n- The input is a photo of a curved or folded document\n- The document has significant perspective distortion\n- Orientation is uncertain (rotated 90\u002F180\u002F270 degrees)\n\n**Display complete results**: Always show the full extracted content to users. Do not truncate with \"...\" unless content exceeds 10,000 characters. When multiple pages are processed, summarize if needed but provide complete results when explicitly requested.\n\n**Handle errors gracefully**: When the CLI returns an error, inform the user of the specific issue rather than silently failing or falling back to your own vision capabilities. Common errors:\n- Authentication: `PADDLEOCR_ACCESS_TOKEN` invalid or missing\n- Quota: API rate limit exceeded\n- No content detected: Image may be blank or contain no text\n\n## CLI Reference\n\nRun `paddleocr api --help` for all options.\n\nFor full documentation, see: [PaddleOCR Official Documentation](https:\u002F\u002Fwww.paddleocr.ai\u002Flatest\u002Fen\u002Fversion3.x\u002Finference_deployment\u002Fserving\u002Fpaddleocr_official_api\u002Fcli.html)\n","# PaddleOCR Text Recognition\n\n## When to Use This Skill\n\n**Use this skill for**:\n\n- Extract text from images (screenshots, photos, scans)\n- Extract text from PDFs or document images when the goal is **line\u002Fbox-level text**\n- Extract text from URLs or local files that point to images\u002FPDFs\n\n**Do not use for**:\n\n- Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead\n\n## Usage\n\n### Basic OCR\n\nFrom URL:\n\n```bash\npaddleocr api \\\n  --model_type ocr \\\n  --file_url \"https:\u002F\u002Fexample.com\u002Fimage.png\"\n```\n\nFrom local file:\n\n```bash\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Fdocument.pdf\"\n```\n\n### Common Options\n\n```bash\n# With specific model\npaddleocr api \\\n  --model_type ocr \\\n  --model PP-OCRv5 \\\n  --file_path \".\u002Freport.pdf\"\n\n# Disable preprocessing (faster, for flat\u002Fwell-oriented images)\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Fdocument.pdf\" \\\n  --use_doc_unwarping False \\\n  --use_doc_orientation_classify False\n\n# Save result to file\npaddleocr api \\\n  --model_type ocr \\\n  --file_url \"https:\u002F\u002F...\" \\\n  --output result.json\n\n# Page ranges\npaddleocr api \\\n  --model_type ocr \\\n  --file_path \".\u002Flarge.pdf\" \\\n  --page_ranges \"1-5,10,15-20\"\n```\n\n### Output Format\n\n```json\n{\n  \"jobId\": \"job-xxx\",\n  \"pages\": [\n    {\n      \"prunedResult\": {\n        \"rec_texts\": [\"Line 1\", \"Line 2\"],\n        \"rec_scores\": [0.98, 0.95]\n      },\n      \"ocrImageUrl\": \"https:\u002F\u002F...\"\n    }\n  ]\n}\n```\n\n## Important Notes\n\n**Preprocessing options**: By default, the API enables document preprocessing (unwarping and orientation classification). For flat, well-oriented images (screenshots, properly scanned documents), you can disable preprocessing for faster results:\n\n```bash\npaddleocr api --model_type ocr --file_path \".\u002Fdocument.pdf\" --use_doc_unwarping False --use_doc_orientation_classify False\n```\n\nKeep preprocessing enabled when:\n- The input is a photo of a curved or folded document\n- The document has significant perspective distortion\n- Orientation is uncertain (rotated 90\u002F180\u002F270 degrees)\n\n**Display complete results**: Always show the full extracted content to users. Do not truncate with \"...\" unless content exceeds 10,000 characters. When multiple pages are processed, summarize if needed but provide complete results when explicitly requested.\n\n**Handle errors gracefully**: When the CLI returns an error, inform the user of the specific issue rather than silently failing or falling back to your own vision capabilities. Common errors:\n- Authentication: `PADDLEOCR_ACCESS_TOKEN` invalid or missing\n- Quota: API rate limit exceeded\n- No content detected: Image may be blank or contain no text\n\n## CLI Reference\n\nRun `paddleocr api --help` for all options.\n\nFor full documentation, see: [PaddleOCR Official Documentation](https:\u002F\u002Fwww.paddleocr.ai\u002Flatest\u002Fen\u002Fversion3.x\u002Finference_deployment\u002Fserving\u002Fpaddleocr_official_api\u002Fcli.html)\n",{"name":5,"license":15,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"install":27,"requires":32,"primaryEnv":34},"🔤",[28],{"bins":29,"kind":31,"package":30},[30],"paddleocr","uv",{"env":33,"bins":35},[34],"PADDLEOCR_ACCESS_TOKEN",[30],"dev","43ddf82aded0870549685e5df8dceb70bf42a4c2","old\u002Fpaddlepaddle-paddleocr-skills-paddleocr-text-recognition-skill-md",1,"https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test","https:\u002F\u002Fgithub.com\u002Fxs3curity","security engineer","2026-09-01 00:39:28",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add xs3curity\u002Fskillguard-action-test --skill paddleocr-text-recognition",{"tool":50,"command":51},"bunx","bunx skills add xs3curity\u002Fskillguard-action-test --skill paddleocr-text-recognition",{"tool":53,"command":54},"pnpm","pnpm dlx skills add xs3curity\u002Fskillguard-action-test --skill paddleocr-text-recognition","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fpaddlepaddle-paddleocr-skills-paddleocr-text-recognition-skill-md\u002FSKILL.md",true,[],[59,67,75,82,89,96],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":63,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7BNDGBAMKWZJRG5QAH7JGK1","mcp-apps-builder","**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns.\n\n**READ THIS FIRST** before any MCP server work, including:\n- Creating new MCP servers\n- Modifying existing MCP servers (adding\u002Fupdating tools, resources, prompts, widgets)\n- Debugging MCP server issues or errors\n- Reviewing MCP server code for quality, security, or performance\n- Answering questions about MCP development or mcp-use patterns\n- Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets\n\nThis skill contains critical architecture decisions, security patterns, and common pitfalls.\nAlways consult the relevant reference files BEFORE implementing MCP features.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-generative-ui-agents-ai-mcp-app-builder-apps-mcp-use-server-agent-skills-mcp-apps-builder-skill-md\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-generative-ui-agents-ai-mcp-app-builder-apps-mcp-use-server-agent-skills-mcp-apps-builder-skill-md\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7BNDBAK4CH7F5QF3HCW90FD","chatgpt-app-builder","DEPRECATED: This skill has been replaced by `mcp-app-builder`.\nCheck if `mcp-app-builder` is available in the skills folder. If not, install it:\n`npx skills install mcp-use\u002Fmcp-use --skill mcp-app-builder`\nUse `mcp-app-builder` instead of this skill.\n\nBuild ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK.\nUse when creating ChatGPT apps, building MCP servers with widgets, defining React widgets,\nworking with Apps SDK, or when user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-generative-ui-agents-ai-mcp-app-builder-apps-mcp-use-server-agent-skills-chatgpt-app-builder-skill-md\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-generative-ui-agents-ai-mcp-app-builder-apps-mcp-use-server-agent-skills-chatgpt-app-builder-skill-md\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7BND3E7T2VTBFM95V6DTFQ8","thinking-out-loud","A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's inferences and guesses quarantined away from the user's own phrasing, so the user verifies what the model believes, not just what it doubts. Use when the user says \"let me think out loud\" or wants to ramble a bit before building anything, when a message opens with a speech-to-text preamble like \"switching to voice, sorry for typos\", when input is a long weakly punctuated stream with restarts and mid-message reversals (\"actually no, wait, scrap that idea entirely\"), or when the user asks to be interviewed about a fuzzy half-formed idea. Includes an optional capture mode for rambles spread across several messages and an optional targeted interview.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-agent-skills-thinking-out-loud-skill-md\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BNCZA24EY6B9D6BNQGG0VT","scope-creep-detector","Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too broad, or what unrelated stuff they touched, and wants keep, split, or justify guidance. Operates locally and offline.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-agent-skills-scope-creep-detector-skill-md\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7BNCT47CZHQS68CMD9JEZVX","project-graveyard","Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions abandoned, unfinished, or old side projects, asks \"what should I finish\", wants to revive or resurrect a project, says \"run the graveyard\", wonders why they never finish anything, or is about to start a new project that sounds like one they already built. Runs entirely locally.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-agent-skills-project-graveyard-skill-md\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7BNCMBHV66QM01QQWE0HGNP","dependency-doctor","Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest for dependency problems, asks why dependencies won't install or whether anything is wrong with their dependencies, wants a dependency autopsy, or suspects dependency manifest rot. Runs offline by default as a local tool for the user's own project, not repository CI.","https:\u002F\u002Fgithub.com\u002Fxs3curity\u002Fskillguard-action-test\u002Fblob\u002Fdev\u002Fold\u002Fshubhamsaboo-awesome-llm-apps-agent-skills-dependency-doctor-skill-md\u002FSKILL.md",[],[]]