# Send anakin to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "anakin", "name": "anakin", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Viraal-Bambori/anakin", "canonicalUrl": "https://clawhub.ai/Viraal-Bambori/anakin", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/anakin", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anakin", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "README.md", "SKILL.md", "skill.json", "rules/install.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "anakin", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-11T16:34:24.086Z", "expiresAt": "2026-05-18T16:34:24.086Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anakin", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anakin", "contentDisposition": "attachment; filename=\"anakin-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "anakin" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/anakin" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/anakin", "downloadUrl": "https://openagent3.xyz/downloads/anakin", "agentUrl": "https://openagent3.xyz/skills/anakin/agent", "manifestUrl": "https://openagent3.xyz/skills/anakin/agent.json", "briefUrl": "https://openagent3.xyz/skills/anakin/agent.md" } } ``` ## Documentation ### Anakin - Web Data Extraction Convert websites into clean data at scale using the anakin-cli. Supports single URL scraping, batch scraping, AI-powered search, and autonomous deep research. ### Installation & Authentication Check status and authentication: anakin status Output when ready: ✓ Authenticated Endpoint: https://api.anakin.io Account: user@example.com If not installed: pip install anakin-cli Always refer to the installation rules in rules/install.md for more information if the user is not logged in. If not authenticated, run: anakin login --api-key "ak-your-key-here" Get your API key from anakin.io/dashboard. ### Organization Create a .anakin/ folder in the working directory unless it already exists to store results. Add .anakin/ to the .gitignore file if not already there. Always use -o to write directly to file (avoids flooding context): mkdir -p .anakin echo ".anakin/" >> .gitignore anakin scrape "https://example.com" -o .anakin/output.md ### 1. Scrape a Single URL Extract content from a single web page in multiple formats. When to use: Extracting content from a single web page Converting a webpage to clean markdown Extracting structured data from one URL Getting full raw API response with metadata Basic usage: # Clean readable text (default markdown format) anakin scrape "https://example.com" -o output.md # Structured data (JSON) anakin scrape "https://example.com" --format json -o output.json # Full API response with HTML and metadata anakin scrape "https://example.com" --format raw -o output.json Advanced options: # JavaScript-heavy or single-page app sites anakin scrape "https://example.com" --browser -o output.md # Geo-targeted scraping (country code) anakin scrape "https://example.com" --country gb -o output.md # Custom timeout for slow pages (in seconds) anakin scrape "https://example.com" --timeout 300 -o output.md ### 2. Batch Scrape Multiple URLs Scrape up to 10 URLs at once for efficient parallel processing. When to use: Scraping multiple web pages simultaneously Comparing products across different sites Collecting multiple articles or pages Gathering data from several sources at once Basic usage: # Batch scrape multiple URLs (up to 10) anakin scrape-batch "https://example.com/page1" "https://example.com/page2" "https://example.com/page3" -o batch-results.json For large lists (>10 URLs): # First batch (URLs 1-10) anakin scrape-batch "https://url1.com" ... "https://url10.com" -o batch-1.json # Second batch (URLs 11-20) anakin scrape-batch "https://url11.com" ... "https://url20.com" -o batch-2.json Output format: JSON file with combined results, each URL's status (success/failure), content, metadata, and any errors. ### 3. AI-Powered Web Search Run intelligent web searches to find pages, answer questions, and discover sources. When to use: Finding pages on a specific topic Answering questions with web sources Discovering relevant sources for research Gathering links before scraping specific pages Quick factual lookups Basic usage: # AI-powered web search anakin search "your search query here" -o search-results.json Follow-up workflow: # 1. Search for relevant pages anakin search "machine learning tutorials" -o search-results.json # 2. Scrape specific results for full content anakin scrape "https://result-url-from-search.com" -o page.md Output format: JSON file with search results including titles, URLs, snippets, relevance scores, and metadata. ### 4. Deep Agentic Research Run comprehensive autonomous research that explores the web and returns detailed reports. When to use: Comprehensive research on complex topics Market analysis requiring multiple sources Technical deep-dives across documentation and articles Comparison research (products, technologies, approaches) Questions requiring synthesis from many sources Basic usage: # Deep agentic research (takes 1-5 minutes) anakin research "your research topic or question" -o research-report.json # With extended timeout for complex topics anakin research "comprehensive analysis of quantum computing" --timeout 600 -o research-report.json ⏱️ Important: Deep research takes 1-5 minutes and runs autonomously. Always inform the user about this duration before starting. What it does: Autonomously searches for relevant sources Scrapes and analyzes multiple pages Synthesizes information across sources Generates comprehensive reports with citations Provides key insights and conclusions Output format: JSON file with executive summary, detailed report by subtopics, key insights, citations with URLs, confidence scores, and related topics. ### Decision Guide Use anakin scrape when: You have a single specific URL to extract You need content in markdown, JSON, or raw format The page is static or JavaScript-heavy (use --browser) Use anakin scrape-batch when: You have 2-10 URLs to scrape simultaneously You need efficient parallel processing You want combined results in one file Use anakin search when: You need to find relevant URLs first You want quick factual lookups You need results in under 30 seconds You know what you're looking for Use anakin research when: You need comprehensive analysis across 5+ sources The topic is complex and requires deep exploration You want a synthesized report with insights You can wait 1-5 minutes for autonomous research The question requires comparing multiple perspectives ### URL Handling Always quote URLs to prevent shell interpretation of ?, &, # characters Example: anakin scrape "https://example.com?param=value" not anakin scrape https://example.com?param=value ### Output Management Always use -o to save output to a file rather than flooding the terminal Choose appropriate output filenames based on content type ### Format Selection Default to markdown for readability unless user explicitly asks for JSON or raw Use --format json for structured data processing Use --format raw for full API response with HTML ### Special Cases Use --browser only when standard scrape returns empty or incomplete content For batch scraping: Maximum 10 URLs per command — split larger lists For research: Always warn about 1-5 minute duration before starting ### Rate Limiting On HTTP 429 errors (rate limit), wait before retrying Do not loop immediately on rate limit errors ### Authentication On HTTP 401 errors, re-run anakin login rather than retrying the same command ### Error Handling ErrorSolutionHTTP 401 (Unauthorized)Re-run anakin login --api-key "your-key"HTTP 429 (Rate Limited)Wait before retrying, do not loop immediatelyEmpty contentTry adding --browser flag for JavaScript-heavy sitesTimeoutIncrease with --timeout for slow pagesBatch partial failureCheck output JSON for individual statuses, retry failed URLs with --browserResearch failsFall back to search + multiple scrape calls manually ### Markdown (default for scrape) Clean, readable text stripped of navigation and ads Best for human reading and summarization File extension: .md ### JSON (structured) Structured data with title, content, metadata Best for processing and parsing File extension: .json ### Raw (full response) Full API response including HTML, links, images, metadata Best for debugging or accessing all available data File extension: .json ### Example 1: Article extraction anakin scrape "https://blog.example.com/article" -o article.md ### Example 2: Product comparison anakin scrape-batch "https://store1.com/product" "https://store2.com/product" "https://store3.com/product" -o products.json ### Example 3: Find and scrape # Step 1: Find relevant URLs anakin search "best coffee shops in Seattle" -o coffee-search.json # Step 2: Scrape the top results anakin scrape-batch "url1" "url2" "url3" -o coffee-details.json ### Example 4: Market research anakin research "market trends in electric vehicle adoption 2024-2026" -o ev-research.json ### Example 5: JavaScript-heavy site anakin scrape "https://spa-application.com" --browser -o spa-content.md ### Example 6: Geo-targeted content anakin scrape "https://news-site.com" --country us -o us-news.md anakin scrape "https://news-site.com" --country gb -o gb-news.md ### Best Practices Start simple: Try basic scrape first, add flags only if needed Be specific: Use clear, specific search queries and research topics Quote URLs: Always wrap URLs in quotes Save output: Always use -o flag to save results to files Check status: Run anakin status before starting work Batch wisely: Group similar URLs together, max 10 per batch Wait on rate limits: Don't retry immediately on 429 errors Choose the right tool: Single page → scrape Multiple pages → scrape-batch Don't have URLs → search first Need deep analysis → research ### Authentication issues # Check status anakin status # Re-authenticate anakin login --api-key "ak-your-key-here" ### Empty or incomplete content Add --browser flag for JavaScript-heavy sites Increase timeout with --timeout 300 Check if the site requires specific geo-location with --country ### Rate limiting Wait before retrying (don't loop immediately) Consider spacing out requests for large batch operations Check your API plan limits at anakin.io/dashboard ### Resources Anakin Website Anakin Dashboard - Get API keys and check usage anakin-cli on PyPI Support ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Viraal-Bambori - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-11T16:34:24.086Z - Expires at: 2026-05-18T16:34:24.086Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/anakin) - [Send to Agent page](https://openagent3.xyz/skills/anakin/agent) - [JSON manifest](https://openagent3.xyz/skills/anakin/agent.json) - [Markdown brief](https://openagent3.xyz/skills/anakin/agent.md) - [Download page](https://openagent3.xyz/downloads/anakin)