# Send Twitter/X Reader 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": "twitter-reader", "name": "Twitter/X Reader", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/iheardulkBTC/twitter-reader", "canonicalUrl": "https://clawhub.ai/iheardulkBTC/twitter-reader", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/twitter-reader", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-reader", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "INSTALLATION.md", "README.md", "SKILL.md", "scripts/read_thread.sh", "scripts/read_tweet.sh", "scripts/read_tweet_nitter.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "twitter-reader", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-10T07:52:25.634Z", "expiresAt": "2026-05-17T07:52:25.634Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-reader", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-reader", "contentDisposition": "attachment; filename=\"twitter-reader-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "twitter-reader" }, "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/twitter-reader" }, "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/twitter-reader", "downloadUrl": "https://openagent3.xyz/downloads/twitter-reader", "agentUrl": "https://openagent3.xyz/skills/twitter-reader/agent", "manifestUrl": "https://openagent3.xyz/skills/twitter-reader/agent.json", "briefUrl": "https://openagent3.xyz/skills/twitter-reader/agent.md" } } ``` ## Documentation ### Twitter/X Reader Skill A comprehensive skill for reading and extracting data from X (formerly Twitter) tweets using multiple reliable data sources. ### Overview This skill extracts complete tweet information including text content, author details, engagement statistics, media attachments, and quoted tweets from X/Twitter URLs. It uses a multi-tier approach for maximum reliability and data completeness. ### When to Use Primary Triggers: User shares a tweet URL (x.com//status/ or twitter.com//status/) User asks to "read this tweet" with a URL User requests tweet analysis, summary, or data extraction User mentions getting information from a specific tweet Example User Requests: "What does this tweet say? https://x.com/elonmusk/status/123456789" "Can you read this tweet for me?" "Summarize this Twitter thread" "What are the engagement stats on this tweet?" "Extract the media from this tweet" ### Data Extracted Tweet Content: Full text with proper formatting Author Information: Display name and handle (@username) Timestamps: Both human-readable and original format Engagement Stats: Likes, retweets, replies, quote tweets Media Attachments: Photos and videos with direct URLs Quote Tweets: Full quoted tweet content and author info Thread Context: When available ### Supported URL Formats https://x.com/username/status/1234567890 https://twitter.com/username/status/1234567890 URLs with query parameters (e.g., ?s=20, ?t=abc123) Mobile URLs (m.twitter.com automatically handled) ### Basic Usage # Read a single tweet ./scripts/read_tweet.sh "https://x.com/username/status/1234567890" # Read a full thread (follows reply chain from the same author) ./scripts/read_thread.sh "https://x.com/username/status/1234567890" # Fallback method using Nitter ./scripts/read_tweet_nitter.sh "https://x.com/username/status/1234567890" ### Agent Instructions When a user provides a tweet URL: Validate the URL format - ensure it's a valid X/Twitter status URL Use the primary script - scripts/read_tweet.sh first Handle failures gracefully - if primary fails, try scripts/read_tweet_nitter.sh Present data clearly - format the output for human consumption Preserve context - include engagement stats and media references ### Sample Response Format The scripts return structured JSON with this format: { "success": true, "tweet": { "text": "Tweet content here...", "author": { "name": "Display Name", "handle": "username" }, "timestamp": { "formatted": "2024-01-15 14:30:25 UTC", "original": "Mon Jan 15 14:30:25 +0000 2024" }, "url": "https://x.com/username/status/1234567890", "engagement": { "likes": 1250, "retweets": 340, "replies": 89, "quotes": 45 }, "media": { "photos": ["https://pbs.twimg.com/media/..."], "video": "https://video.twimg.com/..." }, "quoted_tweet": { "text": "Quoted tweet text...", "author": { "name": "Quoted Author", "handle": "quoted_user" }, "url": "https://x.com/quoted_user/status/987654321" } }, "source": "fxtwitter", "fetched_at": 1705327825 } ### Agent Response Example **Tweet from @elonmusk:** > "Just had a great meeting about sustainable transport. The future is electric! ⚡🚗" **Posted:** January 15, 2024 at 2:30 PM UTC **Engagement:** 1,250 likes • 340 retweets • 89 replies • 45 quotes **Media:** 1 photo attached - Photo: https://pbs.twimg.com/media/example.jpg **Quote Tweet from @teslaofficial:** > "Our latest Model S update includes new charging optimizations..." ### Primary Method: FxTwitter API Endpoint: https://api.fxtwitter.com/{username}/status/{tweet_id} Advantages: No authentication, comprehensive data, reliable Rate Limits: Generous for personal use Response: Complete JSON with all tweet metadata ### Fallback Method: Nitter Scraping (Best-Effort) Instances: Multiple public Nitter instances as backup Advantages: Works when FxTwitter is unavailable Limitations: Basic data extraction, no engagement stats Usage: Automatic fallback when primary method fails ⚠️ Note: Most public Nitter instances have shut down or become unreliable since 2024. This fallback is best-effort and may not return results. The FxTwitter API should be considered the only reliable method. ### Error Handling Invalid URL format detection Network timeout handling API error response parsing Graceful fallback between methods Clear error messages for users ### Dependencies Required System Tools: curl - HTTP requests to APIs jq - JSON parsing and formatting bash - Script execution environment grep/sed - Text processing (Nitter fallback only) Optional Enhancements: gdate (GNU date via Homebrew on macOS) - Better timestamp formatting ### Security Features ✅ No external data collection - Data stays on your system ✅ No analytics or telemetry - No tracking or usage reporting ✅ Fully auditable code - Open source, readable shell scripts ✅ Minimal network calls - Only to FxTwitter API and Nitter instances ✅ No sensitive data exposure - Scripts don't store or log personal info ✅ Safe URL handling - Proper URL validation and sanitization ### Network Connections Approved External Hosts: api.fxtwitter.com - Primary data source (FxTwitter API) nitter.net and other Nitter instances - Fallback scraping No other external connections made Data Flow: User provides tweet URL Script extracts username/ID from URL Makes API request to FxTwitter or Nitter Parses response locally Returns formatted JSON (never stored permanently) ### Audit Trail All network requests include: Clear user-agent identification Minimal necessary headers only No authentication tokens or personal identifiers Requests only to extract public tweet data ### Common Errors Invalid URL Format: { "error": "Invalid Twitter/X URL format", "expected": "x.com/user/status/123456789 or twitter.com/user/status/123456789" } Tweet Not Found: { "error": "API Error", "code": 404, "message": "NOT_FOUND" } Network Failure: { "error": "Failed to fetch tweet data", "details": "Network request failed" } Fallback Needed: { "error": "All Nitter instances failed", "suggestion": "Try the main script with FxTwitter API, or wait for Nitter instances to recover" } ### Agent Error Handling When errors occur: Parse the error JSON to understand the issue Try the fallback method if primary fails Explain to the user what went wrong in plain language Suggest alternatives (try again later, check URL format, etc.) ### Thread Reading Full thread unrolling is supported via read_thread.sh: Given any tweet URL in a thread, walks UP the reply chain via replying_to fields Only collects tweets from the same author (self-reply threads) Returns tweets in chronological order as a JSON array Safety limit of 50 tweets per thread (configurable via second argument) Usage: ./scripts/read_thread.sh "https://x.com/user/status/123" [max_depth] ### Media Handling Photos: Direct URLs via media.photos array (full-resolution) Videos: Links to MP4 files via media.videos with thumbnails and duration All media: Combined media.all array with type annotations for complete coverage Article covers: Long-form X posts ("articles") have media.article_cover extracted GIFs: Handled as video content External Links: Preserved in tweet text ### Quote Tweet Recursion The skill can extract nested quote tweets up to reasonable depth to avoid infinite loops. ### Response Times FxTwitter API: Typically 200-500ms Nitter Scraping: 1-3 seconds per instance Network Dependent: May vary based on connection quality ### Caching Considerations No persistent caching implemented by default Consider temporary caching for repeated requests Respect rate limits of external services ### Common Issues "No tweet data in API response" Tweet may be deleted or protected Check URL format and tweet ID Try fallback method "Network request failed" Check internet connection FxTwitter API may be temporarily down Fallback to Nitter method "All Nitter instances failed" Nitter instances may be blocked or down Wait and retry with FxTwitter API Check firewall/proxy settings ### Debug Mode For debugging, run with verbose output: bash -x scripts/read_tweet.sh "https://x.com/username/status/123" ### Adding New Data Sources To add additional fallback methods: Create new script in scripts/ directory Follow same JSON output format Update main skill logic to include new method Test thoroughly and update documentation ### Modifying Output Format The JSON structure can be customized by modifying the final jq command in each script. Maintain consistency across all methods. ### Adding Features Consider these enhancement areas: Sentiment analysis of tweet content Hashtag and mention extraction Link expansion and preview Image OCR for text in media Translation support for non-English tweets ### Version History v1.1 - Thread following (read_thread.sh), comprehensive media extraction (photos, videos, all media, article covers) v1.0 - Initial release with FxTwitter API and Nitter fallback Multi-source reliability with comprehensive data extraction Full security audit compliance Production-ready for ClawHub distribution ## Trust - Source: tencent - Verification: Indexed source record - Publisher: iheardulkBTC - 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: 2026-05-10T07:52:25.634Z - Expires at: 2026-05-17T07:52:25.634Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/twitter-reader) - [Send to Agent page](https://openagent3.xyz/skills/twitter-reader/agent) - [JSON manifest](https://openagent3.xyz/skills/twitter-reader/agent.json) - [Markdown brief](https://openagent3.xyz/skills/twitter-reader/agent.md) - [Download page](https://openagent3.xyz/downloads/twitter-reader)