# Send Twitter Search 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-search-skill", "name": "Twitter Search", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/flyfoxCI/twitter-search-skill", "canonicalUrl": "https://clawhub.ai/flyfoxCI/twitter-search-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/twitter-search-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-search-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "references/twitter_api.md", "scripts/run_search.sh", "scripts/twitter_search.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "twitter-search-skill", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-10T08:00:13.063Z", "expiresAt": "2026-05-17T08:00:13.063Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-search-skill", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twitter-search-skill", "contentDisposition": "attachment; filename=\"twitter-search-skill-0.1.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "twitter-search-skill" }, "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-search-skill" }, "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-search-skill", "downloadUrl": "https://openagent3.xyz/downloads/twitter-search-skill", "agentUrl": "https://openagent3.xyz/skills/twitter-search-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/twitter-search-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/twitter-search-skill/agent.md" } } ``` ## Documentation ### Overview Search Twitter for keywords using advanced search syntax, fetch up to 1000 relevant tweets, and analyze the data to produce professional reports with insights, statistics, and actionable recommendations. ### Prerequisites API Key Required: Users must configure their Twitter API key from https://twitterapi.io The API key can be provided in three ways: Environment variable (recommended): Set TWITTER_API_KEY in your ~/.bashrc or ~/.zshrc echo 'export TWITTER_API_KEY="your_key_here"' >> ~/.bashrc source ~/.bashrc As an argument: Use --api-key YOUR_KEY with the wrapper script Passed directly: As first argument to the Python script ### Using the Wrapper Script (Recommended) The wrapper script automatically handles environment variable loading and dependency checks: # Basic search (uses TWITTER_API_KEY from shell config) ./scripts/run_search.sh "AI" # With custom API key ./scripts/run_search.sh "AI" --api-key YOUR_KEY # With options ./scripts/run_search.sh "\\"Claude AI\\"" --max-results 100 --format summary # Advanced query ./scripts/run_search.sh "from:elonmusk since:2024-01-01" --query-type Latest ### Direct Python Script Usage # Search for a keyword scripts/twitter_search.py "$API_KEY" "AI" # Search with multiple keywords scripts/twitter_search.py "$API_KEY" "\\"ChatGPT\\" OR \\"Claude AI\\"" # Search from specific user scripts/twitter_search.py "$API_KEY" "from:elonmusk" # Search with date range scripts/twitter_search.py "$API_KEY" "Bitcoin since:2024-01-01" ### Advanced Queries # Complex query: AI tweets from verified users, English only scripts/twitter_search.py "$API_KEY" "AI OR \\"machine learning\\" lang:en filter:verified" # Recent crypto tweets with minimum engagement scripts/twitter_search.py "$API_KEY" "Bitcoin min_retweets:10 lang:en" # From specific influencers scripts/twitter_search.py "$API_KEY" "from:elonmusk OR from:VitalikButerin since:2024-01-01" ### Output Format # Full JSON with all tweets scripts/twitter_search.py "$API_KEY" "AI" --format json # Summary with statistics (default) scripts/twitter_search.py "$API_KEY" "AI" --format summary ### Options --max-results N: Maximum tweets to fetch (default: 1000) --query-type Latest|Top: Sort order (default: Top for relevance) --format json|summary: Output format (default: summary) ### 1. Understand User Requirements Clarify the analysis goal: What topic/keyword to search? Date range preference? Specific users to include/exclude? Language preference? Type of insights needed (trends, sentiment, influencers)? ### 2. Build the Search Query Use Twitter Advanced Search syntax: SyntaxExampleDescriptionkeywordAISingle keyword"phrase""machine learning"Exact phraseORAI OR ChatGPTEither termfrom:userfrom:elonmuskFrom specific userto:userto:elonmuskReply to usersince:DATEsince:2024-01-01After dateuntil:DATEuntil:2024-12-31Before datelang:xxlang:enLanguage code#hashtag#AIHashtagfilter:linksfilter:linksTweets with linksmin_retweets:Nmin_retweets:100Minimum retweets ### 3. Fetch Data Execute the search script: scripts/twitter_search.py "$API_KEY" "YOUR_QUERY" --max-results 1000 --query-type Top Important: Default is 1000 tweets maximum. The script automatically: Paginates through all available results Stops at 1000 tweets (API limit consideration) Handles errors gracefully ### 4. Analyze and Generate Report After fetching data, produce a comprehensive professional report with: Report Structure Executive Summary (2-3 sentences) What was searched Key findings overview Data Overview Total tweets analyzed Date range of data Query parameters used Key Metrics Total engagement (likes, retweets, replies, quotes, views) Average engagement per tweet Language distribution Reply vs. original tweet ratio Top Content Analysis Most retweeted tweets (with URL links to original tweets) Most liked tweets (with URL links to original tweets) Top hashtags with frequency Most mentioned users Selected tweet examples with full URL references Influencer Analysis Top users by follower count Most active users Verified user percentage Trend Insights (based on data patterns) Emerging themes Sentiment indicators Temporal patterns Conversation drivers Key Takeaways 3-5 bullet points of core insights Data-backed conclusions Actionable Recommendations Specific, implementable suggestions Based on the data findings Prioritized by impact Analysis Guidelines Be data-driven: Every claim should reference actual metrics Provide context: Explain why metrics matter Identify patterns: Look for trends across the dataset Stay objective: Present facts, avoid speculation Be specific: Recommendations should be concrete and actionable Consider external context: Use web search for background when relevant ### 5. Output Format Present the report in clear markdown with: Headers for each section Tables for structured data Bullet points for lists Bold for key metrics Code blocks for tweet examples Clickable URLs for all referenced tweets (format: [@username](https://x.com/username/status/tweet_id)) Tweet URL Format Always include clickable links to tweets: | Author | Tweet | URL | |--------|-------|-----| | @user | Summary of tweet content | [View](https://x.com/user/status/123456) | Or inline format: - **@username**: Tweet summary - [View Tweet](https://x.com/username/status/123456) ### Trend Analysis "AI" OR "artificial intelligence" lang:en min_retweets:50 ### Competitor Monitoring from:competitor1 OR from:competitor2 since:2024-01-01 ### Product Launch Tracking #ProductName OR "Product Name" lang:en filter:verified ### Crisis Monitoring #BrandName OR "Brand Name" lang:en --query-type Latest ### Influencer Discovery #Topic lang:en min_retweets:100 min_faves:500 ### Sentiment Analysis "brand name" OR #BrandName lang:en --max-results 1000 ### scripts/run_search.sh (Wrapper Script) Convenience wrapper that handles environment variable loading and dependency checks: Automatically loads TWITTER_API_KEY from ~/.bashrc or ~/.zshrc Checks Python availability and installs missing dependencies Provides user-friendly error messages Supports all command-line options from the Python script Usage: ./scripts/run_search.sh [options] Options: --api-key KEY: Override environment variable API key --max-results N: Maximum tweets to fetch (default: 1000) --query-type Latest|Top: Sort order (default: Top) --format json|summary: Output format (default: json) ### scripts/twitter_search.py Executable Python script that: Fetches tweets from Twitter API Handles pagination automatically Extracts key tweet metrics Calculates aggregate statistics Outputs structured JSON data Usage: scripts/twitter_search.py [options] ### references/twitter_api.md Comprehensive API documentation including: Complete parameter reference Query syntax guide Response structure details Pagination instructions Best practices for analysis Error handling guide Read this when: Building complex queries or understanding data structure. ### Tips for Better Analysis Use Top query type for trend analysis (more relevant results) Set date filters for timely insights Filter by language for accurate text analysis Include minimum engagement to filter noise Combine with web search to validate trends Look beyond metrics - analyze content themes Track hashtags to identify sub-conversations Identify influencers by combining followers + engagement ### Error Handling If the script fails: Check API key validity Verify query syntax Ensure network connectivity Check rate limits (if applicable) Review error messages for specific issues ## Trust - Source: tencent - Verification: Indexed source record - Publisher: flyfoxCI - Version: 0.1.2 ## 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: 2026-05-10T08:00:13.063Z - Expires at: 2026-05-17T08:00:13.063Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/twitter-search-skill) - [Send to Agent page](https://openagent3.xyz/skills/twitter-search-skill/agent) - [JSON manifest](https://openagent3.xyz/skills/twitter-search-skill/agent.json) - [Markdown brief](https://openagent3.xyz/skills/twitter-search-skill/agent.md) - [Download page](https://openagent3.xyz/downloads/twitter-search-skill)