Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
X/Twitter research skill powered by TwitterAPI.io. Agentic search, profile analysis, thread reading, watchlists, and sourced briefings. Use when asked to sea...
X/Twitter research skill powered by TwitterAPI.io. Agentic search, profile analysis, thread reading, watchlists, and sourced briefings. Use when asked to sea...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
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.
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.
General-purpose X/Twitter research agent powered by TwitterAPI.io. Search, filter, monitor โ all from the terminal. No X Developer Portal account needed. For API details: read references/twitterapi-io.md.
X API OfficialTwitterAPI.ioCost$100+/mo (Basic plan)~$0.15/1k tweets (pay-per-use)SetupDeveloper Portal applicationJust an API keyRate limit10 req/15min200 QPSArchive7 days (recent)Full archive
Get a TwitterAPI.io key from twitterapi.io Set the env var: export TWITTERAPI_KEY="your-key-here" Or add to your .env file. Node.js 18+ required (for native fetch). No npm install needed โ zero dependencies.
All commands run from the scripts directory: cd <skill-dir>/scripts
npx tsx x-search.ts search "<query>" [options] Options: --sort likes|retweets|impressions|recent โ sort order (default: likes) --since 1h|3h|12h|1d|7d โ time filter --min-likes N โ filter minimum likes --min-impressions N โ filter minimum views --pages N โ pages to fetch, 1-5 (default: 1) --limit N โ max results to display (default: 15) --quick โ fast mode: 1 page, max 10 results, noise filter, 1hr cache --from <username> โ shorthand for from:username in query --quality โ filter low-engagement tweets (โฅ10 likes) --no-replies โ exclude replies --save โ save results to file --type Top|Latest โ search mode (default: Latest; Top returns algorithmic ranking) --json โ raw JSON output --markdown โ markdown formatted output Auto-adds -is:retweet unless query already includes it. Cost estimate shown after each search. Examples: npx tsx x-search.ts search "AI agents Base chain" --sort likes --limit 10 npx tsx x-search.ts search "BNKR" --quick npx tsx x-search.ts search "from:frankdegods" --sort recent npx tsx x-search.ts search "(opus OR claude) trading" --pages 2 --save npx tsx x-search.ts search "$SOL memecoin" --min-likes 50 --since 1d Search operators (passed through to X): OperatorExampleNoteskeywordbun 2.0Implicit ANDORbun OR denoMust be uppercase--is:retweetNegation()(fast OR perf)Groupingfrom:from:elonmuskPosts by userto:to:elonmuskReplies to user##buildinpublicHashtag$$AAPLCashtaglang:lang:enLanguage filteris:retweet-is:retweetFilter retweetsis:reply-is:replyFilter replieshas:mediahas:mediaContains mediahas:linkshas:linksContains linksmin_faves:min_faves:100Min likes (native)
npx tsx x-search.ts profile <username> [--count N] [--replies] [--json] Fetches user info and recent tweets. Excludes replies by default.
npx tsx x-search.ts tweet <tweet_id> [--json]
npx tsx x-search.ts thread <tweet_id> Fetches root tweet, author thread continuations, and replies in chronological order.
npx tsx x-search.ts replies <tweet_id> [--sort likes|recent] [--limit N] Get replies to a specific tweet, sorted by engagement.
npx tsx x-search.ts quotes <tweet_id> [--sort likes|recent] [--limit N] See who quoted a tweet and what they said.
npx tsx x-search.ts mentions <username> [--since 1d|7d] [--sort recent|likes] [--limit N] Get tweets that mention a user. Great for tracking what people are saying about someone.
npx tsx x-search.ts followers <username> [--limit N] npx tsx x-search.ts following <username> [--limit N] List a user's followers or who they follow. Shows name, follower count, and bio snippet.
npx tsx x-search.ts users "<query>" [--limit N] Search for user accounts by keyword.
npx tsx x-search.ts trending [--woeid N] [--count N] Get trending topics. Default: worldwide (woeid=1). Common WOEIDs: US=23424977, UK=23424975, Italy=23424853.
npx tsx x-search.ts community <id> # Community info npx tsx x-search.ts community tweets <id> # Community tweets Research X Communities by ID.
npx tsx x-search.ts watchlist # Show all npx tsx x-search.ts watchlist add <user> [note] # Add account npx tsx x-search.ts watchlist remove <user> # Remove account npx tsx x-search.ts watchlist check # Check recent from all Watchlist stored in data/watchlist.json. Use for periodic monitoring โ check if key accounts posted anything notable.
npx tsx x-search.ts cache clear # Clear all cached results Default 15-minute TTL. Quick mode uses 1-hour TTL. Avoids repeat API charges.
When doing deep research (not just a quick search), follow this loop:
Turn the research question into 3-5 keyword queries: Core query: Direct keywords for the topic Expert voices: from: specific known experts Pain points: Keywords like (broken OR bug OR issue) Positive signal: Keywords like (shipped OR love OR fast) Links: has:links for resource-rich tweets Crypto spam: Add -airdrop -giveaway -whitelist if needed
Run each query via CLI. After each, assess: Signal or noise? Adjust operators. Key voices worth searching from: specifically? Threads worth following via thread command?
When a tweet has high engagement or is a thread starter: npx tsx x-search.ts thread <tweet_id>
Use --save flag or --markdown for research docs.
Too much noise? Add --no-replies, use --sort likes, narrow keywords Too few results? Broaden with OR, remove restrictive operators Crypto spam? Add -airdrop -giveaway -whitelist to query Expert takes only? Use from: or --min-likes 50 Substance over hot takes? Search with has:links
On heartbeat, run watchlist check to see if key accounts posted anything notable. Flag only if genuinely interesting/actionable.
TwitterAPI.io pay-per-use pricing: ~$0.15 per 1,000 tweets fetched ~$0.18 per profile lookup Cost estimate shown after each command Cache prevents redundant charges
skills/x-research/ โโโ SKILL.md # This file โโโ package.json # Zero dependencies โโโ scripts/ โ โโโ x-search.ts # CLI entry point โ โโโ lib/ โ โโโ api.ts # TwitterAPI.io wrapper โ โโโ cache.ts # File-based cache (15min/1hr TTL) โ โโโ format.ts # Terminal + markdown formatters โโโ data/ โ โโโ watchlist.json # Accounts to monitor โ โโโ cache/ # Auto-managed โโโ references/ โโโ twitterapi-io.md # API endpoint reference
Node.js 18+ (for native fetch) A TwitterAPI.io API key No npm install needed โ zero dependencies
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.