[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75023":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":17,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":15,"starSnapshotCount":15,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},75023,"x-research-skill","rohunvora\u002Fx-research-skill","rohunvora","X\u002FTwitter research skill for Claude Code and OpenClaw. Agentic search, thread following, deep-dives, sourced briefings.",null,"TypeScript",1143,111,5,4,0,3,9,28,64.45,false,"main",true,[],"2026-06-12 04:01:17","# x-research\n\nX\u002FTwitter research agent for [Claude Code](https:\u002F\u002Fcode.claude.com) and [OpenClaw](https:\u002F\u002Fopenclaw.ai). Search, filter, monitor — all from the terminal.\n\n## What it does\n\nWraps the X API into a fast CLI so your AI agent (or you) can search tweets, pull threads, monitor accounts, and get sourced research without writing curl commands.\n\n- **Search** with engagement sorting, time filtering, noise removal\n- **Quick mode** for cheap, targeted lookups\n- **Watchlists** for monitoring accounts\n- **Cache** to avoid repeat API charges\n- **Cost transparency** — every search shows what it cost\n\n## Install\n\n### Claude Code\n```bash\n# From your project\nmkdir -p .claude\u002Fskills\ncd .claude\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Frohunvora\u002Fx-research-skill.git x-research\n```\n\n### OpenClaw\n```bash\n# From your workspace\nmkdir -p skills\ncd skills\ngit clone https:\u002F\u002Fgithub.com\u002Frohunvora\u002Fx-research-skill.git x-research\n```\n\n## Setup\n\n1. **X API Bearer Token** — Get one from the [X Developer Portal](https:\u002F\u002Fdeveloper.x.com)\n2. **Set the env var:**\n   ```bash\n   export X_BEARER_TOKEN=\"your-token-here\"\n   ```\n   Or save it to `~\u002F.config\u002Fenv\u002Fglobal.env`:\n   ```\n   X_BEARER_TOKEN=your-token-here\n   ```\n3. **Install Bun** (for CLI tooling): https:\u002F\u002Fbun.sh\n\n## Usage\n\n### Natural language (just talk to Claude)\n- \"What are people saying about Opus 4.6?\"\n- \"Search X for OpenClaw skills\"\n- \"What's CT saying about BNKR today?\"\n- \"Check what @frankdegods posted recently\"\n\n### CLI commands\n```bash\ncd skills\u002Fx-research\n\n# Search (sorted by likes, auto-filters retweets)\nbun run x-search.ts search \"your query\" --sort likes --limit 10\n\n# Profile — recent tweets from a user\nbun run x-search.ts profile username\n\n# Thread — full conversation\nbun run x-search.ts thread TWEET_ID\n\n# Single tweet\nbun run x-search.ts tweet TWEET_ID\n\n# Watchlist\nbun run x-search.ts watchlist add username \"optional note\"\nbun run x-search.ts watchlist check\n\n# Save research to file\nbun run x-search.ts search \"query\" --save --markdown\n```\n\n### Search options\n```\n--sort likes|impressions|retweets|recent   (default: likes)\n--since 1h|3h|12h|1d|7d     Time filter (default: last 7 days)\n--min-likes N              Filter minimum likes\n--min-impressions N        Filter minimum impressions\n--pages N                  Pages to fetch, 1-5 (default: 1, 100 tweets\u002Fpage)\n--limit N                  Results to display (default: 15)\n--quick                    Quick mode (see below)\n--from \u003Cusername>          Shorthand for from:username in query\n--quality                  Pre-filter low-engagement tweets (min_faves:10)\n--no-replies               Exclude replies\n--save                     Save to ~\u002Fclawd\u002Fdrafts\u002F\n--json                     Raw JSON output\n--markdown                 Markdown research doc\n```\n\n## Quick Mode\n\n`--quick` is designed for fast, cheap lookups when you just need a pulse check on a topic.\n\n**What it does:**\n- Forces single page (max 10 results) — reduces API reads\n- Auto-appends `-is:retweet -is:reply` noise filters (unless you explicitly used those operators)\n- Uses 1-hour cache TTL instead of the default 15 minutes\n- Shows cost summary after results\n\n**Examples:**\n```bash\n# Quick pulse check on a topic\nbun run x-search.ts search \"BNKR\" --quick\n\n# Quick check what someone is saying\nbun run x-search.ts search \"BNKR\" --from voidcider --quick\n\n# Quick quality-only results\nbun run x-search.ts search \"AI agents\" --quality --quick\n```\n\n**Why it's cheaper:**\n- Prevents multi-page fetches (biggest cost saver)\n- 1hr cache means repeat searches are free\n- Noise filters mean fewer junk results in your 100-tweet page\n- You see cost after every search — no surprises\n\n## `--from` Shorthand\n\nAdds `from:username` to your query without having to type the full operator syntax.\n\n```bash\n# These are equivalent:\nbun run x-search.ts search \"BNKR from:voidcider\"\nbun run x-search.ts search \"BNKR\" --from voidcider\n\n# Works with --quick and other flags\nbun run x-search.ts search \"AI\" --from frankdegods --quick --quality\n```\n\nIf your query already contains `from:`, the flag won't double-add it.\n\n## `--quality` Flag\n\nFilters out low-engagement tweets (≥10 likes required). Applied post-fetch since `min_faves` isn't available as an X API search operator.\n\n```bash\nbun run x-search.ts search \"crypto AI\" --quality\n```\n\n## Cost\n\nAs of February 2026, the X API uses **pay-per-use pricing** with prepaid credits. No subscriptions, no monthly caps. You buy credits in the [Developer Console](https:\u002F\u002Fconsole.x.com) and they're deducted per request.\n\n**Per-resource costs:**\n| Resource | Cost |\n|----------|------|\n| Post read | $0.005 |\n| User lookup | $0.010 |\n| Post create | $0.010 |\n\n**Search cost:** Each search page returns up to 100 posts = ~$0.50\u002Fpage.\n\n| Operation | Est. cost |\n|-----------|-----------|\n| Quick search (1 page, ≤100 posts) | ~$0.50 |\n| Standard search (1 page) | ~$0.50 |\n| Deep research (3 pages) | ~$1.50 |\n| Profile check (user + posts) | ~$0.51 |\n| Watchlist check (5 accounts) | ~$2.55 |\n| Cached repeat (any) | free |\n\n**24-hour deduplication:** If you request the same post twice in a UTC day, you're only charged once. This means repeat searches on the same topic within a day cost less than the estimate above.\n\n**Spending controls:** Set auto-recharge thresholds and spending limits per billing cycle in the Developer Console. Failed requests are never billed.\n\n**xAI credit bonus:** Spend $200+\u002Fcycle on X API → earn 10-20% back as xAI\u002FGrok API credits. See [pricing docs](https:\u002F\u002Fdocs.x.com\u002Fx-api\u002Fgetting-started\u002Fpricing).\n\n**How x-search saves money:**\n- Cache (15min default, 1hr in quick mode) — repeat queries are free\n- 24-hour dedup means re-running the same search costs $0 at API level too\n- Quick mode prevents accidental multi-page fetches\n- Cost displayed after every search so you know what you're spending\n- `--from` targets specific users instead of broad searches\n- Monitor your usage programmatically: `GET \u002F2\u002Fusage\u002Ftweets`\n\n## File structure\n\n```\nx-research\u002F\n├── SKILL.md              # Agent instructions (Claude reads this)\n├── x-search.ts           # CLI entry point\n├── lib\u002F\n│   ├── api.ts            # X API wrapper\n│   ├── cache.ts          # File-based cache\n│   └── format.ts         # Telegram + markdown formatters\n└── data\u002F\n    ├── watchlist.json    # Accounts to monitor\n    └── cache\u002F            # Auto-managed\n```\n\n## Security\n\n**Bearer token handling:** x-search reads your token from the `X_BEARER_TOKEN` env var or `~\u002F.config\u002Fenv\u002Fglobal.env`. The token is never printed to stdout, but be aware:\n\n- **AI coding agents** (Claude Code, Codex, etc.) may log tool calls — including HTTP headers — in session transcripts. If you're running x-search inside an agent session, your bearer token could appear in those logs.\n- **Recommendations:**\n  - Set `X_BEARER_TOKEN` as a system env var (not inline in commands)\n  - Review your agent's session log settings\n  - Use a token with minimal permissions (read-only)\n  - Rotate your token if you suspect exposure\n\n## Limitations\n\n- Search covers last 7 days only (uses `\u002F2\u002Ftweets\u002Fsearch\u002Frecent` — the full-archive `\u002F2\u002Ftweets\u002Fsearch\u002Fall` endpoint is available on the same pay-per-use plan but not yet implemented in this skill)\n- Read-only — never posts or interacts\n- Requires X API access with prepaid credits ([sign up](https:\u002F\u002Fconsole.x.com))\n- `min_likes` \u002F `min_retweets` search operators unavailable (filtered post-hoc instead)\n- Full-archive search (beyond 7 days) is available on pay-per-use (same credits). See [X API search docs](https:\u002F\u002Fdocs.x.com\u002Fx-api\u002Fposts\u002Fsearch\u002Fintroduction). This skill currently only uses recent search — full-archive support coming soon.\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=rohunvora\u002Fx-research-skill&type=Date)](https:\u002F\u002Fstar-history.com\u002F#rohunvora\u002Fx-research-skill&Date)\n\n## License\n\nMIT\n","x-research 是一个针对 Claude Code 和 OpenClaw 的 X\u002FTwitter 研究工具，通过命令行界面实现推文搜索、主题跟踪和账号监控。其核心功能包括基于用户参与度排序的搜索、时间过滤、噪声去除以及成本透明化显示等。此外，它还支持快速模式以降低API调用成本，并具备缓存机制避免重复计费。该技能适合需要从终端进行高效社交媒体分析的研究人员或开发者使用，无论是自然语言查询还是详细的CLI命令操作都能满足需求。",2,"2026-06-11 03:51:59","high_star"]