atrislabs/atris/x-search
Claude Code and agent skill by atrislabs/atris
- community
Checking that the SKILL.md file is still in the repository.
X/Twitter search via xAI Grok API. Use when user wants to search tweets, monitor topics, find viral posts, or run social listening. Costs 5 credits per search. Triggers on x search, tweet search, twitter search, social listening, revenue intel, viral tweets.
Install
npx vskill@latest install atrislabs/atris/x-searchSKILL.md
X Search
Drop this in~/.claude/skills/x-search/SKILL.mdand Claude Code becomes your X/Twitter intelligence tool.
Feature map
Hard path. Follow in order. Soft memory does not override this.
- Login: stored login, then
atris login --agentif needed. Never paste tokens. Never/auth/cli. - Search:
atris x-search "QUERY". Always billed (5 credits). Prints to stdout. Rich ephemeral prints one apply next-step, one inferred check plusscore: 0, then onenext: atris youtube search "<query>"(person mode uses--name), and writes nothing. Thin ephemeral printscheck: fill thisthen that youtube-search next, and writes nothing. Empty successful pull (no tweets) prints onenext: atris youtube search " ". Explicit refund or failed search writes nothing extra. Empty, 502, 401, or 402 with unused credits print Credits when present and do not say refunded unless credits_refunded is explicit. A 401 that remints and retries prints those same credit lines from the first payload before the retry.--jsonstays quiet. --saveonly when you want a brief. Rich results (a number-with-units or a named mechanism) file the brief, mintatris/experiments/x-search-<slug>/, write one Apply that names that pack and the keep rule, and prove that fixture starts at score 0. Thin--saveprintsthin: no number or named mechanism. no brief.and writes nothing.--savedoes not print a youtube-search next-step.- Stop.
--json, explicit refund, or failed search does not print apply, check, score, or youtube-search next-step.
Customer path (preferred)
Logged-in customers should use the CLI. Same auth and billing as atris youtube process (5 credits).
Every cited post is looked up on X for free (the public embed endpoint, 5s cap), whatever layout the answer uses. A cited post whose words appear in the answer is checked: its https://x.com/<handle>/status/<id> (checked) link prints under that post, or in a Checked posts: list when the answer is a table or prose. A quote of 40+ characters that matches no real post says (could not find this post on X, treat as unverified); if X could not be reached it says so and is never called fake. Citations no post uses print as Other sources:. The last line is posts: N checked, N unverified, N unknown. --no-check skips the lookup. Bench it with atris x-search bench --free (0 credits) or --quick (5 credits).
Add --json for the raw API payload (plus a checks list). Curl below is the raw API for debugging only.
Bootstrap (ALWAYS Run First)
Before any X search operation, run this bootstrap to ensure everything is set up:
API Reference
Base: https://api.atris.ai/api/x-search
All requests require: -H "Authorization: Bearer $TOKEN"
Get Token (after bootstrap)
Search X/Twitter
With date filter (last N days only):
Response:
Research a Person
Response:
Workflows
"Search X for tweets about a topic"
- Prefer
atris x-search "<query>"(or bootstrap + curl if debugging the API) - Display results: tweet text, citations (x.com links), credits used/remaining
"Find tweets from the last week about X"
- Prefer
atris x-search "<query>" --days 7 --limit 10 - Display results and citations
"Research a person before a meeting"
- Prefer
atris x-search person --name "..." --handle ... --company ... --context "..." - Display profile, background, talking points
"Monitor keyword clusters for revenue intel"
- Run bootstrap
- Run multiple searches across keyword clusters:
"CRM is dead" OR "Salesforce is dead" OR "HubSpot sucks""revenue operations" (broken OR frustrated OR replacing)(founder OR CEO) "tech stack" (consolidating OR ripping out)
- Each search costs 5 credits
- Combine results, rank by engagement, draft replies
"Find viral tweets in my industry"
- Run bootstrap
- Search with engagement filter:
POST /x-search/searchwith query includingmin_faves:50 - Display top tweets sorted by likes/retweets
Query Tips
| Goal | Query Example | |
|---|---|---|
| Specific phrase | "revenue operations" | |
| OR logic | "CRM is dead" OR "Salesforce alternative" | |
| From a user | from:levelsio | |
| High engagement | "AI agents" min_faves:50 | |
| Exclude retweets | "your query" -is:retweet | |
| Multiple keywords | (founder OR CEO) ("AI adoption" OR "AI native") |
Billing
- Every search costs 5 credits (flat)
- 1 credit = $0.01, so 1 search = $0.05
- Research person also costs 5 credits
- Credits are deducted server-side before the search runs
- If insufficient credits, returns
402 Insufficient credits
Error Handling
| Error | Meaning | Solution | |
|---|---|---|---|
401 Not authenticated | Invalid/expired token | Run atris login | |
402 Insufficient credits | Not enough credits | Purchase credits at atris.ai | |
502 Search failed | xAI API issue | Retry in a few seconds |
Quick Reference
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingatris/skills/x-search/SKILL.md
Popularity
- Repository stars
- 58
- Repository forks
- 2
- Repository npm downloads, 7 days
- 256
- 7-day trend score
- 36
Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 20 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/atrislabs/atris/x-search)