Felo X Search logo

Felo X Search

Organization
Felo-Inc
felo-x-search

Search X (Twitter) data using Felo X Search API. Use when users ask about X/Twitter users, tweets, trending topics on X, tweet replies, or when explicit commands like /felo-x-search are used. Supports user lookup, user search, user tweets, tweet search, and tweet replies.

Overview

PublisherFelo-Inc
Repositoryfelo-skills
Skill namefelo-x-search
Stars
248
Forks
23
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Felo-Inc on GitHub. Read the source before you install it.

Installation

Install the Felo X Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Felo-Inc/felo-skills/tree/main/felo-x-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Felo-Inc/felo-skills.git /tmp/felo-skills
mkdir -p .claude/skills
cp -r /tmp/felo-skills/felo-x-search .claude/skills/felo-x-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Felo X Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Felo X Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Felo X Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Felo X Search Skill

When to Use

Trigger this skill when the user wants to:

  • Look up X (Twitter) user profiles by username
  • Search for X users by keyword
  • Get tweets from a specific X user
  • Search tweets by keyword or advanced query
  • Get replies to specific tweets

Trigger keywords (examples):

  • English: twitter, tweet, X user, X search, tweets from, replies to, trending on X
  • 简体中文: 推特, 推文, X用户, X搜索, 推文回复
  • 日本語: ツイッター, ツイート, Xユーザー, X検索

Explicit commands: /felo-x-search, "search X", "search twitter"

Do NOT use for:

  • General web search (use felo-search)
  • Webpage extraction (use felo-web-extract)
  • Generating slides (use felo-slides)

Setup

1. Get API key

  1. Visit felo.ai
  2. Open Settings -> API Keys
  3. Create and copy your API key

2. Configure environment variable

Linux/macOS:

bash
export FELO_API_KEY="your-api-key-here"

Windows PowerShell:

powershell
$env:FELO_API_KEY="your-api-key-here"

How to Execute

Option A: Use the bundled script or packaged CLI

Packaged CLI (after npm install -g felo-ai):

bash
felo x [query] [options]

Script (from repo):

bash
node felo-x-search/scripts/run_x_search.mjs [query] [options]

Usage Pattern

The x command uses parameter combinations to infer intent — no subcommands needed.

With query (search mode):

UsageBehavior
felo x "AI news"Search tweets (default)
felo x -q "AI news"Same as above
felo x "OpenAI" --userSearch users

With --id (lookup mode):

UsageBehavior
felo x --id "1234567890"Get tweet replies (default)
felo x --id "elonmusk" --userGet user info
felo x --id "elonmusk" --user --tweetsGet user tweets

Options

OptionDescription
[query]Positional arg, search keyword (equivalent to -q)
-q, --query <text>Search keyword
--id <values>Tweet IDs or usernames (comma-separated)
--userSwitch to user mode
--tweetsGet user tweets (with --id --user)
-l, --limit <n>Number of results
--cursor <str>Pagination cursor
--include-repliesInclude replies (with --tweets)
--query-type <type>Query type filter (tweet search)
--since-time <val>Start time filter
--until-time <val>End time filter
-j, --jsonOutput raw JSON
-t, --timeout <seconds>Timeout in seconds (default: 30)

Option B: Call API with curl

bash
# Search tweets
curl -X POST "https://openapi.felo.ai/v2/x/tweet/search" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "AI news", "limit": 20}'

# Search users
curl -X POST "https://openapi.felo.ai/v2/x/user/search" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "artificial intelligence"}'

# Get user info
curl -X POST "https://openapi.felo.ai/v2/x/user/info" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["elonmusk", "OpenAI"]}'

# Get user tweets
curl -X POST "https://openapi.felo.ai/v2/x/user/tweets" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"username": "elonmusk", "limit": 20}'

# Get tweet replies
curl -X POST "https://openapi.felo.ai/v2/x/tweet/replies" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"tweet_ids": ["1234567890"]}'

Output Format

User Info (default, non-JSON)

markdown
## @elonmusk (Elon Musk 🔵)
- User ID: `44196397`
- Followers: 100.0M
- Following: 500
- Total Tweets: 30.0K
- Bio: ...
- Location: Mars
- Account Created: 2009-06-02T00:00:00Z

---

Tweet (default, non-JSON)

markdown
### @elonmusk(Elon Musk ✓)
- Posted: 2026-03-09T12:00:00Z | Tweet ID: `1234567890`

Tweet content here...

Engagement: 5.0K likes | 1.0K retweets | 200 replies

---

Error Handling

Common Error Codes

  • INVALID_API_KEY — API Key is invalid or revoked
  • X_SEARCH_FAILED — X search request failed (check parameters or downstream error)

Missing API Key

If FELO_API_KEY is not set, display setup instructions and stop.

API Reference (summary)

  • Base URL: https://openapi.felo.ai. Override with FELO_API_BASE env if needed.
  • Auth: Authorization: Bearer YOUR_API_KEY
  • Endpoints:
    • POST /v2/x/user/info — Batch get user profiles
    • POST /v2/x/user/search — Search users
    • POST /v2/x/user/tweets — Get user tweets
    • POST /v2/x/tweet/search — Search tweets
    • POST /v2/x/tweet/replies — Get tweet replies

Important Notes

  • Always check FELO_API_KEY before calling; if missing, return setup instructions.
  • Format output as readable Markdown by default; use --json for raw API response.
  • Use pagination cursors (next_cursor) for fetching more results.
  • For tweet search, advanced query syntax is supported (same as X advanced search).

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Felo X Search AI skill do?

Search X (Twitter) data using Felo X Search API. Use when users ask about X/Twitter users, tweets, trending topics on X, tweet replies, or when explicit commands like /felo-x-search are used. Supports user lookup, user search, user tweets, tweet search, and tweet replies.

Why use Felo X Search on TypingMind?

Because you install it once and use it with any model. Felo X Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Felo X Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Felo-Inc/felo-skills/tree/main/felo-x-search. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Felo X Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Felo X Search?

As many as you like. As long as a model supports skills, you can use Felo X Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Felo X Search AI skill free?

It is published on GitHub by Felo-Inc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇