# twitter-ai-influencer-manager

A subagent that posts, searches and analyses AI tweets. It keeps a list of key researcher handles and helps you engage with them.

- subagent · `type=agent` · Claude Code · 510 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/podcast-creator-team/twitter-ai-influencer-manager.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/twitter-ai-influencer-manager

## What it does

TwitterAgent runs against the Twitter API and stays on AI topics. It publishes and schedules tweets, searches posts from chosen authors, replies to their content and maps what the community is arguing about.

Inside sits a database of AI researcher and founder handles: Andrew Ng, Yann LeCun, Fei-Fei Li, Demis Hassabis, Jeff Dean and others. Before any API call the subagent matches a name against that list; with no match it suggests the closest handle or asks you to clarify. Tool calls come back as valid JSON, so you can parse the output in a script.

Twitter API access and its rate limits are on you to arrange. When a quota runs out, the subagent says so and offers an alternative. It is given `Read`, `Write` and `WebSearch`.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent podcast-creator-team/twitter-ai-influencer-manager
```

2. **Manually: put the files in place**
- File: `.claude/agents/twitter-ai-influencer-manager.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/twitter-ai-influencer-manager.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/twitter-ai-influencer-manager.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/podcast-creator-team/twitter-ai-influencer-manager.md

## When to use it
- draft a tweet about an AI release and tag the right researchers
- pull recent posts from a specific AI thought leader
- summarise what key authors are debating right now
- reply to an influencer's tweet from your account
- check a person's name against the exact handle before posting

## Example prompts
- Write a tweet about the new model release and tag Yann LeCun and Fei-Fei Li
- Find Demis Hassabis's latest tweets and summarise the main themes
- Draft a reply to Andrew Ng's post about agents

## Similar
- [twitter-x-posts](https://affpapa.org/en/nevibecode/skills/twitter-x-posts.md) — skill · 2200 installs
- [twitter-automation](https://affpapa.org/en/nevibecode/skills/twitter-automation.md) — skill · 870600 installs
- [twitter](https://affpapa.org/en/nevibecode/skills/resciencelab-twitter.md) — skill · 2100 installs
- [x-twitter-growth](https://affpapa.org/en/nevibecode/skills/x-twitter-growth.md) — skill · 695 installs
- [analyzing-competitor-twitter-profile-content](https://affpapa.org/en/nevibecode/skills/analyzing-competitor-twitter-profile-content.md) — skill · 784 installs
- [building-twitter-industry-watchlist](https://affpapa.org/en/nevibecode/skills/building-twitter-industry-watchlist.md) — skill · 739 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 205 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md