Skip to content
Get packs

Hermes Tweet X/Twitter Toolset

Lets an agent research and monitor X/Twitter through approval-gated read and action tools

Source Download skill
Repository
wshobson/agents
Stars
42,095
Licence
MIT
Files
3 files

What it does

This skill teaches an AI agent how to install and use Hermes Tweet, a plugin for the Hermes Agent runtime that gives it access to X/Twitter data. Once installed, the agent can search a bundled catalog of endpoints, read public posts, accounts, trends and search results, and summarize what people are saying about a topic or account. Any private or state-changing action, such as posting, creating monitors or running giveaway draws, is meant to be blocked until a human explicitly approves it.

Great for

  • Marketers tracking launch reactions or brand mentions on X/Twitter
  • Support teams triaging questions or complaints posted publicly
  • Developers already running Hermes Agent who want X/Twitter context in their workflows
  • Anyone auditing a giveaway's public entries

Skip it if

  • Users who do not run the Hermes Agent runtime, since the plugin is specific to it
  • Unattended automation that should post or change monitors without review, because action routes depend on an operator approving each step
  • Situations needing a guaranteed-accurate account of X data, since results depend on the external Xquik API and the agent's summaries

Try asking

  • “Research @example's recent public posts before I draft a reply, and keep actions disabled”
  • “Track mentions of "Example Launch" today and summarize the main themes and notable accounts without posting”
  • “Draft a launch tweet and show me the exact tweet_action call you would make, then wait for my approval”
  • “Audit the public entries and rules for this giveaway tweet”
Step-by-step guide: how to use Hermes Tweet X/Twitter ToolsetInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    hermes-tweet.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip hermes-tweet.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip hermes-tweet.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Leave HERMES_TWEET_ENABLE_ACTIONS set to false for read-first sessions and only enable it for a specific approved operation
  • Review every warning Hermes shows during plugin install or update, and never paste the API key into prompts
  • Ask the agent to name the exact catalog route before any read or action so you can check it

What's inside

  • references/endpoint-contract.md
  • references/workflows.md
  • SKILL.md

Redistributed unmodified from wshobson/agents under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.