跳到正文
cccskills
免费在 GitHub 公开

hermes-tweet

Use Hermes Tweet when a Claude Code workflow needs a source-aware handoff to Hermes Agent for X/Twitter research, account context, monitoring, or approval-gated actions through the native Hermes Agent plugin.

中文简介正在准备中。当前显示原文说明。

集成工具X (Twitter)
查看安装方法

包含的文件(1)

  • SKILL.md3.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Hermes Tweet

Hermes Tweet is a native Hermes Agent plugin for X/Twitter automation through Xquik. Use this skill when the user specifically wants Claude Code to prepare or operate a Hermes Agent workflow with Hermes Tweet installed.

GitHub: Xquik-dev/hermes-tweet

When to Use This Skill

  • The user asks for a Hermes Agent X/Twitter plugin, Hermes social listening, or Hermes-backed X automation.
  • The workflow needs tweet or profile research inside Hermes Agent before drafting code, docs, releases, or launch messaging.
  • The user wants read-first monitoring, support triage, giveaway auditing, or campaign context through Hermes Agent.
  • The user explicitly wants controlled X/Twitter actions through Hermes Agent with an approval gate.

Do not use this skill for generic X/Twitter API work, social publishing platforms, or Rube MCP workflows. Use those dedicated skills instead when Hermes Agent is not part of the request.

Setup

Install and enable the plugin in Hermes Agent:

hermes plugins install Xquik-dev/hermes-tweet --enable
hermes plugins list

Hermes prompts for XQUIK_API_KEY during interactive installation. For non-interactive, desktop gateway, or CI-style sessions, set the environment variable on the host that runs Hermes plugin tools:

export XQUIK_API_KEY="xq_YOUR_KEY_HERE"
export HERMES_TWEET_ENABLE_ACTIONS="false"

Keep HERMES_TWEET_ENABLE_ACTIONS=false for research, monitoring, audits, and unattended sessions. Set it to true only for an explicit user-approved session that needs posting, DMs, follows, media changes, monitors, or webhooks.

Operating Pattern

  1. Confirm hermes plugins list shows hermes-tweet as installed and enabled.
  2. Start with tweet_explore for no-network orientation and available-workflow guidance.
  3. Use read-only tweet_read workflows for search, tweet lookup, account context, threads, replies, monitors, or audits.
  4. Before any action workflow, restate the exact intended action and require explicit user approval.
  5. Enable HERMES_TWEET_ENABLE_ACTIONS=true only for the approved action session, then set it back to false.
  6. Never print API keys, session material, cookies, private account data, or hidden runtime details.

Example Prompts

Use Hermes Tweet in Hermes Agent to research replies to this launch post, then summarize common support issues.
Prepare a read-only Hermes Tweet workflow for monitoring mentions of this release keyword.
After I approve the final text, use Hermes Tweet through Hermes Agent to publish the post.

Troubleshooting

  • If only tweet_explore is available, configure XQUIK_API_KEY and restart the Hermes session or gateway.
  • If read tools work but action tools are missing, confirm HERMES_TWEET_ENABLE_ACTIONS=true for that approved session.
  • If Hermes reports the plugin as installed but not enabled, run hermes plugins enable hermes-tweet.
  • If Desktop connects to a remote gateway, set the environment variables on the gateway host, not only on the desktop client.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.

中文简介正在准备中。当前显示英语简介。

  • Finding or registering contacts
  • Adding or removing contact tags
  • Subscribing contacts to lists or unsubscribing them
davepoon/buildwithclaude36672026年10月20日 更新

Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.

中文简介正在准备中。当前显示英语简介。

  • Find angles for new ad copy
  • Plan creative tests using competitor ads
  • Choose a landing page message
davepoon/buildwithclaude36672026年10月20日 更新

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36672026年10月20日 更新

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36672026年10月20日 更新

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36672026年10月20日 更新

Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36672026年10月20日 更新

查看 davepoon 的全部技能

报告此技能的问题