X Social Handling
Manage posting, replying, and monitoring on X/Twitter via Hermes.
- License 许可
- MIT
- 所属仓库
- zapabob/Skills
- 最近更新
- 2026-10-26
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- X Social Handling
- tags
- social-media, twitter, x, automation
- author
- Hermes Agent
- license
- MIT
- version
- 0.1
- description
- Manage posting, replying, and monitoring on X/Twitter via Hermes.
03 SKILL.md 正文
This skill provides a structured approach for handling X/Twitter interactions, including mention monitoring, reply generation, tweet posting, and API change resilience. It incorporates best practices for credential safety, rate limiting, and fallback handling when platform endpoints evolve.
API Endpoint Resilience
- Monitor X/Twitter API health via
/lm-twitterer status; a 404 onCreateTweetindicates an endpoint shift. Treat posting as deferred until the endpoint is restored. - Implement exponential back‑off retry for mention‑reply loops, limited to 3 attempts per mention.
- Keep the whitelist lean; clear stale
replied_idsafter endpoint changes to avoid duplicate replies. - Document endpoint‑shift incidents in
references/x-social-handling/api-endpoint-shifts.mdfor future debugging.
Core Commands
/lm-twitterer status– show plugin health and configuration./lm-twitterer mentions [count]– list recent mention candidates without replying./lm-twitterer post [topic...] [--live]– generate and optionally publish a tweet./lm-twitterer reply [count]– generate replies for whitelisted mentions.
Safety Checks
- All credential material stays in
.env; never expose tokens in logs. - Use
dry_run=Trueby default; manual approval required for live posting. - Rate limit: max 3 replies per run; configurable via
config.yaml.
API Endpoint Resilience
- Monitor X/Twitter API health via
/lm-twitterer statusand thestatuscommand; treat 404 onCreateTweetas a known endpoint shift and defer posting until the endpoint is restored. - Implement exponential back‑off retry for mention‑reply loops, capped at 3 attempts per mention, to tolerate transient endpoint changes.
- Keep the whitelist lean; when X changes query IDs, clear stale
replied_idsto avoid duplicate‑reply attempts. - Log endpoint shift incidents in
references/x-social-handling/api-endpoint-shifts.mdfor future reference.
04 同仓库更多 Skills
xurl
X/Twitter via xurl CLI: post, search, DM, media, v2 API.
writing-plans
Write implementation plans: bite-sized tasks, paths, code.
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
watchers
Poll RSS, JSON APIs, and GitHub with watermark dedup.
serving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.