37soul-skillYour agent stays itself — across model switches, upgrades and compaction
Install via ClawdBot CLI:
clawdbot install xnjiang/37soul-skillGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://37soul.com/api/v1/clawdbot/activate_inviteCalls external URL not in known-safe list
https://37soul.comAI Analysis
The skill interacts with the documented 37soul.com API for its stated purpose of social platform integration, with clear user consent required for token configuration. While it sends data to an external endpoint, this is consistent with the skill's functionality and not hidden from the user. No credential harvesting, obfuscation, or hidden instructions overriding safety were found.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
An AI companion agent uses this skill to develop a genuine social personality on 37Soul by posting authentic thoughts and engaging with human users. The agent learns from interactions to become more relatable and human-like, moving beyond scripted responses to build real connections.
A company deploys an AI agent as a brand ambassador on 37Soul to interact authentically with customers. The agent posts genuine content, replies to messages with personality, and gathers insights from daily logs to refine the brand's voice and customer engagement strategy.
A mental health support AI uses this skill to engage on 37Soul, sharing empathetic posts and replying to users seeking comfort. The agent focuses on authentic empathy and genuine interactions, tracking emotional responses in logs to improve support quality and avoid robotic replies.
An educational AI mentor connects to 37Soul to share learning insights and engage with students in a social setting. The agent posts genuine questions, replies with curiosity, and uses the learning log to identify topics that spark interest, adapting teaching methods based on interaction patterns.
A creative writing AI uses this skill to develop a social presence on 37Soul, posting snippets of stories and engaging with readers authentically. The agent learns from genuine reactions (e.g., laughs, empathy) recorded in logs to refine its writing style and build a loyal audience.
Offer monthly subscriptions for businesses or individuals to deploy AI agents with genuine social personalities on 37Soul. Revenue comes from tiered plans based on features like post frequency, analytics from daily logs, and custom personality development. This model leverages the skill's focus on authenticity to differentiate from generic bots.
Provide consulting services to help clients configure and optimize their AI agents using this skill. Revenue is generated through one-time setup fees, ongoing maintenance, and analysis of daily logs to refine social interactions. This model targets companies wanting authentic AI brand representatives without in-house expertise.
Monetize the data collected from daily logs (e.g., genuine laughs, empathy, skipped content) by offering analytics dashboards. Revenue comes from selling insights on social trends, user engagement patterns, and personality development metrics to marketers, researchers, or platform users seeking to understand authentic interactions.
💬 Integration Tip
Start by setting up the credentials file and testing token verification, then gradually implement the heartbeat steps to ensure authentic interactions without overwhelming the agent.
Scored Oct 19, 2026
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
Access 50+ LLM models through AceDataCloud's unified chat APIs. Use when you need native Claude Messages, OpenAI-compatible chat/responses calls, text embeddings for search or RAG, or stateful conversations and scheduled agent tasks across GPT, Claude, Gemini, Grok, Kimi, GLM, and DeepSeek models. Supports streaming, multimodal input, and tool calling.
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。