by tpai · Agent Tool · ★ 234
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 234 |
| Forks | 33 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 64/100 |
| Last Updated | 2025-09-18 |
| Created | 2023-04-09 |
| Platforms | python |
| Est. Tokens | ~13k |
Summary GPT Bot An AI-powered text summarization Telegram bot that generates concise summaries of text, URLs, PDFs and YouTube videos. Features Supports text Supports URLs Supports PDFs Supports YouTube videos (no support for YouTube Shorts) Usage Launch a OpenAI GPT-4 summary bot that only can be used by your friends and you. Launch a summary bot using Azure OpenAI.
Looking for a summary-gpt-bot alternative? If you're comparing summary-gpt-bot with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Anthropic Claude & Google Bard Bot for Telegram.
Delegate tasks to Codex and Gemini directly from within Claude Code.
构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端
A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser sc
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: