Tencent — 11 Open-Source AI Agent Skills
Tencent is the author of 11 open-source AI agent skills and MCP servers spanning agent-tool, mcp-server, claude-skill, codex-skill, with a combined 51,273+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 63/100) and security-graded — 11 verified safe.
Top skills by Tencent
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. (33.1k★ · quality 63/100 · security: safe)
- BrowserSkill — Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capab (10.2k★ · quality 67/100 · security: safe)
- AI-Infra-Guard — A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and (6.4k★ · quality 63/100 · security: safe)
- loli_profiler — Memory instrumentation tool with CI and AI support for android app&game developers. (696★ · quality 58/100 · security: safe)
- wave-mcp — Open-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with (249★ · quality 65/100 · security: safe)
- workrally — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。 (184★ · quality 48/100 · security: safe)
- SkillHone — Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every d (172★ · quality 65/100 · security: safe)
- tat-agent — TAT agent is an agent written in Rust, which run in CVM, Lighthouse or CPM 2.0 instances. Its role is to run commands remotely without ssh l (156★ · quality 68/100 · security: safe)
View Tencent on GitHub · Explore audited agent skills