by kangarooking · Agent Tool · ★ 191
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 | 191 |
| Forks | 41 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 58/100 |
| Last Updated | 2026-05-04 |
| Created | 2026-05-04 |
| Est. Tokens | ~6k |
System Prompt Skills 一套可直接使用的 Agent skill 工具包——从 165 个顶级 AI 产品系统提示词中，蒸馏出 15 个可复用的系统提示词设计模式。 它不是泄露提示词合集，也不是 prompt 模板库。原始提示词只是语料来源，本仓库保留的是可迁移的方法论：身份、人格、工具、安全、记忆、上下文、搜索、引用、输出、移动端、语音端和编程代理的系统级设计模式。 这套 skills 能解决什么问题 想设计一个稳定的 AI 产品 system prompt，但不知道从身份、工具、安全还是输出格式开始 想把 Chat 助手升级为 Agent，需要工具权限、任务路由、子代理和上下文管理 想降低 prompt injection、越权工具调用、记忆污染和引用不可审计等风险 想为移动端、语音端、代码代理、AI 搜索等不同场景设计专用提示词 想学习...
These tools work well together with system-prompt-skills for enhanced workflows:
Looking for a system-prompt-skills alternative? If you're comparing system-prompt-skills 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.
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Open-source Python, TypeScript, and Go SAST with dead code detection. Finds secrets, exploitable flows, and
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: