Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

community-skills

Complete guide to using and extending Community Skills — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure community skills, troubleshoot issues, spawn agent instances, or make code contributions.

117 repo starsObserved in 1 repos
Agent Building

community-subagent-driven-development

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

117 repo starsObserved in 1 repos
Agent Building

community-webhook-subscriptions

Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

117 repo starsObserved in 1 repos
Agent Building

conversation-flow

当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于:纯问答型系统(无任务执行)、单轮交互(无对话状态)、简单的 prompt 模板(无路由逻辑)。当需求仅涉及"输出什么格式"而非"如何决定输出什么"时,应该用 output-formatting 而非本 Skill。

117 repo starsObserved in 1 repos
Agent Building

create-skill-package

Create ArgentOS marketplace skill packages. Use when the user wants to build a new skill, plugin, or extension for the ArgentOS Marketplace. Guides through SKILL.md creation, packaging, and submission.

117 repo starsObserved in 1 repos
Agent Building

early-experience-data

Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test the pipeline", "set up a new env for early experience", or any work that produces expert / IWM / reflection SFT JSONL files. Do NOT trigger for model training, evaluation, or unrelated work.

117 repo starsObserved in 1 repos
Agent Building

injection-defense

当系统提示需要防御提示注入、越狱攻击、社会工程、内容信任边界突破等安全威胁时调用此 Skill。适用于构建 AI Agent、聊天机器人、文档处理助手等任何接受外部输入的系统提示。不适用于纯内部工具调用场景或已完全隔离的沙箱环境,也不适用于 UI 布局或响应格式设计。

117 repo starsObserved in 1 repos
Agent Building

memory-system

当需要为 AI 设计记忆存储、检索、应用和更新机制时调用此 skill。典型场景包括:设计持久化记忆架构(用户偏好、历史上下文、项目知识)、定义记忆的创建/读取/更新/删除生命周期、实现静默记忆应用(不在回复中透露记忆内容)、管理敏感记忆边界。 不适用于:定义工具接口(tool-specification)、定义安全规则(safety-guardrails)、定义人格风格(personality-system)。 关键 trigger 信号:AI 需要跨会话记住用户信息、记忆内容可能敏感、需要在回复中隐式应用记忆而非显式引用、用户要求"记住这个"。

117 repo starsObserved in 1 repos
Agent Building

mobile-adaptation

当系统提示面向移动端(手机、平板)场景时调用。适用于 iOS/Android 应用内 AI 助手、移动端聊天界面、响应式输出的系统提示设计。不适用于桌面端优先的场景,不适用于移动端 UI 开发(非提示层),不适用于语音场景(语音场景使用 voice-optimization)。

117 repo starsObserved in 1 repos
Agent Building

output-formatting

当系统提示词需要为 AI 输出定义格式规范、长度约束、风格指南或反"AI味"策略时调用此 Skill。适用于聊天机器人、CLI 工具、移动端助手、设计生成器等需要自适应输出的场景。不适用于:纯内容生成(无格式要求)、内部推理链设计、安全策略制定。当需求仅涉及"用什么格式返回数据"而非"如何控制输出的风格与密度"时,这不是最佳 Skill。

117 repo starsObserved in 1 repos
Agent Building