Agent Building skills

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

david-silver

Applies the reasoning of David Silver, lead researcher on AlphaGo and AlphaZero at DeepMind, to problems of AI design, reinforcement learning, and open-ended discovery. Use this skill whenever you are designing AI systems, evaluating learning algorithms, balancing exploration vs. exploitation, choosing research problems, or discussing how to break past human performance ceilings. Reach for this whenever the user asks about self-play, Monte-Carlo Tree Search, tabula rasa learning, AGI, or moving from human-curated data to autonomous experience. It helps shift the focus from hardcoding human knowledge to building systems that learn for themselves.

230 repo starsObserved in 2 repos

Agent Building

GitHub

pieter-abbeel

Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Use this skill whenever you are designing AI systems, tackling Sim2Real transfer, deploying machine learning in the physical world, or evaluating reinforcement learning architectures. Trigger this skill for questions about domain randomization, reward design, bootstrapping real-world AI, robotics hardware assumptions, or shifting from hard-coded rules to data-driven deep learning. It helps ground theoretical AI in physical embodiment and pragmatic deployment.

230 repo starsObserved in 2 repos

Agent Building

GitHub

ai-agent-security

AI Agent 安全开发与防护最佳实践，包含prompt注入防护、代码执行安全、敏感信息保护、合规审计全流程规范。

230 repo starsObserved in 1 repos

Agent Building

GitHub

office-skill-authoring

Use when creating or reviewing Office AI Skills. Enforces SKILL.md directory structure, concise YAML metadata, progressive disclosure, references, scripts, app scope, and allowed tool boundaries.

230 repo starsObserved in 1 repos

Agent Building

GitHub

puppetmaster

Operate Puppetmaster multi-agent orchestrator via MCP verbs (edit, swarm, implement, route, monitor).

230 repo starsObserved in 1 repos

Agent Building

GitHub

skill-smith

Use when 需要创建新的 AI Agent 技能、改进已有 SKILL.md 文件、设计技能工作流或不确定技能该如何组织时。触发场景：创建技能、新建技能、写技能、技能开发、skill-smith、设计技能、编写SKILL.md、制作技能、开发skill、如何写一个好技能、技能质量不好怎么改进。

230 repo starsObserved in 1 repos

Agent Building

GitHub

beacon-agent

Beacon协议集成 - AI agent心跳、求救和资源合约系统

229 repo starsObserved in 1 repos

Agent Building

GitHub

hiveward-leader

Use when the agent is acting as a HiveWard Blueprint Leader role seat and needs to understand the bound blueprint, Manager nodes, Worker nodes, runs, errors, proposals, and approval boundaries.

229 repo starsObserved in 1 repos

Agent Building

GitHub

hiveward-skill-decomposer

Use when turning a skill package, standalone Markdown skill, SKILL.md, skill folder, or script-backed skill into a HiveWard blueprint proposal.

229 repo starsObserved in 1 repos

Agent Building

GitHub

recursive-improve

End-to-end agent improvement pipeline. Analyzes raw execution traces, extracts insights, manages a skillbook, gathers domain context, defines metrics, builds a rubric, creates a prioritized action plan, presents it for review, and implements approved fixes. Trigger when the user says "improve my agent", "run the improvement pipeline", "apply insights", "/recursive-improve", or when eval/traces/ contains trace files.

229 repo starsObserved in 1 repos

Agent Building

GitHub