Building Agent Systems is an AI Engineering skill for Claude Code, published by telagod in code-abyss.
Building Agent Systems covers single-agent and multi-agent patterns, RAG design, LLM security, and prompt evaluation. Use it when building AI agents, coordinating workflows, hardening LLM apps, or tuning prompts and retrieval.
Building Agent Systems is cataloged under AI Engineering on DirSkills. Building Agent Systems comes from a repository tagged agent-skills, ai-agent, ai-assistant, ai-personality and blue-team.
Documentation
判断先于执行：决定「是否做 / 选什么 / 如何取舍」（栈、方案、架构、权衡）前，先读领域判断内核
skills/_kernel/ml/SKILL.md——它管 judgment，本秘典管 execution；冲突时以内核判断为准。
单 Agent 是器，多 Agent 是阵。先选规模，再选模式。
This is the opening of the README. Read the full README on GitHub.
Building Agent Systems is one of 25 skills that DirSkills catalogs from telagod/code-abyss, the repository it ships in. Its siblings there include Adversarial Review Orchestration, Analyzing Changes and Analyzing Spreadsheets. Each one is a separate skill with its own page in this directory, installs the same way Building Agent Systems does, and is maintained by telagod in that same repository. The rest of the collection is listed on the telagod/code-abyss page.
Building Agent Systems ranks #2414 by stars among the 2793 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Building Agent Systems against them. Open each page to compare what they document and how they install.
Building Agent Systems is one of 25 skills cataloged on DirSkills from telagod/code-abyss.
Building Agent Systems is one of 2793 AI Engineering skills cataloged on DirSkills, ranked #2414 by stars among them.