Skip to content
Development
Skill

/building-agent-systems

AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking,

From plugin
code-abyss
24530 skills

Claude Code

$ npx -y skills add telagod/code-abyss --skill building-agent-systems --agent claude-code

SKILL.md

building-agent-systems.SKILL.md
name: building-agent-systems
description: AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge). Use when building AI agents, designing RAG pipelines, orchestrating multi-agent workflows, hardening LLM apps, or writing prompts.
user-invocable: false

丹鼎秘典 · Agent / LLM 工程

> **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。

路由

| 意图 | 加载 | 核心 | |------|------|------| | 单 Agent 开发(工具调用、ReAct) | [agent-dev](references/agent-dev.md) | ReAct / Plan-Execute / Reflection | | 多 Agent 协同(>=3 文件 or >=2 并行) | [multi-agent-coordination](references/multi-agent-coordination.md) | 蚁群仿生、文件锁、依赖图 | | 多 Agent 协议细节(消息素、收阵报告) | [multi-agent-protocol](references/multi-agent-protocol.md) | Codex 原生协议、角色定义 | | LLM 安全(注入、越狱、输出过滤) | [llm-security](references/llm-security.md) | OWASP LLM Top 10 视角 | | RAG 系统(向量、检索、重排) | [rag-system](references/rag-system.md) | Chunking / 混合检索 / Cohere rerank | | Prompt + 评估 | [prompt-and-eval](references/prompt-and-eval.md) | Few-shot / CoT / RAGAS / LLM-as-Judge |

规模决策

单步任务(一文件、一查询)         → 直接执行(不需要 Agent 框架)
多步任务(计划 + 工具)             → 单 Agent (ReAct)
复杂任务(>5 步、需反思)           → 单 Agent (Plan-Execute / Reflection)
独立并行任务(>=3 文件、>=2 流)    → 多 Agent (TeamCreate)
跨域协作(角色明确)                → 多 Agent (角色分工)

**犹豫时优先 TeamCreate** — 串行降级容易,并行升级难。

通用原则

Prompt 即代码须版控 | 输入输出皆验证 | 成本效果平衡 | 持续评估迭代 | 安全边界明确

跨场景铁律

1. **Prompt 版控** — Prompt 是代码,必须 Git;变更要走 review 2. **I/O 验证** — 输入侧防注入,输出侧防 hallucination 落地(结构化 schema、引用追溯) 3. **评估前置** — 上线前必有 eval set;RAGAS / LLM-as-Judge 至少二选一 4. **成本观测** — token / latency / 失败率必埋点;预算阈值自动告警 5. **降级路径** — 多 Agent 失败 → 单 Agent;单 Agent 失败 → 直接回答 + 标记 `[unverified]`

多 Agent 启用判据

| 信号 | 启用 TeamCreate | |------|-----------------| | 涉及 ≥3 独立文件 | ✅ | | 需 ≥2 并行流 | ✅ | | 总步骤 >10 | ✅ | | 用户明确要求 | ✅ | | 单一探索任务 | ❌(用 explorer 或单 Agent) | | 单文件改动 | ❌(用 worker 或直接执行) | | 单步任务 | ❌(直接执行) |

详细生命周期、文件锁规则、依赖感知、过载保护、降级链:[multi-agent-coordination.md](references/multi-agent-coordination.md)

与其他 skill 联动

  • 涉及部署 → [provisioning-infrastructure](../provisioning-infrastructure/SKILL.md)(Vector DB、模型服务)
  • 涉及前端 → [applying-ui-design-system](../applying-ui-design-system/SKILL.md)(Chat UI / Agent 状态可视化)
  • 涉及安全审计 → [securing-systems](../securing-systems/SKILL.md)(LLM AppSec 子域)
  • 涉及评估自动化 → [automating-devops](../automating-devops/SKILL.md)(CI 中跑 eval)
Read more
@telagod
Ships withcode-abyss

Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec.

Stars on GitHub

Momentum

stars in total
245
Star history of telagod/code-abyss on GitHub, a chart by star-history.com

Other skills on code-abyss.

analyzing-changes

analyzing-changes

Analyzes code changes, detects documentation drift, and evaluates change impact scope. Use when reviewing diffs, checking doc…

@telagod@telagodInstall Skill
analyzing-security

analyzing-security

Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when…

@telagod@telagodInstall Skill
analyzing-spreadsheets

analyzing-spreadsheets

Processes Excel spreadsheet files (.xlsx, .xlsm, .csv). Creates workbooks, builds formulas, preserves formatting, analyzes…

@telagod@telagodInstall Skill
architecting-security

architecting-security

安全架构与治理:威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing…

@telagod@telagodInstall Skill
automating-devops

automating-devops

DevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml,…

@telagod@telagodInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about building-agent-systems.

Which coding agents can use building-agent-systems?
building-agent-systems installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.