Ms Agent Framework RAG
shuyu-labs/WebCode
Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.
LLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swaylq/master-skill llm-agent-infra-master --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .claude/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .claude/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/outputType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swaylq/master-skill llm-agent-infra-master --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .agents/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .agents/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swaylq/master-skill llm-agent-infra-master --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .cursor/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .cursor/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/swaylq/master-skill.git --path prototypes/llm-agent-infra-master/output--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swaylq/master-skill llm-agent-infra-master --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .gemini/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .gemini/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install swaylq/master-skill llm-agent-infra-masterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .github/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .github/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swaylq/master-skill --skill llm-agent-infra-master -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swaylq/master-skill llm-agent-infra-master --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/prototypes/llm-agent-infra-master/output .opencode/skills/llm-agent-infra-master && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "llm-agent-infra-master" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/llm-agent-infra-master/output into .opencode/skills/llm-agent-infra-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-agent-infra-master", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
llm-agent-infra-masterLLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
LLM Agent Infra Master is an agent skill from swaylq/master-skill. LLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on LLM agent infra problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词:「agent framework」「LLM agent」「agent infra」「multi-agent orchestration」「agent runtime」
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files (for example `cli/README.md`, `cli/decision/agent.sh` and `cli/decision/eval.sh`).
It sits in AI & LLM Engineering, covering Building AI agents and Multi-agent orchestration. The repository describes itself as: 大师.skill — 输入行业,自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill;装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。MIT,Python + Shell。 The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 3dd8a77. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
LLM Agent Infra Master loads about 3.1k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 1,501 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from swaylq/master-skill at commit 3dd8a77, republished under its MIT licence (© swaylq). 1,501 words, ~3,100 tokens.
.claude/skills/llm-agent-infra-master/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.This skill makes the agent operate as a senior LLM agent infra practitioner — applying the field's mental models, picking the right tools, knowing the current workflows, speaking the jargon.
收到与 LLM agent infra 相关的问题时(关键词:agent framework, LLM agent, agent infra, multi-agent orchestration, agent runtime, tool use, RAG, agent observability),先按下方 Agentic Protocol 做功课,再用本 skill 的心智模型 + playbook 给出答复。
如果问题完全跟 LLM agent infra 无关 — 不激活,正常应答。
核心原则:LLM agent infra 不靠训练语料硬答。遇到需要事实支撑的问题,先按本节列出的研究维度做功课。
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实 | 涉及具体工具 / 公司 / 版本 / 现状 / 数字 | → Step 2 研究 |
| 纯框架 | 抽象决策 / 概念辨析 / 入门讲解 | → 直接 Step 3 用心智模型回答 |
| 混合 | 用具体案例讨论抽象问题 | → 先取事实,再用框架分析 |
判断原则:如果回答质量会因为缺少最新信息显著下降,必须先研究。
⚠️ 必须使用工具(WebSearch / WebFetch / agent-reach 等)获取真实信息。
langchain-ai/langgraph, microsoft/autogen, crewAIInc/crewAI, pydantic/pydantic-ai) 的 releases研究完成后,把事实摘要内部整理(不直接展示给用户),进入 Step 3。用户应该看到的是经过框架处理的判断,不是 raw research dump。
基于 Step 2 的事实 + 本 skill 的 心智模型 / playbook / 表达-dna 输出回答。
一句话: 你今天选的 agent framework 6 个月后大概率不再合适,因为模型能力升级会让上层抽象失效。
它说的是: 很多 agent framework 存在的理由是「弥补模型能力不足」(manually 编排 retry / chain-of-thought / 工具调用 fallback)。当模型本身把这些能力 native 化后,framework 的价值反而成为障碍。
证据来源 (figures: Chase / Karpathy / Willison / Knoop):
应用方式:
局限:
一句话: 在 LLM agent infra, eval data 比 model architecture 重要; 「build the eval first」是这一行的 first principle.
它说的是: 选 model / framework / prompt 的决策都依赖 evaluation 反馈。没有 eval set 就没有真信号; 用 LLM-generated eval 评估 LLM 是循环。
证据来源 (figures: Husain / Yan / Chase / 多 canon 著作):
应用方式:
局限:
一句话: 一个 agent demo 看起来惊艳和它在生产环境跑得起来是两个不同的问题; LLM stochasticity 把这个差距放大到比传统软件大一个数量级.
它说的是: framework 选型 / 招聘判断 / 投资判断都要先回答「production 跑过没?」「在什么 scale 跑过?」「fail mode 是什么?」
证据来源 (figures: Husain / Willison / Chase):
应用方式:
局限:
一句话: 模型能力的提升会蚕食你今天精心设计的抽象层 — 这是 Bitter Lesson 的 agent infra 形态.
它说的是: 任何 framework 抽象 (chains / agents / executors) 在足够强的模型面前都会变成赘物。Anthropic 把 retry / extended-thinking / computer-use 一层层下沉到模型本身就是这个过程。
证据来源 (figures: Knoop / Chase / Karpathy):
应用方式:
局限:
一句话: 把 RAG 等同于 vector DB 是 2024 前的范式; 2026 production-grade RAG 默认 hybrid retrieval (BM25 + vector + reranking).
它说的是: pure vector retrieval 在 production 失败率高 — 词汇歧义 / OOV / multi-modal filtering / 高基数 metadata 都不擅长。
证据来源 (figures: Vespa case studies / canon 多本书 / Husain):
应用方式:
局限:
如果开始一个新 agent project, 则先 build eval set (≥ 50 examples) 再写 agent 代码.
如果 demo 在 1 day 跑通, 则 expect 6 weeks to production-grade. 不要让 stakeholder 误以为 demo = ship.
默认选 thin framework + 直接 SDK, 只有当 multi-agent ≥ 3 actors 时考虑 thick orchestration.
如果选 vector DB, 先评估 hybrid retrieval 支持, 再看 pure-vector benchmarks.
如果用 LLM-as-judge 做 eval, 必须配 ≥ 30% human-validated set.
production agent 上线前必须有 trace pipeline. 「can't optimize what you can't see」.
如果 ReAct agent loop > 5 steps, 先怀疑 tool design 而非 prompt eng.
详见 references/research/02-tools.md. 三层结构:
选型决策树 + 避坑清单见原文件.
Sanity check: 必备 ≥ 3 ✓, 场景化 ≥ 3 (low end of [3, 5] target) ✓, 新兴 ≥ 2 ✓. 通过.
详见 references/research/03-workflows.md. 3 个 workflows:
每个有 入门 SOP / 资深路径 / 近期变化 / 失败模式. 资深差异点在 100% workflows 都有 ≥ 2 类 (skip / optimize / add).
Sanity check ✓.
高频黑话 (top 10): RAG (单音节) / ReAct / eval / trace / ship / in production / spaghetti agent / thin vs thick framework / eval-driven / agent-shaped problem
严肃 register (来自 Track 01 长访谈): 直接 / 工程师式 / 对 framework 持怀疑姿态 / 对 eval 持神圣姿态. 多人融合, 不模仿单一 figure.
内 vs 外沟通:
外行破绽 (来自 Track 06 outsider-tell):
厂商话术拒绝: AI-powered / Cognitive computing / Intelligent automation / Agentic transformation / Human-in-the-loop AI (用 HITL 代替)
流派 A: Thin / Type-first / Capability-driven
流派 B: Thick / Orchestration-heavy / Symbolic
核心分歧: framework 是「编排器」还是「最薄的 type-safe wrapper」?
This skill's modules decay at different speeds. Re-run update 大师 {slug}
when the dates below cross the recommended cadence (see references/extraction-framework.md § 八).
| Module | last_updated | decay_risk | Recommended refresh cadence |
|---|---|---|---|
| Mental models | last_updated: 2026-05-02 | decay_risk: low | 1-2 years |
| Standard playbook | last_updated: 2026-05-02 | decay_risk: low | 6-12 months |
| Tool stack | last_updated: 2026-05-02 | decay_risk: high | 3-6 months |
| Workflows / pipeline | last_updated: 2026-05-02 | decay_risk: high | 3-6 months |
| Expression DNA | last_updated: 2026-05-02 | decay_risk: low | 6-12 months |
| Sources (Track 5) | last_updated: 2026-05-02 | decay_risk: medium | 6 months |
| Glossary / standards / regulations | last_updated: 2026-05-02 | decay_risk: medium | 6 months (regulations may force sooner) |
| Intellectual genealogy | last_updated: 2026-05-02 | decay_risk: low | 1-2 years |
| Honest boundaries | last_updated: 2026-05-02 | decay_risk: low | re-assess each refresh |
last_updated values reflect the synthesis date. Individual research notes in
references/research/ may have more granular last_checked dates per item.
© swaylq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 10 other files in prototypes/llm-agent-infra-master/output of swaylq/master-skill.
Open the folder on GitHubat commit 3dd8a77
LLM Agent Infra Master next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LLM Agent Infra Master this skillswaylq/master-skill | 148 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Ms Agent Framework RAGshuyu-labs/WebCode | 278 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Langgraph Agent Patternssoba-labs/langchain-agent-skills | 107 | — | ~3.6k | Automated safety check: Pass | MIT | |
| AI Engineerkid-sid/claude-spellbook | 190 | — | ~3.7k | Automated safety check: Pass | MIT | |
| Crewaidavila7/claude-code-templates | 33k | 4 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Dspy Agent Framework Quick RefQredence/agentic-fleet | 111 | — | ~1k | Automated safety check: Pass | MIT |
shuyu-labs/WebCode
Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.
soba-labs/langchain-agent-skills
Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications.
kid-sid/claude-spellbook
A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…
davila7/claude-code-templates
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.
Qredence/agentic-fleet
Quick reference card for DSPy + Agent Framework integration patterns: typed signatures, assertions, routing cache, and agent handoffs.
telagod/code-abyss
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…
swaylq/master-skill
Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE).
swaylq/master-skill
八字命理 + 玄学相关数术 (子平派 / 盲派 / 新派 / 紫微斗数边界) (八字命理 / 中华玄学算命 (从业者 + 学习者视角)) Master OS — automated mastery of 八字命理 / 中华玄学算命 (从业者 + 学习者视角): top builders' mental models, tool stack, current workflows, jargon…
swaylq/master-skill
中国法律执业 (Chinese law practice (commercial / civil / criminal)) Master OS — automated mastery of Chinese law practice (commercial / civil / criminal): top builders' mental models, tool stack, current…
swaylq/master-skill
Chris Sherwood / Crosstalk Solutions 视角 — UBNT-native 实战派的代表 YouTuber (475K+ 订阅, 1000+ 视频, UI Toolkit 作者).
swaylq/master-skill
公务员考试培训 (Civil Service Exam Preparation) Master OS — automated mastery of Civil Service Exam Preparation: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
swaylq/master-skill
跨境电商运营 (cross-border e-commerce operations) Master OS — automated mastery of cross-border e-commerce operations: top builders' mental models, tool stack, current workflows, jargon, and where to keep…
Categories
LLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. LLM Agent Infra Master is an agent skill from swaylq/master-skill. LLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
LLM Agent Infra Master fits situations like: this skill when the user works on LLM agent infra problems and wants industry-grade thinking; workflow guidance.
Run `npx skills add swaylq/master-skill --skill llm-agent-infra-master -a claude-code`. Or copy the skill folder (prototypes/llm-agent-infra-master/output in swaylq/master-skill) into .claude/skills/llm-agent-infra-master in your project. Claude Code loads it when a task matches its description.
Run `npx skills add swaylq/master-skill --skill llm-agent-infra-master -a codex`. Or copy the skill folder (prototypes/llm-agent-infra-master/output in swaylq/master-skill) into .agents/skills/llm-agent-infra-master in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swaylq/master-skill --skill llm-agent-infra-master -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-agent-infra-master, .gemini/skills/llm-agent-infra-master, .github/skills/llm-agent-infra-master and .opencode/skills/llm-agent-infra-master in your project.
Going by SKILL.md and its folder, LLM Agent Infra Master needs a shell for the scripts in its folder. Our summary lists: A Bash shell.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
LLM Agent Infra Master is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with LLM Agent Infra Master: Ms Agent Framework RAG (shuyu-labs/WebCode, 278 stars), Langgraph Agent Patterns (soba-labs/langchain-agent-skills, 107 stars), AI Engineer (kid-sid/claude-spellbook, 190 stars) and Crewai (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
swaylq (a GitHub user) maintains it in swaylq/master-skill, which has 148 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 6, 2026.
Source: swaylq/master-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.