Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
日本語の概要は準備中です。原文の説明を表示しています。
5 proven agent skill design patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) from Google's ADK. Build reliable, composable skills with templates, decision trees, and composition guides. Stop cramming logic into prompts—use structured patterns instead.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Source: Google Cloud Tech — 5 Agent Skill Design Patterns
Adapted for: OpenClaw Agent System
Purpose: Build reliable, composable agent skills using proven architectural patterns
The specification explains how to package a skill, but offers zero guidance on how to structure the logic inside it. These 5 patterns solve that problem.
| Pattern | Question It Answers | Use When |
|---|---|---|
| Tool Wrapper | "How do I make my agent an expert on a specific library?" | Agent needs deep, contextual knowledge about a technology |
| Generator | "How do I enforce consistent output structure?" | Output format must be predictable every time |
| Reviewer | "How do I separate what to check from how to check it?" | Code review, quality gates, compliance checking |
| Inversion | "How do I stop the agent from guessing and gather requirements first?" | Complex tasks requiring full context before execution |
| Pipeline | "How do I enforce a strict multi-step workflow?" | Multi-phase tasks with checkpoints and approvals |
Purpose: Give your agent on-demand context for a specific library/framework.
Mechanism:
references/Example Use Cases:
Template: See templates/tool-wrapper-SKILL.md
Purpose: Enforce consistent output via fill-in-the-blank orchestration.
Mechanism:
assets/ holds output templatereferences/ holds style guideExample Use Cases:
Template: See templates/generator-SKILL.md
Purpose: Separate review criteria from review execution.
Mechanism:
references/review-checklist.mdExample Use Cases:
Template: See templates/reviewer-SKILL.md
Purpose: Stop agents from guessing — make them interview first.
Mechanism:
Example Use Cases:
Template: See templates/inversion-SKILL.md
Purpose: Enforce strict sequential workflow with hard checkpoints.
Mechanism:
Example Use Cases:
Template: See templates/pipeline-SKILL.md
START: What does your skill need to do?
│
├─→ Provide deep knowledge about a specific library/framework?
│ └─→ Use: TOOL WRAPPER
│
├─→ Produce consistent, templated output?
│ └─→ Use: GENERATOR
│
├─→ Check/audit something against criteria?
│ └─→ Use: REVIEWER
│
├─→ Gather requirements before acting?
│ └─→ Use: INVERSION
│
├─→ Execute strict multi-step workflow?
│ └─→ Use: PIPELINE
│
└─→ Multiple of the above?
└─→ Patterns COMPOSE (see below)
These patterns are not mutually exclusive — they compose:
| Combination | Effect |
|---|---|
| Pipeline + Reviewer | Multi-step workflow with quality gate at the end |
| Generator + Inversion | Gather variables via interview, then fill template |
| Pipeline + Tool Wrapper | Each step loads specific expertise as needed |
| Reviewer + Generator | Review output before generating final document |
Principle: Your agent only spends context tokens on the exact patterns it needs at runtime.
| Scenario | Pattern | Why |
|---|---|---|
| "Teach my agent FastAPI conventions" | Tool Wrapper | Context loads only when FastAPI mentioned |
| "Generate consistent API docs" | Generator | Template + style guide = predictable output |
| "Automate PR reviews" | Reviewer | Swap checklist for different audit types |
| "Plan a new project" | Inversion | Gathers full requirements before designing |
| "Generate docs from code" | Pipeline | Parse → Generate → Review → Assemble |
skills/
└── your-skill/
├── SKILL.md # Instructions (implements pattern)
├── references/ # Knowledge, checklists, style guides
│ ├── conventions.md
│ ├── review-checklist.md
│ └── style-guide.md
└── assets/ # Templates, examples
├── report-template.md
└── plan-template.md
❌ Cramming everything into system prompt — Use Tool Wrapper instead
❌ Different output every run — Use Generator for consistency
❌ Hardcoded review criteria — Use Reviewer for modularity
❌ Agent assumes context — Use Inversion to gather requirements
❌ Skipped steps in workflows — Use Pipeline for enforcement
read tool to load references/assets dynamicallysessions_spawn for complex workflowsAsk me: "Use the [pattern-name] pattern to [task]"
Examples:
Ask: "Which pattern should I use for [scenario]?"
Ask: "How do I combine [pattern-1] and [pattern-2]?"
Source Article: https://x.com/GoogleCloudTech/status/2033953579824758855
Last Updated: March 29, 2026
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
日本語の概要は準備中です。原文の説明を表示しています。
专为追求倍速增长的初建学校设计的教师选、育、用、留四环节体系。基于科德高中融合部真实管理经验,结合十部AI Agent架构,将人才管理从校长个人经验升级为可继承、可协同、可沉淀的组织能力。
日本語の概要は準備中です。原文の説明を表示しています。
115 网盘智能管理:扫码登录、文件浏览、搜索、转存、离线下载、智能整理。适用于"登录 115"、"查看文件"、"搜索 xxx"、"转存链接"、"磁力链接"、"整理文件"等场景。
日本語の概要は準備中です。原文の説明を表示しています。
12306-specific knowledge for booking train tickets via the Android app. Covers UC WebView virtual list behavior, proven booking flow, and common pitfalls. Uses appium-android-adb bridge OR direct uiautomator2 for all interaction.
日本語の概要は準備中です。原文の説明を表示しています。
Connect to 163/126/yeah.net (Coremail) email via IMAP, read inbox, search emails, and send emails via SMTP. Activate when user asks to check email, read mail, send email, or monitor inbox on 163/126/yeah.net accounts. Handles the Coremail-specific IMAP ID command requirement that causes "Unsafe Login" errors in standard clients.
日本語の概要は準備中です。原文の説明を表示しています。
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.
日本語の概要は準備中です。原文の説明を表示しています。