--- title: "Five Agent Skill Design Patterns for ADK | TauX" description: "Tool Wrapper, Generator, Reviewer, Inversion and Pipeline — the five patterns from Google Cloud Tech, and what problem each one is actually solving." url: "https://taux.io/en-US/adk-skill-patterns" locale: "en-US" alternates: ja-JP: "https://taux.io/ja-JP/adk-skill-patterns" ko-KR: "https://taux.io/ko-KR/adk-skill-patterns" zh-Hans-CN: "https://taux.io/zh-Hans-CN/adk-skill-patterns" zh-Hant-TW: "https://taux.io/zh-Hant-TW/adk-skill-patterns" --- # Five Skill Patterns Drawn from Google Cloud's "5 Agent Skill Design Patterns Every ADK Developer Should Know" ### Why patterns at all? It is easy to assume that getting the YAML in `SKILL.md` right is the job. That part is only the shell. The real work is **designing what goes inside**: how do you stop an agent skipping steps, guessing, or returning something shaped differently every time? These five patterns are the answer to that. 01 ## The five at a glance | # | Pattern | In one line | Use it for | | -- | ------------ | ------------------------------------------------ | -------------------------------------------- | | 01 | Tool Wrapper | Load the expert knowledge only when it is needed | Working with a specific framework or library | | 02 | Generator | A template guarantees the shape of the output | Reports, documentation, API docs | | 03 | Reviewer | A checklist stands between the work and done | Code review, security audits | | 04 | Inversion | Ask enough questions before starting | Tasks where the requirement is still vague | | 05 | Pipeline | A strict multi-step pipeline | Deployments, approvals, complex workflows | 02 — Tool wrapper ## Tool Wrapper Domain expertise, loaded on demand ### The problem Put every framework document — FastAPI conventions, React rules, the SQL style guide — into the system prompt and you pay for all of it on every turn, while the model's attention spreads across things this task does not need. ### The pattern In `SKILL.md` declare a trigger. When the agent notices the user mention a framework, it pulls the matching conventions from `references/` at that moment, and not before. SKILL.md → Tool Wrapper pattern ``` # trigger when: user mentions "FastAPI" or "API endpoint" load: references/fastapi-conventions.md # behaviour then: develop against the conventions just loaded tokens spent only when relevant ``` Why it works The context window stays clean. Specialist knowledge arrives when it is relevant, so nothing irrelevant is competing for the model's attention. 03 — Generator ## Generator A template for consistent output ### The problem Ask a model to write a report freehand and the shape changes every time — a table of contents on Tuesday, none on Wednesday; three sections once, thirty the next. ### The pattern Write the template up front (in `assets/`) and have the agent fill it in rather than construct a document from nothing. assets/report-template.md ``` # {{title}} ## Executive Summary {{summary: two or three sentences}} ## Key Findings {{findings: bulleted, three to five}} ## Risk Assessment | Risk | Severity | Action | |---|---|---| {{risks: fill the table}} ## Next Steps {{actions: in priority order}} ``` Why it works Format and content come apart. The model spends its effort on what is worth saying; the template guarantees the shape. 04 — Reviewer ## Reviewer A checklist stands between the work and done ### The problem What comes back looks right and has a hole in it — an unhandled edge case, a missing security check, a team convention nobody wrote down. ### The pattern A separate reviewer skill that loads its own checklist from `references/`, verifies against it item by item, and reports findings grouped by severity. Critical Security holes, data exposure Warning Performance, maintainability Info Style, best practice Why it works Checking is separated from producing. One agent does the work, another inspects it — the same reason code review is not done by the author. 05 — Inversion ## Inversion Ask before you build ### The problem "Build me a website" arrives, and the agent starts writing React. What comes out bears little relation to what was wanted, because the default instinct is to act rather than to find out. ### The pattern **Invert the behaviour**: make it an interviewer before it is an implementer. Non-negotiable gates: no work starts until every parameter it needs has been collected. Inversion, step by step ``` ✕ Default agent User: "build me a website" Agent -> starts a React project... ✓ Inversion User: "build me a website" Agent → Phase 1: interview "What kind of site is this?" "Who is it for?" "Is there a design to work from?" → Phase 2: confirm "Here is what I have. Is this right?" → Phase 3: build start development ``` Why it works Asking first is what stops the model filling gaps with invention. The more complete the context, the less there is to invent. 06 — Pipeline ## Pipeline A strict multi-step pipeline ### The problem A complex task has stages, and a model will skip one, merge two, or lose the important middle step — most often when the context is already long. ### The pattern Design the skill as a **strict pipeline**: named phases, with a gate between each. The agent finishes the current phase and gets a human confirmation before the next one opens. Phase 1 Research → Gate → Phase 2 Plan → Gate → Phase 3 Execute → Done Verify Why it works Unpredictable text generation becomes a state machine — controllable, repeatable, and auditable after the fact. 07 ## Three things to hold on to #### Progressive disclosure ADK's SkillToolset loads instructions and context at the moment they are needed — cheaper, and more focused. #### Format apart from content `SKILL.md` gives you a standard shell; these patterns are what decides how the agent thinks and acts inside it. #### They compose Mix them. Put a reviewer at the end of a pipeline; put inversion in front of a generator to collect its parameters first. 08 ### Further reading [Prompting guide →](https://taux.io/en-US/agent-prompting-guide) [Claude Skills guide →](https://taux.io/en-US/claude-skills-guide) [The GEO guide →](https://taux.io/en-US/geo-guide)