adk-agent-builder
Build production-ready AI agents using Google's Agent Development Kit with AI assistant integration, React patterns, multi-agent orchestration, and comprehensive tool libraries. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill adk-agent-builder51
Quality
37%
Does it follow best practices?
Impact
63%
1.31xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/jeremy-google-adk/skills/adk-agent-builder/SKILL.mdDiscovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description suffers from placeholder text that defeats the purpose of trigger guidance. While it identifies the technology domain (Google ADK) and lists some high-level capabilities, the 'Use when' and 'Trigger with' clauses are non-functional templates that provide no actual selection criteria. Claude would struggle to know when to choose this skill over others.
Suggestions
Replace 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' with explicit triggers like 'Use when user mentions Google ADK, Agent Development Kit, building AI agents with Google, or multi-agent systems.'
Add concrete actions instead of abstract concepts: 'Create agent workflows, configure tool integrations, orchestrate multi-agent pipelines, deploy ADK applications.'
Include natural user phrases: 'Google agent', 'ADK project', 'agent orchestration', 'agentic workflow', 'Google AI agent'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google's Agent Development Kit) and lists some capabilities (React patterns, multi-agent orchestration, tool libraries), but these are high-level concepts rather than concrete actions like 'create agent', 'configure tools', or 'deploy workflows'. | 2 / 3 |
Completeness | While it partially answers 'what' (building AI agents with ADK), the 'when' clause is completely non-functional: 'Use when appropriate context detected' and 'Trigger with relevant phrases' are meaningless placeholders that provide no actual guidance. | 1 / 3 |
Trigger Term Quality | The phrase 'Trigger with relevant phrases based on skill purpose' is a meta-placeholder that provides zero actual trigger terms. No natural keywords users would say like 'ADK', 'Google agent', 'build agent', or 'orchestration' are explicitly listed as triggers. | 1 / 3 |
Distinctiveness Conflict Risk | Mentions Google's Agent Development Kit specifically which provides some distinctiveness, but generic terms like 'AI agents', 'multi-agent orchestration', and 'tool libraries' could overlap with other agent-building or AI development skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid structural framework for ADK agent building with good organization and appropriate external references. However, it lacks the concrete, executable code examples that would make it immediately actionable—the examples section describes outcomes rather than showing actual code. The workflow is clear conceptually but missing explicit validation commands and feedback loops.
Suggestions
Add executable Python code snippets showing minimal ADK agent setup (e.g., `from google.adk import Agent; agent = Agent(...)`) rather than just describing the scaffold structure
Include actual CLI commands for scaffolding and deployment (e.g., `adk init my-agent`, `adk deploy --project=...`) instead of placeholders like `adk deploy ...`
Add explicit validation commands between workflow steps (e.g., `python -c 'from src.agents import MyAgent'` to verify imports, specific test commands)
Provide a concrete smoke test example with expected output rather than just mentioning 'smoke test prompt'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some redundancy (e.g., 'production-ready' appears multiple times, overview restates what's in instructions). Could be tightened by removing the overview section which largely duplicates the instructions. | 2 / 3 |
Actionability | Provides structured steps and clear scope but lacks executable code examples. The instructions describe what to do conceptually (scaffold, implement, deploy) but don't provide actual Python code, CLI commands, or copy-paste ready snippets for ADK agent creation. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced logically, but validation checkpoints are vague ('smoke test prompt', 'validation checklist') rather than explicit commands. Error handling section mentions retries but doesn't show how to implement them. Missing concrete validation commands between steps. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections and appropriate references to external resources (full guide in references, repo standards, ADK docs). Content is appropriately scoped for an overview skill file with one-level-deep references clearly signaled. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.