adk-agent-builder
tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill adk-agent-builderBuild 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.
Activation
17%This description suffers from placeholder text in its trigger guidance ('Use when appropriate context detected', 'Trigger with relevant phrases based on skill purpose') which renders it nearly useless for skill selection. While it names the specific technology (Google ADK), the lack of concrete actions and complete absence of real trigger terms means Claude cannot reliably choose this skill.
Suggestions
Replace the placeholder 'Use when appropriate context detected' with specific triggers like 'Use when user mentions Google ADK, Agent Development Kit, building AI agents with Google, or multi-agent systems'
Add concrete actions such as 'Create agent workflows, configure tool integrations, set up multi-agent communication, deploy ADK applications'
Include natural user phrases as triggers: 'ADK', 'Google agent framework', 'agent orchestration', 'build an 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 workflow'. | 2 / 3 |
Completeness | While the 'what' is partially addressed, the 'when' clause is completely non-functional: 'Use when appropriate context detected' and 'Trigger with relevant phrases based on skill purpose' are placeholder text that provide no actual guidance on when to use this skill. | 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 terms like 'AI agents', 'React patterns', and 'multi-agent orchestration' could overlap with other agent-building or React-related skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
42%This skill provides a reasonable high-level framework for ADK agent building but lacks the concrete, executable guidance that would make it immediately actionable. The structure and organization are good, but the absence of actual code examples, specific ADK API calls, or copy-paste ready commands significantly limits its practical utility.
Suggestions
Add executable Python code examples showing actual ADK imports, agent initialization, and tool registration (e.g., `from google.adk import Agent; agent = Agent(...)`)
Replace vague 'adk deploy ...' with actual deployment commands including required flags and parameters
Add a concrete validation checkpoint after scaffolding (e.g., 'Run `python -c "from src.agents import main_agent"` to verify imports')
Include a minimal but complete working agent example that can be copy-pasted and run locally
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is reasonably efficient but includes some unnecessary framing ('production-ready', 'repo-ready') and could be tighter. The overview section partially duplicates the instructions section. | 2 / 3 |
Actionability | Instructions are abstract and procedural without concrete code examples. No executable Python code, no actual ADK API calls, no copy-paste ready commands beyond vague 'adk deploy ...' references. | 1 / 3 |
Workflow Clarity | Steps are numbered and sequenced, but lack explicit validation checkpoints. The 'If deploying' conditional creates ambiguity, and there's no feedback loop for error recovery during scaffolding or deployment. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections and appropriate references to external resources (full guide, repo standards, ADK docs). Content is well-organized with one-level-deep references. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
81%| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 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.