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.

Quality

29%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/jeremy-google-adk/skills/adk-agent-builder/SKILL.md

Quality

Discovery

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.

The description names a specific technology (Google ADK) but is severely undermined by placeholder trigger language ('Use when appropriate context detected', 'Trigger with relevant phrases based on skill purpose') that provides zero selection guidance. The 'what' is partially addressed but lacks concrete actions, and the 'when' is entirely absent in any meaningful sense.

Suggestions

Replace the placeholder 'Use when appropriate context detected' with explicit trigger conditions, e.g., 'Use when the user asks about building agents with Google ADK, Agent Development Kit, or multi-agent systems using Google's framework.'

Add specific natural trigger terms users would say, such as 'ADK', 'Google ADK', 'Agent Development Kit', 'google agent framework', 'adk orchestration'.

List more concrete actions the skill performs, e.g., 'Scaffolds ADK agent projects, configures agent-to-agent communication, integrates ADK tool libraries, and sets up React-based agent UIs.'

Dimension	Reasoning	Score
Specificity	Names the domain (Google's Agent Development Kit) and some actions (multi-agent orchestration, React patterns, tool libraries), but 'Build production-ready AI agents' is somewhat generic and the listed capabilities lack concrete specificity about what actions the skill actually performs.	2 / 3
Completeness	While there is a weak 'what' (build AI agents with ADK), the 'when' clause is completely vacuous — 'Use when appropriate context detected' and 'Trigger with relevant phrases based on skill purpose' provide no actionable guidance whatsoever. This is effectively missing the 'when'.	1 / 3
Trigger Term Quality	The description says 'Trigger with relevant phrases based on skill purpose' which is a meaningless placeholder providing zero actual trigger terms. Natural keywords like 'ADK', 'Google ADK', 'agent framework', 'adk agent' are entirely absent.	1 / 3
Distinctiveness Conflict Risk	Mentioning 'Google's Agent Development Kit' provides some distinctiveness from generic AI agent skills, but the vague trigger language and broad terms like 'AI agents', 'multi-agent orchestration', and 'tool libraries' could easily overlap with other agent-building or AI framework skills.	2 / 3
	Total	6 / 12 Passed

Implementation

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is well-structured as an overview with good progressive disclosure to detailed references, but it critically lacks actionable, executable content. There are no code snippets, no concrete CLI commands, and no real examples showing actual ADK code—making it more of a planning checklist than a skill Claude can execute. The workflow has reasonable sequencing but lacks the explicit validation steps needed for deployment operations.

Suggestions

Add executable Python code examples showing actual ADK agent creation (e.g., importing from google.adk, defining an agent class, registering tools) rather than describing what the code should do abstractly.

Provide concrete, copy-paste-ready CLI commands for scaffolding, testing, and deployment (e.g., actual `adk deploy` command with placeholder arguments, `pytest` commands for smoke tests).

Add explicit validation checkpoints with concrete commands in the workflow, such as 'Run `python -c "import google.adk"` to verify installation' and 'Run `adk agent test --prompt "..."` to validate the agent responds correctly'.

Flesh out the examples section with actual code showing a minimal working agent definition and tool registration, not just a description of what the result would contain.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably concise but includes some unnecessary elaboration. Phrases like 'production-oriented ADK scaffold (agent entrypoint, tool registry, config, and tests)' repeat information found elsewhere, and some bullet points could be tightened. It doesn't over-explain concepts Claude knows, but it's not maximally lean either.	2 / 3
Actionability	The skill provides no executable code, no concrete commands (beyond vague 'adk deploy ...'), no actual code snippets for agent creation, tool wiring, or configuration. The instructions are high-level descriptions of what to do rather than specific, copy-paste-ready guidance. The examples describe inputs and outputs abstractly without showing actual code.	1 / 3
Workflow Clarity	There is a numbered sequence of steps (1-6) which provides some structure, but validation checkpoints are vague ('smoke test prompt', 'post-deploy validation checklist') without concrete commands or explicit feedback loops. For a skill involving deployment and multi-step scaffolding, the lack of explicit validate-fix-retry loops caps this at 2.	2 / 3
Progressive Disclosure	The skill appropriately keeps the main content as an overview and references a detailed guide at `${CLAUDE_SKILL_DIR}/references/SKILL.full.md`, repo standards documents, and external ADK docs. References are one level deep and clearly signaled with descriptive labels.	3 / 3
	Total	8 / 12 Passed

Validation

81%

Warnings & errors only

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

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: c8a915c

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.