adk-deployment-specialist

Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.

Quality

56%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/ai-ml/jeremy-adk-orchestrator/skills/adk-deployment-specialist/SKILL.md

Quality

Discovery

77%

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 does a good job listing specific capabilities and includes explicit 'Use when' guidance with trigger phrases. However, the trigger terms mix highly specific jargon (A2A protocol, AgentCard) with overly broad terms ('deploy', 'infrastructure', 'CI/CD') that risk conflicting with other deployment or infrastructure skills. The description would benefit from more targeted trigger terms that distinguish this agent orchestration skill from general deployment workflows.

Suggestions

Narrow the generic trigger terms: 'deploy', 'infrastructure', and 'CI/CD' are too broad and will conflict with general DevOps skills. Replace with more specific triggers like 'Vertex AI agent', 'A2A protocol', 'ADK deployment', 'multi-agent orchestration'.

Add natural user phrases that are more specific, such as 'set up agent communication', 'agent-to-agent', 'agent card', 'Vertex AI agents' to improve trigger term coverage without introducing conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: deploy and orchestrate Vertex AI ADK agents, manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. These are concrete, named capabilities.	3 / 3
Completeness	Clearly answers both 'what' (deploy and orchestrate Vertex AI ADK agents, manage AgentCard discovery, task submission, etc.) and 'when' (explicit 'Use when' clause with trigger phrases like 'deploy ADK agent', 'orchestrate agents', 'deploy', 'infrastructure', 'CI/CD').	3 / 3
Trigger Term Quality	Includes some relevant trigger terms like 'deploy ADK agent', 'orchestrate agents', 'deploy', 'infrastructure', 'CI/CD', but the terms are a mix of domain-specific jargon (A2A protocol, AgentCard) and generic terms ('infrastructure', 'CI/CD') that could conflict with other skills. Missing natural variations users might say like 'agent deployment', 'Vertex AI', 'multi-agent'.	2 / 3
Distinctiveness Conflict Risk	The Vertex AI ADK and A2A protocol specifics create some distinctiveness, but generic trigger terms like 'deploy', 'infrastructure', and 'CI/CD' could easily conflict with general deployment, DevOps, or infrastructure skills. These broad terms would cause false matches.	2 / 3
	Total	10 / 12 Passed

Implementation

35%

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

This skill reads more like a project brief or checklist than actionable guidance for Claude. It lacks any concrete code examples, deployment commands, or executable snippets — everything is either abstract instruction or deferred to referenced files that don't exist in the bundle. The workflow has reasonable sequencing but misses validation checkpoints critical for infrastructure deployment operations.

Suggestions

Add concrete, executable code examples inline — at minimum show the actual `vertexai.Client.agent_engines.create()` invocation with required parameters, an AgentCard definition, and a basic agent skeleton.

Include explicit validation/feedback loops in the workflow: e.g., 'Run `gcloud ai agent-engines describe ...` to verify deployment → if status != ACTIVE, check logs with `gcloud logging read ...` → fix and redeploy'.

Either provide the referenced bundle files (errors.md, examples.md) or inline the most critical error handling patterns and at least one complete example directly in the SKILL.md.

Remove explanatory text Claude already knows (e.g., the Overview paragraph explaining what ADK does) and replace with actionable constraints or decision trees for choosing orchestration patterns.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but the Overview section restates concepts Claude already knows (what ADK orchestration patterns are, what A2A protocol is). The Prerequisites section includes some unnecessary guidance like 'never commit long-lived keys' which Claude already understands. Could be tightened.	2 / 3
Actionability	The skill provides only abstract, high-level steps ('Confirm the desired architecture', 'Define the AgentCard') with no concrete code, commands, or executable examples. There are no copy-paste ready snippets, no actual deployment commands shown, and the examples are deferred entirely to a referenced file that doesn't exist in the bundle.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence and include a validation step (step 5), but there are no explicit feedback loops for error recovery, no validation checkpoints between steps, and the error handling is entirely deferred to a referenced file. For a deployment workflow involving destructive/infrastructure operations, this lacks sufficient validation gates.	2 / 3
Progressive Disclosure	References to errors.md and examples.md are well-signaled and one level deep, which is good structure. However, no bundle files were provided, meaning these references point to non-existent files, undermining the progressive disclosure. The main content is also too thin — it defers critical content (examples, error handling) without providing enough substance in the SKILL.md itself.	2 / 3
	Total	7 / 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: 196527a

Reviewed: 1 day 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.