google-cloud-agent-sdk-master

Execute automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is a concise, well-structured instruction skill with a clear sequenced workflow and validation feedback loops. Its main weaknesses are incomplete actionability (no executable scaffold/code) and a couple of dangling or non-bundle references that weaken progressive disclosure.

Suggestions

Add a minimal concrete scaffold (directory layout or a small code snippet) so the implementation guidance is copy-paste actionable rather than purely descriptive.

Fix the empty 'ADK / Agent Engine docs:' bullet by adding the actual link, and convert the external repo path '000-docs/6767-a-...' into a clearly signaled local reference or remove it.

Tighten the Output section into a concrete checklist with example commands for local and CI validation.

Dimension	Reasoning	Score
Conciseness	The ~45-line body is lean and well-sectioned with no padding or explanation of concepts Claude already knows; nearly every line earns its place.	3 / 3
Actionability	It offers concrete-ish planning guidance (tool contracts, validation, deployment verification) but lacks executable code, commands, or a concrete scaffold, leaving key implementation details missing.	2 / 3
Workflow Clarity	The four-step Instructions are clearly sequenced with an explicit validation step (#4) and an Error Handling section providing feedback loops for recovery.	3 / 3
Progressive Disclosure	It keeps SKILL.md lean and links to a real one-level-deep reference (references/SKILL.full.md), but the empty 'ADK / Agent Engine docs:' bullet and the non-bundle repo path show imperfect signaling and organization.	2 / 3
	Total	10 / 12 Passed

Description

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 is vague and boilerplate-heavy, naming a domain (ADK) but no concrete actions and no real trigger terms a user would naturally say. Both the 'what' and 'when' are present but content-free, leaving it largely indistinguishable from a generic activation skill.

Suggestions

Replace 'Execute automatic activation' with concrete actions, e.g. 'Master Google ADK patterns for building and deploying production agents, defining tool contracts, and adding validation guardrails.'

Replace the boilerplate 'Use when appropriate context detected' with natural trigger phrases users would say, such as 'Use when building or deploying Google Agent Development Kit (ADK) agents, designing agent tool interfaces, or planning Vertex AI Agent Engine deployment.'

Keep third-person voice and ensure the description clearly distinguishes this skill from general Google Cloud or generic agent-building skills.

Dimension	Reasoning	Score
Specificity	The only action stated is the vague 'Execute automatic activation', with no concrete capabilities named; it falls short of listing multiple specific actions.	1 / 3
Completeness	Both the 'what' (automatic activation for ADK) and the 'when' (appropriate context detected) are present but very weak, matching the 'both very weak' anchor.	1 / 3
Trigger Term Quality	'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose' is boilerplate with no natural keywords a user would actually say.	1 / 3
Distinctiveness Conflict Risk	The Google Cloud / ADK domain gives it a somewhat specific niche, but the absence of distinct triggers means it could still overlap with similar skills.	2 / 3
	Total	5 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 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.