CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

32

Quality

28%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/productivity/004-jeremy-google-cloud-agent-sdk/skills/google-cloud-agent-sdk-master/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-3

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

The content is a clean, well-organized overview with a sensible workflow and a real reference file, but it stays at the level of abstract guidance — no executable code or commands, an empty docs bullet, and only loosely specified validation checkpoints.

Suggestions

Add at least one minimal executable scaffold (e.g. a short ADK agent code snippet or a concrete `adk`/Vertex command) so the actionability reaches copy-paste ready.

Fill in or remove the empty 'ADK / Agent Engine docs' bullet under Resources, and confirm the `000-docs/6767-...` path exists within the bundle or note it as an external standard.

Make the validation checkpoints explicit and command-backed (e.g. a concrete smoke-prompt command and a CI verification command) so the workflow has a real validate-fix-retry loop.

DimensionReasoningScore

Conciseness

The body is mostly lean and well-sectioned with little concept re-explanation, but phrases like 'produce a safe, production-oriented plan (structure, patterns, deployment, verification) rather than ad-hoc snippets' and the placeholder ADK docs bullet add slight padding that could be trimmed.

2 / 3

Actionability

Guidance names concrete deliverables (architecture recommendation, tool interfaces, scaffold) but offers no executable code, commands, or copy-paste examples — it describes and instructs abstractly rather than providing executable artifacts.

2 / 3

Workflow Clarity

The four numbered instructions form a clear sequence and step 4 mentions validation (smoke prompts, regression tests), but the validation checkpoints are not tied to specific commands and the Error Handling section lacks a feedback loop, so checkpoints are present but implicit.

2 / 3

Progressive Disclosure

The body is a concise overview that points to a real one-level reference (references/SKILL.full.md, which exists), but the 'ADK / Agent Engine docs' bullet is an empty/missing link and the second reference path (000-docs/6767-...) is not clearly signaled as part of the bundle, leaving navigation incomplete.

2 / 3

Total

8

/

12

Passed

Description

7%Weight 40%Scale 1-3

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 mostly placeholder text — it gestures at activation and trigger phrases without naming concrete actions or any real trigger keywords. It reads as a template draft rather than a usable skill description.

Suggestions

Replace 'Execute automatic activation ... Use when appropriate context detected' with concrete actions such as 'Architect and scaffold Google ADK agents, define tool contracts, and plan deployment to Vertex AI Agent Engine.'

Add an explicit 'Use when' clause with natural trigger phrases users would actually say, e.g. 'Use when the user asks about building, structuring, or deploying agents with Google's Agent Development Kit (ADK).'

Remove the meta-instruction 'Trigger with relevant phrases based on skill purpose' — the description itself should contain the trigger terms.

DimensionReasoningScore

Specificity

The description ('Execute automatic activation for all google cloud agent development kit (adk)') names no concrete actions beyond 'execute activation', relying on vague abstraction rather than listing specific capabilities.

1 / 3

Completeness

There is no explicit 'Use when...' trigger clause with real conditions — only the placeholder 'Use when appropriate context detected' — so the 'when' half is effectively missing despite the rubric capping completeness at 2 without a real trigger clause.

1 / 3

Trigger Term Quality

'Trigger with relevant phrases based on skill purpose' provides no actual natural keywords a user would say; it defers trigger terms entirely without naming them, leaving only technical jargon ('agent development kit (adk)').

1 / 3

Distinctiveness Conflict Risk

The 'google cloud agent development kit (adk)' niche is reasonably distinct from other skills, but the generic 'appropriate context detected' trigger leaves overlap risk for any GCP-related task.

2 / 3

Total

5

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.