gcp-examples-expert

Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns. Use when asked to "show ADK example" or "provide GCP starter kit". Trigger with relevant phrases based on skill purpose.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/jeremy-gcp-starter-examples/skills/gcp-examples-expert/SKILL.md

Quality

Content

72%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 skill body is well-organized and token-efficient with excellent progressive disclosure via real, clearly-signaled reference files. It is held back by a lack of executable code in the main body and a workflow that omits explicit validation checkpoints.

Suggestions

Add a short copy-paste code skeleton (e.g. a minimal ADK agent or Genkit flow) directly in the body so the core generation task is actionable without opening a reference.

Insert an explicit validation step in the Instructions workflow, e.g. '11. Verify the generated example: run lint/tests and confirm imports and IAM config resolve before delivering to the user.'

Fold the three 'See ... for ...' pointers (workflow, best-practices, errors, example-interactions) into a single 'References' map so navigation is centralized rather than scattered across sections.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — terse numbered steps, bullet prerequisites, and a concrete error table — with no padding explaining what GCP, ADK, or Genkit are; every section earns its tokens and assumes Claude's competence.	3 / 3
Actionability	Concrete specifics exist (specific IAM roles, 'gcloud services enable aiplatform.googleapis.com', Gemini 2.5 Flash/Pro model choices, regions), but the core task of generating code defers actual executable code to the references rather than providing copy-paste examples in the body.	2 / 3
Workflow Clarity	The 10-step Instructions give a clear, ordered sequence but include no explicit validation or verification checkpoint (e.g. 'lint/test the generated example before delivering'), matching the 'steps listed but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references — 'See ${CLAUDE_SKILL_DIR}/references/workflow.md', errors.md, best-practices-applied.md, etc. — and all five referenced files exist in references/, giving clean, easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

85%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 specific, complete, and distinctive, clearly stating both capability and trigger conditions. Its only weakness is the vague 'Trigger with relevant phrases' filler that dilutes the otherwise concrete trigger-term coverage.

Suggestions

Replace 'Trigger with relevant phrases based on skill purpose' with concrete natural-language triggers a user would actually say, e.g. 'Use when asked for a GCP starter kit, an ADK agent example, a Genkit RAG flow, or Vertex AI sample code.'

Add common keyword variations (e.g. 'GCP sample', 'Vertex AI example', 'Gemini starter code') to broaden trigger-term coverage beyond the two current phrases.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions/sources — 'Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what (generate GCP code examples from official repos) and when via an explicit 'Use when asked to ...' trigger clause, satisfying the both-what-and-when anchor; not capped at 2 since the Use-when clause is present.	3 / 3
Trigger Term Quality	Includes two natural phrases ('show ADK example', 'provide GCP starter kit') but then falls back to the generic filler 'Trigger with relevant phrases based on skill purpose', missing common variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	A clear GCP-example-generation niche with distinct trigger phrases ('show ADK example', 'provide GCP starter kit') makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
Path: plugins/ai-ml/jeremy-gcp-starter-examples/skills/gcp-examples-expert/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.