adk-engineer

Execute software engineer specializing in creating production-ready ADK agents with best practices, code structure, testing, and deployment automation. Use when asked to "build ADK agent", "create agent code", or "engineer ADK application". Trigger with relevant phrases based on skill purpose.

Quality

82%

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

Quality

Content

65%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 concise, well-structured overview with a clear multi-step workflow, but it stays at the instructional level — no executable code or concrete commands — and its progressive disclosure is undermined by a dangling reference path (SKILL.full.md) and inline material that overlaps the real reference files.

Suggestions

Replace the abstract Instructions with at least one concrete, runnable artifact — e.g. a minimal agent/tool scaffolding snippet or the exact test/deploy commands — so the skill is actionable, not just descriptive.

Fix or remove the `${CLAUDE_SKILL_DIR}/references/SKILL.full.md` pointer (no such file exists) and align the Resources section with the actual reference files (ARD.md, errors.md, examples.md, implementation.md).

Add an explicit validate→fix→retry loop with checkpoint commands (e.g. the test command to run, expected pass signal, and triage step) for the build/test and deploy steps to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview that assumes Claude's competence, with no padded explanations of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Guidance is concrete in intent ("add one tool at a time with input validation", "enforce structured error responses") but lacks executable code or specific commands, leaving it instructional rather than copy-paste ready.	2 / 3
Workflow Clarity	The six-step Instructions sequence is clear and step 6 names validation (tests + smoke prompts), but checkpoints are implicit and the validation/Error Handling sections describe outcomes without concrete commands or a validate→fix→retry loop for the build pipeline.	2 / 3
Progressive Disclosure	Sections are well organized and reference real bundle files (references/{errors,examples,implementation,ARD}.md, scripts/setup-project.sh), but navigation is inconsistent: the body points to `${CLAUDE_SKILL_DIR}/references/SKILL.full.md` which does not exist in the bundle, and the inline Examples/Resources content that belongs in those references is duplicated in SKILL.md.	2 / 3
	Total	9 / 12 Passed

Description

100%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 strong: it states concrete capabilities and gives explicit, natural trigger phrases covering both what and when. Minor note that "Trigger with relevant phrases based on skill purpose" is filler that adds nothing, but it does not reduce the score.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "best practices, code structure, testing, and deployment automation" — matching the top anchor for listing several specific actions.	3 / 3
Completeness	Explicitly answers both what (engineer production-ready ADK agents) and when ("Use when asked to 'build ADK agent'...") with explicit trigger guidance.	3 / 3
Trigger Term Quality	Provides natural phrasings a user would actually say ("build ADK agent", "create agent code", "engineer ADK application"), giving good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	Targets a clear ADK-specific niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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-adk-software-engineer/skills/adk-engineer/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.