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

—

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 lean, well-sequenced overview with real validation and feedback loops, but it stays at a high level with no executable ADK code or commands, and its progressive disclosure is broken: it points to a non-existent reference while ignoring the real bundle files.

Suggestions

Add at least one concrete, executable ADK example (agent/tool definition, project scaffold command, or the setup-project.sh invocation) so the guidance is copy-paste ready rather than descriptive.

Fix the Resources section: point to the actual reference files (ARD.md, errors.md, examples.md, implementation.md) instead of the missing SKILL.full.md, and route the inline Error Handling and Examples content to errors.md/examples.md.

Remove or complete the truncated 'ADK / Agent Engine docs:' line so the navigation section is not dead weight.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned, assuming Claude's competence without explaining concepts Claude already knows; the only slack (a summary line that restates the Overview and a truncated 'ADK / Agent Engine docs:' line) is minor and does not rise to verbosity.	3 / 3
Actionability	It gives specific structured direction (named steps, named patterns like 'Memory Bank / external store' and 'retries/backoff, timeouts') but provides no executable code, commands, concrete ADK API usage, or copy-paste-ready file structures, so it describes more than it instructs.	2 / 3
Workflow Clarity	A clear 6-step sequence includes an explicit validation step ('Validate locally' in step 6), incremental regression-test checkpoints (step 4), and error-recovery feedback loops in the Error Handling section, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The overview is well-sectioned, but the one reference it signals (references/SKILL.full.md) does not exist, while the actual bundle files (ARD.md, errors.md, examples.md, implementation.md) are never linked and their content is duplicated inline rather than routed out.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 answers both 'what' and 'when' with an explicit trigger clause and a distinct ADK niche, but is weakened by buzzword padding, missing trigger variations, a template-fluff closing line, and the grammatically awkward lead phrase 'Execute software engineer'.

Suggestions

Drop the buzzword 'best practices' and replace 'Execute software engineer' with a clean third-person verb phrase (e.g. 'Engineer production-ready ADK agents...') for sharper specificity.

Expand trigger coverage with natural variations users would actually say, such as 'write an ADK agent', 'set up an ADK agent', and 'Agent Development Kit'.

Remove the template residue 'Trigger with relevant phrases based on skill purpose.' since it adds no trigger information.

Dimension	Reasoning	Score
Specificity	It names the ADK domain and several action areas ("creating production-ready ADK agents... code structure, testing, and deployment automation"), but pads with the buzzword "best practices" and lists work-categories rather than crisp atomic actions as in the score-3 anchor.	2 / 3
Completeness	It explicitly answers both what (engineering production-ready ADK agents with code structure, testing, deployment automation) and when, via an explicit "Use when asked to..." clause with concrete triggers.	3 / 3
Trigger Term Quality	It offers natural triggers ("build ADK agent", "create agent code", "engineer ADK application") but misses common variations (e.g. "write/set up an ADK agent", "Agent Development Kit") and ends with template fluff ("Trigger with relevant phrases based on skill purpose.") that adds no trigger value.	2 / 3
Distinctiveness Conflict Risk	The ADK-specific framing and ADK-keyed triggers carve a clear niche that is unlikely to fire for non-ADK skills, matching the score-3 distinct-trigger anchor.	3 / 3
	Total	10 / 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: 2cafb23

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.