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.
28
21%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/productivity/004-jeremy-google-cloud-agent-sdk/skills/google-cloud-agent-sdk-master/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely weak across all dimensions. It relies on circular, self-referential trigger language ('Use when appropriate context detected', 'Trigger with relevant phrases based on skill purpose') that provides no actionable guidance. The only redeeming quality is the mention of 'google cloud agent development kit (adk)' which provides minimal domain anchoring.
Suggestions
Replace the vague 'automatic activation' with specific concrete actions the skill performs, e.g., 'Creates, configures, and deploys agents using Google Cloud Agent Development Kit (ADK). Manages agent pipelines, tool definitions, and ADK project scaffolding.'
Replace the circular 'Use when appropriate context detected' with explicit trigger conditions, e.g., 'Use when the user mentions ADK, Google Cloud agents, agent development kit, building conversational agents on Google Cloud, or working with ADK project files.'
Add natural user-facing keywords and file types/terms users would actually say, such as 'ADK', 'Google Cloud agents', 'agent.yaml', 'adk deploy', 'adk create', 'conversational AI on GCP'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'Execute automatic activation for all google cloud agent development kit (adk)' which is vague and does not list any concrete actions. There are no specific capabilities described—just a generic 'automatic activation' phrase. | 1 / 3 |
Completeness | The 'what' is extremely vague ('automatic activation' tells nothing about actual capabilities), and the 'when' is a meaningless tautology ('Use when appropriate context detected'). Neither question is meaningfully answered. | 1 / 3 |
Trigger Term Quality | The trigger guidance is entirely circular and generic: 'Trigger with relevant phrases based on skill purpose' provides zero actual keywords. While 'google cloud agent development kit' and 'adk' are mentioned, the rest is filler with no natural user-facing terms. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'google cloud agent development kit (adk)' does provide some domain specificity that narrows the scope, but the lack of concrete actions or clear triggers means it could still overlap with other Google Cloud or agent-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a high-level planning template rather than actionable technical guidance for working with Google ADK. It lacks any concrete code examples, specific CLI commands, API patterns, or executable snippets that would help Claude actually build ADK agents. The workflow is structured but entirely abstract, making it more of a project management checklist than a technical skill.
Suggestions
Add concrete, executable code examples showing ADK agent creation (e.g., a minimal single-agent scaffold with `google.adk` imports, tool definitions, and agent instantiation).
Replace abstract instructions like 'Define tool interfaces' with specific ADK patterns, including actual Python code for tool contracts, error handling decorators, and configuration.
Include specific CLI commands for local testing, deployment to Vertex AI Agent Engine, and health check verification (e.g., `adk run`, `gcloud` commands).
Add a concrete example in the Example section showing actual input/output with code scaffolds rather than just 'an architecture recommendation with tradeoffs'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some unnecessary framing (e.g., the Overview section restates what the skill does, the Example section is vague and doesn't add much value). The Prerequisites and Instructions sections are reasonably lean but could be tighter. | 2 / 3 |
Actionability | The skill provides no concrete code, no executable commands, no specific ADK API calls, and no copy-paste-ready examples. It reads as a high-level process description ('clarify requirements', 'define tool interfaces', 'provide an implementation plan') rather than actionable guidance. The example shows a vague request/output pair with no actual content. | 1 / 3 |
Workflow Clarity | There is a numbered sequence of steps (clarify, define, implement, validate) and mention of validation/verification, but the steps are abstract and lack specific commands, validation checkpoints with concrete tools, or feedback loops for error recovery. The validation step mentions 'smoke prompts, regression tests' without showing how to run them. | 2 / 3 |
Progressive Disclosure | The skill references a full detailed guide at `${CLAUDE_SKILL_DIR}/references/SKILL.full.md` and external docs, which is good structure. However, no bundle files were provided to verify the reference exists, and the main content itself is thin enough that it's unclear what value the separation provides. The references are one-level deep and clearly signaled, which is positive. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
4801da6
- 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.