vertex-ai-media-master
Execute automatic activation for all google vertex ai multimodal operations operations. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
32
17%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/productivity/003-jeremy-vertex-ai-media-master/skills/vertex-ai-media-master/SKILL.mdQuality
Discovery
0%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 poor across all dimensions. It reads as auto-generated boilerplate with circular, self-referential language ('trigger with relevant phrases based on skill purpose') and no concrete information about what the skill actually does or when it should be used. It would be essentially useless for Claude to select this skill appropriately from a pool of available skills.
Suggestions
Replace vague language with specific concrete actions the skill performs, e.g., 'Sends images, video, and audio to Google Vertex AI for analysis, generates multimodal content, and processes responses from Gemini models.'
Add an explicit 'Use when...' clause with natural trigger terms users would say, e.g., 'Use when the user asks about Vertex AI, Gemini, Google Cloud AI, image analysis, multimodal prompts, or vision tasks.'
Remove the circular filler phrases ('trigger with relevant phrases based on skill purpose', 'when appropriate context detected') and replace them with actual distinguishing details about the skill's scope and boundaries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'automatic activation' and 'multimodal operations operations' without listing any concrete actions. No specific capabilities such as image analysis, text generation, or video processing are mentioned. | 1 / 3 |
Completeness | The 'what' is essentially absent—'multimodal operations' is not a meaningful description of capabilities. The 'when' clause ('when appropriate context detected') is completely vacuous and provides no actionable trigger guidance. | 1 / 3 |
Trigger Term Quality | The description contains no natural keywords a user would actually say. 'Relevant phrases based on skill purpose' is entirely circular and unhelpful. Terms like 'automatic activation' and 'appropriate context detected' are not user-facing language. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it could conflict with any AI/ML-related skill. 'Multimodal operations' and 'automatic activation' provide no distinguishing characteristics to differentiate this from other vertex AI or multimodal skills. | 1 / 3 |
Total | 4 / 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 provides a broad overview of Vertex AI multimodal operations with decent structure and useful error handling, but critically lacks any executable code examples. The instructions read more like a product overview or tutorial outline than actionable guidance Claude can follow. The absence of concrete Python snippets for any of the described operations severely limits its utility.
Suggestions
Add executable Python code snippets for at least the core operations: initializing the Vertex AI client, generating an image with Imagen 4, analyzing a video with Gemini 2.5 Pro, and generating audio with Lyria.
Replace the narrative examples with concrete code examples showing actual API calls, request construction, and response handling that Claude can copy-paste and adapt.
Add explicit validation steps with concrete commands or code (e.g., checking response status codes, verifying file sizes, validating JSON output schemas) rather than the vague 'validate results against brand guidelines'.
Move the detailed error handling table and extended examples to a referenced file, and use the freed space for core executable code patterns in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately verbose with some unnecessary explanation (e.g., the Output section lists things Claude could infer, and the Examples section describes workflows at a high level without executable code). The prerequisites and error handling table are useful but the overall content could be tightened. | 2 / 3 |
Actionability | Despite covering multiple complex operations, the skill provides zero executable code. All instructions are abstract descriptions ('Initialize the Vertex AI client', 'Construct the generation request') without concrete Python snippets, API calls, or copy-paste-ready commands. The examples describe inputs/outputs narratively but never show actual code. | 1 / 3 |
Workflow Clarity | Steps are listed in a logical sequence and the error handling table is a useful addition, but validation is mentioned only vaguely in step 7 ('Validate results against brand guidelines or schema expectations') with no concrete validation commands or feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The skill references a bundle file (`${CLAUDE_SKILL_DIR}/references/core-capabilities.md`) and external documentation links, which is good structure. However, no bundle files were actually provided, and the main SKILL.md contains a lot of inline content (full error table, detailed examples) that could be split out, while the core executable guidance that should be inline is missing. | 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
3a2d27d
- 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.