genkit-production-expert
tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill genkit-production-expertBuild production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.
Validation
81%| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
Implementation
22%This skill is a generic template with no actual Genkit-specific content. Despite the description promising guidance on RAG systems, multi-step flows, tool calling, and Firebase deployment, the body contains only placeholder boilerplate. It fails to provide any actionable guidance for the complex production tasks it claims to support.
Suggestions
Add executable code examples for core Genkit operations: creating flows, implementing RAG with retrievers, and tool calling patterns
Include specific deployment commands and configuration for Firebase Functions and Cloud Run
Replace generic instructions with a concrete workflow showing the sequence for building a Genkit application with validation steps
Populate the referenced files (errors.md, examples.md) with actual content or inline the essential guidance directly in the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is brief but wastes tokens on generic boilerplate ('This skill provides automated assistance...') that adds no value. It's not verbose, but every line is filler rather than substantive guidance. | 2 / 3 |
Actionability | Completely vague with no concrete code, commands, or specific guidance. Instructions like 'Invoke this skill when trigger conditions are met' and 'Provide necessary context' are abstract and non-executable. No Firebase Genkit-specific content whatsoever. | 1 / 3 |
Workflow Clarity | The 4-step 'Instructions' section is generic placeholder text with no actual workflow for building Genkit applications, RAG systems, or deployments. No validation checkpoints or meaningful sequence for the complex operations described. | 1 / 3 |
Progressive Disclosure | References to external files (errors.md, examples.md) exist and are one level deep, but the main content provides no useful overview. The references use placeholder paths ({baseDir}) and the skill body itself contains no substantive content to disclose progressively from. | 2 / 3 |
Total | 6 / 12 Passed |
Activation
85%This is a strong description that clearly identifies the Firebase Genkit domain with specific capabilities and deployment targets. The explicit 'Use when...' clause provides good trigger guidance. The main weakness is the vague final sentence about triggering 'with relevant phrases based on skill purpose' which adds no value and the trigger terms could include more natural user variations.
Suggestions
Remove the meaningless final sentence 'Trigger with relevant phrases based on skill purpose' - it provides no actionable guidance for skill selection.
Expand trigger terms to include natural variations users might say: 'retrieval augmented generation', 'AI pipeline', 'genkit app', 'firebase AI', '.genkit'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling' and 'Deploy to Firebase Functions or Cloud Run with AI monitoring'. Covers specific technologies and deployment targets. | 3 / 3 |
Completeness | Clearly answers both what (build Genkit apps with RAG, flows, tool calling; deploy to Firebase/Cloud Run) and when ('Use when asked to create genkit flow or implement RAG'). Has explicit trigger guidance despite the weak final sentence. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'genkit flow', 'RAG', 'Firebase Functions', 'Cloud Run', but the final sentence 'Trigger with relevant phrases based on skill purpose' is meta-instruction rather than actual trigger terms. Missing natural variations users might say like 'AI pipeline', 'retrieval augmented generation', or 'genkit app'. | 2 / 3 |
Distinctiveness Conflict Risk | Firebase Genkit is a specific framework with clear niche. The combination of 'Genkit', 'Firebase Functions', 'Cloud Run', and 'RAG systems' creates distinct triggers unlikely to conflict with generic AI or Firebase skills. | 3 / 3 |
Total | 11 / 12 Passed |
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.