genkit
Build production-ready AI workflows using Firebase Genkit. Use when creating flows, tool-calling agents, RAG pipelines, multi-agent systems, or deploying AI to Firebase/Cloud Run. Supports TypeScript, Go, and Python with Gemini, OpenAI, Anthropic, Ollama, and Vertex AI plugins.
Install with Tessl CLI
npx tessl i github:supercent-io/skills-template --skill genkit90
Quality
88%
Does it follow best practices?
Impact
92%
1.13xAverage score across 3 eval scenarios
Discovery
100%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 is an excellent skill description that hits all the key criteria. It provides specific concrete actions, includes a comprehensive set of natural trigger terms covering the framework, languages, and AI providers, explicitly states both what it does and when to use it, and carves out a distinct niche around Firebase Genkit that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creating flows, tool-calling agents, RAG pipelines, multi-agent systems, deploying AI to Firebase/Cloud Run' along with supported languages and AI provider plugins. | 3 / 3 |
Completeness | Clearly answers both what ('Build production-ready AI workflows using Firebase Genkit') and when ('Use when creating flows, tool-calling agents, RAG pipelines, multi-agent systems, or deploying AI to Firebase/Cloud Run') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Firebase Genkit', 'flows', 'tool-calling agents', 'RAG pipelines', 'multi-agent systems', 'Cloud Run', plus specific language names (TypeScript, Go, Python) and AI providers (Gemini, OpenAI, Anthropic, Ollama, Vertex AI). | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Firebase Genkit with distinct triggers; the combination of 'Firebase Genkit' plus specific workflow types (flows, RAG pipelines, multi-agent systems) makes it highly distinguishable from generic AI or Firebase skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent executable code examples covering the full Genkit feature set. The main weaknesses are verbosity (could trim explanatory text and consolidate installation options) and the monolithic structure that would benefit from splitting detailed sections into separate reference files.
Suggestions
Move the plugin tables (Model Providers, Vector Databases) to a separate PLUGINS.md reference file and link to it
Consolidate installation options to recommend one primary path (Google AI) with brief mentions of alternatives, moving detailed alternative setups to a separate file
Remove explanatory phrases like 'Flows are the core primitive: type-safe, observable, deployable AI functions' - Claude knows what these concepts mean
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as explaining what flows are ('Flows are the core primitive') and listing multiple installation options when one recommended path would suffice. The plugin tables and extensive setup instructions could be trimmed. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all TypeScript snippets are complete, copy-paste ready with proper imports, and cover the full range of use cases from basic flows to RAG pipelines and multi-agent systems. | 3 / 3 |
Workflow Clarity | Clear numbered steps for installation/setup, explicit validation guidance in constraints section ('Handle null output from generate() — throw meaningful errors'), and well-sequenced multi-step processes for deployment and RAG pipelines. | 3 / 3 |
Progressive Disclosure | The skill is quite long (~500 lines) with extensive inline content that could be split into separate reference files (plugin tables, deployment options, full examples). References section links to external docs but the main content is monolithic. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (679 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 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.