CtrlK
BlogDocsLog inGet started
Tessl Logo

genkit-production-expert

Build 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.

57

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/jeremy-genkit-pro/skills/genkit-production-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly lean overview that delegates detail to one-level-deep references, but it lacks executable code in the body, explicit validation feedback loops before deploy, and links to several existing bundle files. Every dimension lands at the mid anchor.

Suggestions

Add a minimal executable code snippet in the body (or link scripts/init-genkit.sh) so the core flow is copy-paste ready rather than deferred entirely to references.

Insert an explicit validation checkpoint in the Instructions workflow — e.g., run the Genkit Dev UI / schema validation, fix errors, re-validate, then deploy — to create a validate→fix→retry feedback loop.

Link the orphan bundle files (ARD.md, PRD.md, examples.md, and init-genkit.sh) from the relevant sections, or remove them, so the bundle structure matches what the body navigates to.

DimensionReasoningScore

Conciseness

Mostly efficient and free of beginner-concept padding, but the Overview paragraph restates the description and the Resources section ends with vague pointer lines ('Gemini model selection guide...', 'Context caching and token optimization strategies...') that could be tightened.

2 / 3

Actionability

Steps name concrete APIs (ai.defineFlow, ai.defineTool, ai.defineRetriever) and config files, but the body contains no executable code examples — it defers all code to references — and the existing init-genkit.sh script is never referenced, leaving guidance incomplete.

2 / 3

Workflow Clarity

The 10-step sequence is clearly ordered, but validation is only implicit ('Test locally... then deploy') with no explicit validate→fix→retry feedback loop before destructive deployment, which caps workflow clarity at 2 per the rubric.

2 / 3

Progressive Disclosure

Signaled references (how-it-works.md, production-best-practices-applied.md, errors.md, workflow-examples.md) are one level deep and clearly contextualized, but three reference files (ARD.md, PRD.md, examples.md) and the scripts/init-genkit.sh bundle file are present yet never linked from the body, leaving navigation incomplete.

2 / 3

Total

8

/

12

Passed

Description

85%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and gives explicit 'Use when' trigger guidance. Its main weakness is limited trigger-term coverage plus a vague filler sentence that adds no real keywords.

DimensionReasoningScore

Specificity

Lists multiple 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' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (build/deploy Genkit apps, RAG, tool calling) and when via an explicit 'Use when asked to...' clause, matching the what-AND-when anchor.

3 / 3

Trigger Term Quality

Includes a couple of natural triggers ('create genkit flow', 'implement RAG') but coverage is narrow and the filler 'Trigger with relevant phrases based on skill purpose' adds no real keywords, so common variations are missing.

2 / 3

Distinctiveness Conflict Risk

The Firebase Genkit niche with RAG/multi-step-flow triggers is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.