ai-product

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill ai-product

What are skills?

1.51x

Quality

27%

Does it follow best practices?

Impact

79%

1.51x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ai-product/SKILL.md

SKILL.md

Review

Evals

Discovery

32%

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 leads with marketing rhetoric ('The question is whether you'll build it right or ship a demo that falls apart') rather than functional capability statements. While it mentions relevant technical domains (LLM integration, RAG, prompts), it lacks explicit trigger guidance and appears truncated. The tone is inappropriate for a skill description that should help Claude select the right tool.

Suggestions

Remove the marketing/opinion opening and start with concrete actions in third person (e.g., 'Implements LLM integration patterns, designs RAG pipelines, engineers prompts for production systems')

Add an explicit 'Use when...' clause with natural trigger terms like 'building AI features', 'adding LLM to app', 'vector search', 'embeddings', 'chatbot integration'

Complete the truncated description to fully enumerate the specific capabilities covered by this skill

Dimension	Reasoning	Score
Specificity	Names the domain (AI/LLM integration) and mentions some specific areas like 'RAG architecture' and 'prompt', but the description is truncated and doesn't list comprehensive concrete actions. The opening is more marketing fluff than capability description.	2 / 3
Completeness	The description partially addresses 'what' (LLM integration patterns, RAG architecture) but is truncated and provides no 'Use when...' clause or explicit trigger guidance. The opening sentence is opinion/marketing rather than functional description.	1 / 3
Trigger Term Quality	Contains some relevant technical keywords like 'AI-powered', 'LLM integration', 'RAG architecture', and 'prompt', but these are more technical jargon than natural user language. Missing common variations users might say like 'chatbot', 'embeddings', 'vector database', 'AI app'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'LLM integration patterns' and 'RAG architecture' provides some specificity, but 'AI-powered' is extremely generic and could overlap with many AI-related skills. The truncation makes it harder to assess full distinctiveness.	2 / 3
	Total	7 / 12 Passed

Implementation

22%

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

This skill reads like an outline or skeleton rather than actionable guidance. It identifies important AI product development concerns (validation, streaming, prompt versioning) but fails to provide any executable code or concrete implementation details. The Sharp Edges table is particularly problematic as it promises solutions but delivers only empty comment placeholders.

Suggestions

Add complete, executable code examples for each pattern (e.g., actual function calling implementation with schema validation, streaming response handling code)

Fill in the Sharp Edges solutions with real code snippets instead of comment placeholders

Add a step-by-step workflow for implementing a basic LLM feature with validation checkpoints (e.g., 1. Define schema → 2. Implement call → 3. Validate response → 4. Handle errors)

Remove the persona paragraph - it adds no actionable value and wastes tokens

Dimension	Reasoning	Score
Conciseness	The persona introduction is unnecessary fluff that Claude doesn't need. The patterns and anti-patterns sections are reasonably concise but the 'Sharp Edges' table has incomplete solutions (just comments like '# Always validate output:' with no actual code).	2 / 3
Actionability	Critically lacking executable guidance. Patterns mention concepts like 'function calling or JSON mode' without code examples. The Sharp Edges table promises solutions but only shows comment placeholders ('# Always validate output:') with no actual implementation code.	1 / 3
Workflow Clarity	No clear workflows or sequences are provided. The skill lists concepts and warnings but never shows how to actually implement an AI feature step-by-step. No validation checkpoints or feedback loops for the complex operations mentioned.	1 / 3
Progressive Disclosure	Content is organized into logical sections (Patterns, Anti-Patterns, Sharp Edges) which provides some structure. However, there are no references to detailed documentation, and the Sharp Edges table appears truncated/incomplete rather than properly linking to detailed guides.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: about 23 hours ago

Table of Contents

Discovery Implementation Validation

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.