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 engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

Quality

19%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

17%

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 has significant structural problems - the 'Use when' clause contains placeholder text instead of actual triggers, making it non-functional for skill selection. The opening sentence is marketing fluff rather than actionable description, and the capabilities listed are topic areas rather than concrete actions Claude can perform.

Suggestions

Replace the broken 'Use when: keywords, file_patterns, code_patterns' with actual trigger terms like 'Use when building AI features, integrating LLMs, implementing RAG, designing AI chatbots, or optimizing API costs'

Remove the marketing opener ('Every product will be AI-powered...') and replace with concrete actions like 'Designs LLM integration architectures, implements RAG pipelines, writes production-ready prompts'

Add specific file patterns or code patterns users might mention, such as 'OpenAI API', 'vector databases', 'embedding models', 'langchain', '.prompt files'

Dimension	Reasoning	Score
Specificity	Names domain (AI/LLM integration) and lists several areas (RAG architecture, prompt engineering, AI UX, cost optimization), but these are high-level categories rather than concrete actions. No specific verbs describing what the skill actually does.	2 / 3
Completeness	The 'what' is vague (covers topics but not actions), and the 'when' is completely broken with placeholder text 'Use when: keywords, file_patterns, code_patterns' - this is non-functional guidance.	1 / 3
Trigger Term Quality	The 'Use when' clause literally contains placeholder text 'keywords, file_patterns, code_patterns' instead of actual trigger terms. Terms like 'LLM', 'RAG', 'prompt engineering' appear in the body but the trigger section is broken.	1 / 3
Distinctiveness Conflict Risk	The AI/LLM focus provides some distinctiveness, but terms like 'cost optimization' and 'UX' are generic enough to overlap with other skills. The broken trigger section makes conflict assessment difficult.	2 / 3
	Total	6 / 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 functions as a bare index page rather than a functional skill. It has a verbose persona section but provides zero actionable content - no code examples, no workflow guidance, and no context for when to use each sub-skill. The progressive disclosure structure is present but undermined by the complete absence of overview content.

Suggestions

Add a quick-start section with at least one concrete, executable code example demonstrating a core AI product pattern (e.g., structured output with Pydantic)

Include brief 1-sentence descriptions for each sub-skill link so readers know what they'll find without clicking through

Add a decision tree or workflow showing when to apply each pattern (e.g., 'For user-facing features → streaming; For data extraction → structured output')

Remove or significantly trim the persona paragraph - the principles can be stated in 1-2 lines

Dimension	Reasoning	Score
Conciseness	The persona description is somewhat verbose and could be trimmed - Claude doesn't need to be told about debugging at 3am or shipping to millions. However, the overall structure is lean with just links to sub-skills.	2 / 3
Actionability	The skill provides no concrete code, commands, or executable guidance - it's entirely a table of contents pointing to other files with no actionable content in the main skill itself.	1 / 3
Workflow Clarity	There is no workflow, sequence, or process described. The skill is purely organizational with no guidance on when to use which sub-skill or how they relate to each other in a development workflow.	1 / 3
Progressive Disclosure	The skill does use one-level-deep references to sub-skills appropriately, but lacks any quick-start content or overview of what each sub-skill covers - it's just a list of links without context or navigation guidance.	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

Repository: Dokhacgiakhoa/antigravity-ide
Commit: 332e58b

Reviewed: 17 days 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.