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.

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-product/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The content is a strong, code-heavy reference for AI/LLM product patterns with mostly executable examples, but it is verbose in its explanatory prose, lacks validation checkpoints in its workflows, and inlines everything into a single large file with no progressive disclosure.

Suggestions

Split the Validation Checks catalog and detailed Sharp Edges fixes into separate reference files (e.g. references/validation-checks.md, references/sharp-edges.md) and link to them from SKILL.md to improve progressive disclosure.

Trim the 'Why this breaks' and Principles prose that restates facts Claude already knows (LLMs are probabilistic, context windows are finite), keeping only non-obvious guidance.

Add explicit validation/verification checkpoints to the Collaboration workflows (e.g. 'validate structured output before integrating backend', 'retrieval eval passes before optimizing'), and define or remove the assumed helpers (CircuitBreaker, rerank, embed) so examples are fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with dense, actionable TypeScript, but the Principles explanations and 'Why this breaks' prose restate concepts Claude already knows (LLMs are probabilistic, context windows are finite, LLMs hallucinate), which could be trimmed.	3 / 5
Actionability	It provides extensive copy-paste-ready code (zod validation, OpenAI streaming, embedding cache, cost tracking, provider fallback), but several examples rely on undefined helpers (CircuitBreaker, rerank, embed, verifySourceExists, calculateCost), leaving minor gaps below fully executable.	4 / 5
Workflow Clarity	The Collaboration section lists sequenced workflows (AI feature dev, RAG implementation) but they lack validation checkpoints, and the skill is a patterns catalog rather than a guided, validated multi-step process.	3 / 5
Progressive Disclosure	Section headers (Principles, Patterns, Sharp Edges, Validation Checks, Collaboration) give clear structure, but the entire ~750-line skill is one monolithic file with no references to separate files, and catalogs like Validation Checks that belong in reference files are inlined; no bundle files exist.	3 / 5
	Total	13 / 20 Passed

Description

28%Weight 40%Scale 1-5

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

The description is a catchy tagline rather than a capability/trigger statement: it names the AI-product domain but lists no concrete actions and provides no 'when to use' guidance. It would not reliably surface this skill for the right requests.

Suggestions

Rewrite as a capability + trigger statement, e.g. 'Design and implement LLM-powered features: RAG architectures, structured output validation, streaming UX, prompt versioning, and cost optimization. Use when building AI/LLM features, chatbots, RAG systems, or integrating models like GPT/Claude.'

Add an explicit 'Use when...' clause listing natural trigger terms users say (LLM integration, RAG, prompt engineering, chatbot, AI feature).

List 3-4 concrete actions (e.g. 'validate structured LLM output', 'implement RAG with hybrid search', 'stream responses', 'track LLM costs') to lift specificity above a slogan.

Dimension	Reasoning	Score
Specificity	The description names the domain ('AI-powered' products) but provides no concrete actions — it reads as a marketing slogan ('build it right or ship a demo that falls apart in production') rather than a capability statement, so it sits just above score 1's pure vagueness.	2 / 5
Completeness	It offers a vague 'what' (build AI products correctly) and entirely lacks a 'when'/'Use when...' trigger clause, matching the anchor for a vague what with no when.	2 / 5
Trigger Term Quality	It contains only generic terms ('AI-powered', 'product', 'production') and omits the natural phrases users actually say when they need this skill ('LLM', 'RAG', 'chatbot', 'prompt engineering', 'AI feature').	2 / 5
Distinctiveness Conflict Risk	'AI product development' is somewhat specific, but the sweeping framing ('Every product will be AI-powered') overlaps broadly with backend, frontend, and devops skills, so it is not clearly distinct.	3 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (754 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/ai-product/SKILL.md
Commit: 1f67c44

Reviewed: about 16 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.