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

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

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 is a motivational or marketing statement rather than a functional skill description. It provides zero information about what the skill does, what actions it performs, or when it should be selected. It would be completely ineffective for skill selection in a multi-skill environment.

Suggestions

Replace the rhetorical statement with concrete actions the skill performs, e.g., 'Guides architecture and implementation of AI-powered product features, including prompt engineering, model selection, and API integration.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about building AI features, integrating LLMs into products, or moving AI prototypes to production.'

Remove the opinion-based framing ('The question is whether you'll build it right') and use third-person descriptive voice focused on capabilities.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It reads as a marketing tagline or opinion statement rather than describing what the skill does. There are no verbs indicating capabilities like 'extract', 'analyze', 'generate', etc.	1 / 3
Completeness	The description answers neither 'what does this do' nor 'when should Claude use it'. There is no 'Use when...' clause or any equivalent guidance. It is a rhetorical statement, not a functional description.	1 / 3
Trigger Term Quality	The only potentially relevant keyword is 'AI-powered', which is extremely generic. There are no natural terms a user would say when needing a specific skill. 'Production', 'demo', and 'ship' are too vague to serve as meaningful triggers.	1 / 3
Distinctiveness Conflict Risk	The description is so vague and generic that it could apply to virtually any AI-related skill. It provides no distinguishing characteristics that would help Claude select it over any other skill.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is a comprehensive but bloated reference document that explains many concepts Claude already understands (probabilistic outputs, prompt injection, API failures). It suffers from significant redundancy between the Patterns and Sharp Edges sections, lacks proper markdown code fencing in several places, and presents no coherent workflow or progressive disclosure structure. The content would benefit greatly from being condensed to novel, project-specific guidance and split across multiple referenced files.

Suggestions

Cut content by 60-70%: Remove explanations of why LLMs are probabilistic, what prompt injection is, why APIs fail, etc. Focus only on project-specific patterns, preferred libraries, and concrete configurations Claude wouldn't already know.

Fix markdown code fencing: Several code blocks in the Patterns section lack ```typescript fencing, making them non-executable and harder to parse.

Split into multiple files: Create separate referenced files for RAG patterns (RAG.md), prompt management (PROMPTS.md), cost optimization (COSTS.md), and sharp edges (SHARP_EDGES.md), with SKILL.md serving as a concise overview with links.

Add a clear workflow with validation: Define a step-by-step process for integrating an LLM feature (e.g., 1. Design prompt → 2. Add validation schema → 3. Implement streaming → 4. Add cost tracking → 5. Test with regression suite) with explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Extensively explains concepts Claude already knows (what LLMs are, that they're probabilistic, what prompt injection is, what fine-tuning vs RAG means). Massive redundancy — the 'Sharp Edges' section repeats patterns already covered (structured output validation, streaming, caching) with lengthy 'Why this breaks' explanations of obvious concepts. The 'Validation Checks' and 'Collaboration' sections add low-value content.	1 / 3
Actionability	Code examples are present and mostly executable (TypeScript with OpenAI SDK, Zod validation, streaming), but many code blocks lack proper markdown fencing (the Patterns section), some are pseudocode-like (RAG hybrid search with invalid JS syntax like `topK: 20` as a bare argument), and the Sharp Edges section largely repeats the same patterns with slight variations rather than adding new actionable guidance.	2 / 3
Workflow Clarity	No clear multi-step workflow with sequencing or validation checkpoints. The content is organized as a catalog of independent patterns and anti-patterns rather than a coherent workflow. The 'Collaboration' section hints at workflows but they're just lists without validation steps. For a skill covering production AI integration (destructive/batch operations like RAG indexing, prompt deployment), the absence of explicit validation checkpoints is a significant gap.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. RAG architecture, prompt engineering, cost optimization, and UX patterns could each be separate referenced documents. No bundle files exist, and no references are made to any. Everything is inlined in one massive file.	1 / 3
	Total	5 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: boisenoise/skills-collections
Commit: cfced3a

Reviewed: about 15 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.