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.
19
7%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/ai-product/SKILL.mdQuality
Discovery
0%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, when it should be used, or what triggers should activate it. It would be completely ineffective for skill selection among even a small set of available skills.
Suggestions
Replace the rhetorical statement with concrete actions the skill performs (e.g., 'Scaffolds AI-powered product architectures, implements LLM integration patterns, and configures model serving pipelines').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about building AI products, integrating LLMs, or setting up ML infrastructure').
Remove the opinion-based framing and adopt third-person descriptive voice that clearly distinguishes this skill's niche from other AI-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It reads as a marketing tagline or opinion statement rather than describing any specific capabilities a skill would perform. | 1 / 3 |
Completeness | The description answers neither 'what does this do' nor 'when should Claude use it'. There is no 'Use when...' clause and no description of functionality. It is purely a rhetorical statement. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'AI-powered' which is extremely generic. There are no natural keywords a user would say when needing a specific skill. Terms like 'demo', 'production' are too vague to serve as 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 extremely verbose and redundant, explaining concepts Claude already knows at length while repeating the same patterns (validation, streaming, error handling) across multiple sections. The content would benefit enormously from being condensed to ~25% of its current size and split across multiple files. While it contains some useful code examples, the lack of proper markdown fencing in places, absence of clear workflows, and monolithic structure significantly reduce its effectiveness.
Suggestions
Reduce content by 70-80%: remove all 'Why this breaks' explanations, 'Symptoms' lists, and concept explanations that Claude already knows. Keep only the concrete code patterns and sharp edge fixes.
Consolidate redundant content: the Patterns section and Sharp Edges section cover the same topics (validation, streaming, caching, error handling). Merge into a single patterns section with inline warnings.
Split into multiple files: move Sharp Edges to SHARP_EDGES.md, Validation Checks to VALIDATION.md, and Collaboration to COLLABORATION.md, with clear one-level references from the main SKILL.md.
Add proper markdown code fences to all code blocks in the Patterns section, and fix syntax errors (e.g., `vectorDB.search(embedding, topK: 20)` is invalid JS).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Extensively explains concepts Claude already knows (what LLMs are, why they hallucinate, what prompt injection is, why streaming matters). Massive redundancy — the same patterns (validation, streaming, caching) appear in both 'Patterns' and 'Sharp Edges' sections with overlapping code examples. The 'Sharp Edges' section explains symptoms and 'why this breaks' for obvious failure modes. | 1 / 3 |
Actionability | Contains concrete TypeScript code examples that are mostly executable, 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 sheer volume dilutes the actionable content. The code is reasonable but not consistently copy-paste ready. | 2 / 3 |
Workflow Clarity | No clear multi-step workflow with sequencing or validation checkpoints. The 'Collaboration' section lists workflows but they are abstract labels (e.g., '1. AI architecture (ai-product)') with no concrete steps. For a skill covering complex multi-step processes like RAG implementation and AI product development, there are no explicit validation gates, feedback loops, or sequenced procedures. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. Everything — principles, patterns, sharp edges, validation checks, collaboration workflows — is crammed into a single file. No bundle files exist to support progressive disclosure, and the content would clearly benefit from being split into separate reference documents. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
81%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
- sickn33/antigravity-awesome-skills
- Commit
22710e9
- 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.