ai-wrapper-product

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.

Quality

52%

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 ./.agent/skills/ai-wrapper-product/SKILL.md

Quality

Content

22%

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

This skill is essentially a table of contents with no actionable content in the main file. It lists 15 sub-skills but provides zero executable examples, no workflow guidance, and no quick-start material. The SKILL.md should serve as a useful standalone overview with at least basic actionable guidance, not just a link index.

Suggestions

Add a 'Quick Start' section with a concrete, executable example of building a basic AI wrapper (e.g., a simple FastAPI endpoint wrapping an OpenAI call with cost tracking).

Include a high-level workflow showing the recommended sequence for building an AI wrapper product (architecture → model selection → prompt engineering → cost management → launch), with validation checkpoints.

Add at least one inline code example for the most common pattern (e.g., a prompt template with output validation) so the skill is actionable without requiring navigation to sub-skills.

Remove the redundant 'Capabilities' bullet list since each capability is already represented as a linked sub-skill below.

Dimension	Reasoning	Score
Conciseness	The capabilities list is somewhat redundant given the sub-skill links that follow, and the introductory paragraph includes some unnecessary flavor text ('AI wrappers get a bad rap'). However, it's not excessively verbose overall.	2 / 3
Actionability	The skill body contains zero executable code, no concrete commands, no specific examples, and no actionable instructions. It is entirely a table of contents pointing to sub-skills with no inline guidance whatsoever.	1 / 3
Workflow Clarity	There is no workflow, no sequencing of steps, and no validation checkpoints. The numbered list is just a link index, not a process. For a skill covering cost management, API integration, and output validation, the absence of any workflow guidance is a significant gap.	1 / 3
Progressive Disclosure	The skill does reference 15 sub-skill files with clear one-level-deep links, which is good structure. However, since no bundle files are provided, we cannot verify these references exist. More importantly, the SKILL.md itself contains almost no substantive content—it's essentially only a table of contents with no quick-start or overview content to orient the reader before drilling into sub-skills.	2 / 3
	Total	6 / 12 Passed

Description

82%

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 is a reasonably well-crafted description that clearly identifies its niche (AI API wrapper products) and includes explicit trigger terms. Its main weaknesses are that the capabilities listed are more like topic areas than concrete actions, and the use of 'Expert in' framing plus some broad terms like 'AI SaaS' could cause mild overlap with adjacent skills. The explicit 'Use when' clause with natural trigger terms is a strong point.

Suggestions

Replace topic areas with concrete actions, e.g., 'Designs API proxy architectures, implements token budgeting and cost controls, engineers production prompts, sets up rate limiting and caching layers' instead of 'Covers prompt engineering for products, cost management, rate limiting'.

Narrow distinctiveness by adding exclusions or sharper boundaries, e.g., 'Not for general AI/ML model training or fine-tuning — focused specifically on wrapping existing AI APIs into paid products'.

Dimension	Reasoning	Score
Specificity	Names the domain (AI API wrapper products) and mentions some actions like prompt engineering, cost management, rate limiting, and building defensible businesses. However, these are more topic areas than concrete actions — it doesn't list specific things it does like 'design pricing models', 'implement token budgeting', or 'architect API proxy layers'.	2 / 3
Completeness	Clearly answers both 'what' (building products that wrap AI APIs, covering prompt engineering, cost management, rate limiting, defensible businesses) and 'when' with an explicit 'Use when:' clause listing trigger terms.	3 / 3
Trigger Term Quality	The 'Use when' clause includes natural terms users would say: 'AI wrapper', 'GPT product', 'AI tool', 'wrap AI', 'AI SaaS'. These are realistic phrases a user building such a product would use. It also mentions specific API providers (OpenAI, Anthropic) in the body text.	3 / 3
Distinctiveness Conflict Risk	The niche of AI wrapper products is fairly specific, but terms like 'AI SaaS' and 'AI tool' could overlap with general AI development skills or SaaS building skills. The description explicitly differentiates from generic ChatGPT clones, which helps, but the broad coverage of 'building defensible AI businesses' could cause overlap with business strategy skills.	2 / 3
	Total	10 / 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
Path: .agent/skills/ai-wrapper-product/SKILL.md
Commit: c4a059b

Reviewed: 1 day 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.