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.

Quality

55%

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-wrapper-product/SKILL.md

Quality

Content

55%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 highly actionable with executable code and useful reference tables, but it is a monolithic wall of text with no progressive disclosure and workflows lacking explicit validation checkpoints. Duplicate section headers signal organizational issues.

Suggestions

Split large reference material (model selection tables, validation checks, collaboration workflows) into separate reference files with clearly signaled one-level-deep links.

Add explicit validation/verification checkpoints to the Sharp Edges fix workflows, especially for cost shutoff and rate-limit handling.

Remove duplicate section headers (e.g., '## AI Product Architecture' following '### AI Product Architecture') and consolidate redundant blocks to improve conciseness.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient with executable code and tables, but it is a large monolithic body with some repetition (e.g., duplicate section headers like '## AI Product Architecture' following '### AI Product Architecture') and mild padding that could be trimmed.	3 / 5
Actionability	Provides concrete, executable JavaScript examples (API calls, retry logic, cost tracking) and reference tables covering common cases, with only minor gaps such as incomplete validateFacts stubs.	4 / 5
Workflow Clarity	Multi-step workflows appear in the Collaboration section, but the Sharp Edges fixes involve batch/destructive-style operations (cost shutoff, rate-limit handling) without explicit validation checkpoints, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one ~688-line document; content that clearly belongs in separate references (model tables, validation checks, collaboration workflows) is monolithic rather than split with one-level-deep references.	2 / 5
	Total	12 / 20 Passed

Description

56%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 clearly conveys the skill's purpose and niche, but omits any explicit 'Use when...' trigger guidance, which limits its completeness and trigger-term quality. Specificity and distinctiveness are reasonably strong.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when building AI wrappers, GPT/Claude products, or AI SaaS tools').

Include natural user keyword variations and file/term synonyms to improve trigger-term coverage.

Tighten the action list into a compact enumeration of concrete capabilities to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — wrapping AI APIs, building 'focused tools people will pay for,' prompt engineering, cost management, rate limiting — but coverage is broad rather than tightly enumerated.	4 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Mentions natural phrases like 'AI wrapper,' 'ChatGPT,' and 'AI APIs' but lacks common variations and the explicit 'Use when...' trigger keywords that a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The 'AI wrapper product' niche is fairly distinct from generic coding skills, with only minor overlap risk against closely related skills like micro-saas-launcher.	4 / 5
	Total	14 / 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 (689 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-wrapper-product/SKILL.md
Commit: 1f67c44

Reviewed: about 17 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.