CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-wrapper-product

You know AI wrappers get a bad rap, but the good ones solve real problems. You build products where AI is the engine, not the gimmick. You understand prompt engineering is product development. You balance costs with user experience. You create AI products people actually pay for and use daily.

45

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ai-wrapper-product/SKILL.md

The canonical home for this skill is ai-wrapper-product in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 provides concrete, actionable code for AI-wrapper architecture, prompt engineering, and cost management, but is undermined by broken/nested code fences, outdated model IDs, missing validation checkpoints in the main flow, and broken cross-references in the Sharp Edges table. It is organized into sections but is monolithic with no progressive disclosure to reference files.

Suggestions

Fix the malformed code fences: the Wrapper Stack diagram and section headings are trapped inside ```python/``` blocks and several fences are nested or unclosed, which breaks rendering and copy-paste.

Replace outdated model IDs (claude-3-haiku-20240307, Claude 3.5 Sonnet, GPT-4o) with current model references, or move them to a clearly marked deprecated/old-patterns section.

Resolve the Sharp Edges table references ("## Controlling AI Costs", "## Handling Rate Limits", etc.) by adding those sections or linking to real reference files, and fold explicit validate→retry→fallback checkpoints into the main generation flow.

DimensionReasoningScore

Conciseness

The body is mostly efficient with code and tables rather than explanatory padding, but the opening paragraph repeats the frontmatter description verbatim and the aspirational intro/capabilities prose could be tightened, fitting the "mostly efficient but some unnecessary content" anchor.

3 / 5

Actionability

Concrete JavaScript examples are provided (generateContent, prompt templates, cost tracking, usage limits), but several code fences are broken/nested (e.g., a ```python block wrapping a markdown heading and an unclosed diagram) and the examples use outdated model IDs (claude-3-haiku-20240307), so they fall short of copy-paste ready.

3 / 5

Workflow Clarity

A sequence exists via the Wrapper Stack diagram and the numbered generateContent steps, but validation checkpoints are only implicit (retry/validation appear in a table, not in the flow), and the Sharp Edges table points to sections ("## Handling Rate Limits", "## Handling Hallucinations") that do not exist in the document.

3 / 5

Progressive Disclosure

The body has section structure (Capabilities, Patterns, Anti-Patterns, Sharp Edges) but is a single ~280-line monolithic file with no bundle files and no one-level-deep references; the broken Sharp Edges cross-references further weaken navigation, fitting the "some structure but could be better organized" anchor.

3 / 5

Total

12

/

20

Passed

Description

45%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 reads as a second-person persona statement rather than a capability + trigger description: it names the AI-wrapper domain but uses generic aspirational language and omits any "Use when..." trigger guidance. Specificity is further penalized for second-person voice.

Suggestions

Rewrite in third person with concrete capabilities (e.g., "Architects AI-powered products: designs prompt templates, tracks API token costs, selects models, validates structured output").

Add an explicit trigger clause, e.g., "Use when building or pricing an AI-wrapper product, managing LLM API costs, or selecting models for a productized AI feature."

Drop the aspirational persona framing ("You know AI wrappers get a bad rap...") to reduce fluff and overlap with general product-building skills.

DimensionReasoningScore

Specificity

The description names the domain ("AI products", "AI wrappers") but the actions are generic and aspirational ("build products", "balance costs", "create AI products people actually pay for") rather than concrete capabilities; second-person voice ("You build...", "You understand...") triggers the -1 specificity penalty, pulling a base of 3 down to 2.

2 / 5

Completeness

A "what" is present (building AI-wrapper products, managing costs), but there is no "Use when..." clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "AI wrappers", "AI products", and "prompt engineering" appear, but common natural variations and explicit trigger phrasing users would actually say are missing, fitting the "some relevant keywords but missing variations" anchor.

3 / 5

Distinctiveness Conflict Risk

The AI-wrapper niche is somewhat specific, but the vague aspirational phrasing and explicit related-skills overlap (llm-architect, micro-saas-launcher) leave moderate overlap risk with similar skills.

3 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.