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

30%

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-product/SKILL.md

Quality

Content

40%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 body is a well-structured lean overview that correctly uses progressive disclosure to push detail into a real one-level-deep reference, and its Limitations/When-to-Use sections are appropriate. Its weaknesses are that the body itself carries no executable guidance or workflow sequence (everything is delegated) and the opening paragraph repeats marketing fluff from the description.

Suggestions

Add a short 'Quick start' snippet with one concrete executable example (e.g. a minimal structured-output-with-validation code block) so the body is actionable without loading the full guide.

Replace the rhetorical opener with a one-line capability summary to remove the duplicated marketing fluff and improve conciseness.

Split the monolithic detailed-guide.md into topic-specific references (e.g. rag.md, prompt-engineering.md, cost-optimization.md) with a navigation list in the body to reach progressive_disclosure 5.

Dimension	Reasoning	Score
Conciseness	The body is short and mostly efficient, but the opening rhetorical paragraph ('Every product will be AI-powered...') duplicates the description's marketing fluff and 'cost optimization that doesn't bankrupt you' is padded, fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	The body contains no executable code or commands — it only lists topic areas ('LLM integration patterns, RAG architecture...') and delegates everything to the detailed guide, matching 'minimal concrete guidance; high-level hints but missing specific steps'.	2 / 5
Workflow Clarity	No sequenced workflow or validation checkpoints appear in the body; it only instructs reading the detailed guide. While it signals the guide's validation requirements are mandatory, the body itself offers only a rough 'read the guide then act' sequence with many gaps.	2 / 5
Progressive Disclosure	The body is a clean overview pointing to a single clearly-signaled, one-level-deep reference (references/detailed-guide.md, which exists), with well-organized sections (Detailed Guide, When to Use, Limitations). It stops short of 5 because all detail lives in one monolithic 19KB file rather than topic-split references.	4 / 5
	Total	11 / 20 Passed

Description

20%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 marketing rhetoric rather than a capability statement: it names the AI-product domain but gives no concrete actions, no natural trigger phrases, and no explicit 'when to use' guidance, and it uses second-person voice. It is distinguishable only at the broadest level and would frequently collide with adjacent skills.

Suggestions

Rewrite in third person listing concrete capabilities, e.g. 'Designs LLM integrations, RAG pipelines, and production-grade prompt systems; optimizes AI feature cost and latency.'

Add an explicit 'Use when...' clause with natural trigger terms users say (LLM integration, RAG, prompt engineering, AI feature, chatbot, cost optimization).

Replace the rhetorical opener with a direct capability + trigger sentence to satisfy both the 'what' and 'when' halves of completeness.

Dimension	Reasoning	Score
Specificity	The description is pure rhetoric ('Every product will be AI-powered... build it right or ship a demo that falls apart') with no concrete actions; it only names the AI-product domain. The second-person 'you'll' triggers the voice penalty, reducing the base score of 2 by one to 1.	1 / 5
Completeness	It gives a vague rhetorical 'what' and has no 'Use when...' clause at all, fitting the 'vague what and no when' anchor; the missing-trigger cap of 3 does not bind since it scores below that.	2 / 5
Trigger Term Quality	It offers only generic terms ('AI-powered', 'demo', 'production') and omits the natural trigger phrases users would actually say ('LLM', 'RAG', 'prompt engineering', 'AI feature'), matching the 'one or two generic keywords; missing natural phrases' anchor.	2 / 5
Distinctiveness Conflict Risk	'Every product will be AI-powered' is extremely broad and would overlap with many AI-related skills, matching the 'very broad; high overlap risk' anchor rather than the fully generic 1.	2 / 5
	Total	7 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/ai-product/SKILL.md
Commit: b1aebac

Reviewed: ~18 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.