llm-application-dev

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Quality

78%

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/llm-application-dev/SKILL.md

Quality

Content

72%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.

A well-organized, highly actionable catalog of LLM-application patterns with lean code examples. Its main weaknesses are the absence of validation checkpoints or feedback loops (it is a reference catalog, not a guided workflow) and no progressive disclosure via bundled reference files.

Suggestions

Add a short end-to-end workflow (e.g., embed -> retrieve -> generate -> validate answer against retrieved context) with an explicit validation/retry checkpoint so workflow_clarity reflects a real sequence.

Move detailed per-provider API patterns or extended examples into reference files (e.g., references/openai-pattern.md) and link them from SKILL.md to enable progressive disclosure.

Trim redundant inline comments (e.g., '// Rate limit - exponential backoff', '// vector column') since the surrounding code already conveys the intent.

Dimension	Reasoning	Score
Conciseness	Mostly lean section headers plus code with almost no concept explanation, matching 'efficient; minor instances of over-explanation'; a few redundant inline comments like '// Rate limit - exponential backoff' and '// vector column' keep it just below the lean 5 anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready TypeScript covering the common cases (OpenAI/Anthropic calls, streaming, RAG pipeline, chunking, retry with backoff), matching the top anchor.	5 / 5
Workflow Clarity	Functions as a pattern catalog rather than a sequenced workflow; the RAG section shows a numbered 1-4 sequence but has no validation checkpoints, matching 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	No bundle files exist and all ~210 lines are inlined under headers with no external references, matching 'some structure but could be better organized'; detailed API patterns that could live in separate reference files are inlined.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong description that clearly states capabilities and provides explicit, natural trigger guidance. Minor gaps in synonym/extension coverage and edge-capability breadth keep it just below the top anchor on specificity, triggers, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the LLM-app domain plus three concrete capabilities ('prompt engineering, RAG patterns, and LLM integration'), matching the 'several specific actions; minor gaps' anchor; not 5 because coverage is not exhaustive (no mention of evals, agents, function-calling).	4 / 5
Completeness	Explicitly states both the 'what' ('Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration') and an explicit 'Use for...' when-clause with concrete triggers, matching the top anchor.	5 / 5
Trigger Term Quality	Provides natural triggers ('AI-powered features, chatbots, or LLM-based automation') users would actually say, matching 'good keyword coverage; a few natural terms missing'; not 5 because synonyms like 'GPT', 'RAG app', or 'copilot' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear LLM-application niche with distinct triggers and minimal conflict risk; not 5 because it could still marginally overlap with general API-integration or coding skills.	4 / 5
	Total	17 / 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: MoizIbnYousaf/ai-agent-skills
Path: skills/llm-application-dev/SKILL.md
Commit: 1159592

Reviewed: 19 days 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.