rag-implementation

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Quality

75%

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 ./plugins/llm-application-dev/skills/rag-implementation/SKILL.md

Quality

Content

68%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 highly actionable with a complete executable example and clean progressive disclosure to a verified reference file. Weakest spots are conciseness (mild over-explanation plus dated version info) and workflow clarity (no validation/feedback steps).

Suggestions

Remove the 'Purpose:' annotations that restate common knowledge (e.g., what a vector database or embeddings do) and keep only non-obvious guidance.

Move the dated '(2026)' embedding-model table into references/details.md or an 'old patterns' section so version drift does not bloat the core SKILL.md.

Add an explicit end-to-end workflow with a validation step (e.g., check retrieval quality / empty-context handling before generating) to give the sequence real checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient bullet/table formatting, but 'Purpose:' lines restate concepts Claude already knows and the dated '(2026)' model table is time-sensitive information not placed in a deprecated/old-patterns section.	3 / 5
Actionability	The Quick Start is a fully executable, copy-paste-ready LangGraph example with all imports, typed state, retrieve/generate nodes, graph wiring, and a usage call covering the common basic RAG case.	5 / 5
Workflow Clarity	A retrieve→generate sequence is present in the graph code, but there are no explicit validation checkpoints or feedback loops; the content reads more as a component catalog than a sequenced workflow.	3 / 5
Progressive Disclosure	The body is a clear overview with a single clearly-signaled, one-level-deep reference to references/details.md (verified present); consolidating all advanced topics into one file is a minor organization gap versus separate per-topic references.	4 / 5
	Total	15 / 20 Passed

Description

82%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 is well-constructed: third-person, concise, and clearly covering both capability and trigger context with a distinct RAG niche. Its only gap is that the 'what' lists just two concrete capabilities rather than a fuller action set.

Suggestions

Expand the 'what' clause to list more concrete actions (e.g., 'index documents, retrieve relevant context, and generate grounded answers') to lift specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('RAG systems for LLM applications') and 1-2 concrete capabilities ('vector databases', 'semantic search') but is not comprehensive, matching the anchor for naming domain plus a couple actions.	3 / 5
Completeness	Explicitly answers what ('Build RAG systems... with vector databases and semantic search') and when ('Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('RAG', 'Retrieval-Augmented Generation', 'semantic search', 'knowledge-grounded AI', 'document Q&A', 'external knowledge bases') that users would say, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear RAG niche with distinct triggers (knowledge-grounded AI, document Q&A, external knowledge bases) and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/llm-application-dev/skills/rag-implementation/SKILL.md
Commit: d6837ae

Reviewed: about 12 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.