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.

2.12x

Quality

72%

Does it follow best practices?

Impact

70%

2.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/rag-implementation/SKILL.md

The canonical home for this skill is rag-implementation in wshobson/agents

Quality

Content

57%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 broad, highly concrete RAG reference with executable code throughout, but it is a monolithic catalog: no sequenced end-to-end workflow with validation checkpoints, no external reference files, and some time-sensitive model/version detail that will age. The strongest dimension is actionability; the weakest are workflow clarity and progressive disclosure.

Suggestions

Split the body into reference files (e.g. references/vector-stores.md, references/advanced-patterns.md, references/chunking.md) and keep SKILL.md as a concise overview with one-level-deep, clearly signaled links — this is the lowest-cost fix for the progressive_disclosure score.

Add a sequenced implementation workflow with explicit validation checkpoints (e.g. 1. chunk and index documents, 2. verify indexed document/chunk counts, 3. run retrieval sanity checks, 4. evaluate with the metrics code before deploying).

Remove the introductory "Master Retrieval-Augmented Generation..." sentence and move the time-sensitive "Models (2026):" embedding table into a dated reference file; also fix the duplicate CohereRerank import and the missing "import os" in the Pinecone snippet.

Dimension	Reasoning	Score
Conciseness	The body is code-dense and mostly lean, but includes unnecessary padding ("Master Retrieval-Augmented Generation (RAG) to build LLM applications that provide accurate, grounded responses") and time-sensitive version details ("Models (2026):" table with model names/dimensions) not placed in a dated or deprecated section, plus a duplicated CohereRerank import. Not 2 because there is no extensive explanation of concepts Claude already knows; not 4 because the time-sensitive model table and intro fluff could be trimmed.	3 / 5
Actionability	The Quick Start is a complete, runnable LangGraph example and there are 15+ concrete snippets covering chunking, vector stores, reranking, and evaluation. Minor gaps keep it below 5: "os" is used but never imported in the Pinecone snippet, "evaluate_answer_quality" is called but undefined, and lines 447-448 import CohereRerank twice from two different modules.	4 / 5
Workflow Clarity	Content is organized as a component catalog rather than a sequenced build workflow; the implicit retrieve-then-generate sequence in Quick Start exists, but there are no validation checkpoints (e.g. verify indexing counts, retrieval sanity checks) between steps. Not 4 because checkpoints are absent rather than minor-gapped; not 2 because sections are coherently ordered and 'Common Issues' provides some implicit error-recovery guidance.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent) and ~565 lines are inlined in SKILL.md. Section headers give it structure, but content that clearly belongs in separate files — four full vector-store configuration blocks, five advanced patterns, four chunking strategies — is all inline, matching the 'some structure but content that should be separate is inline' anchor rather than the inlined-monolith of anchor 2.	3 / 5
	Total	13 / 20 Passed

Description

87%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.

Strong description: third-person voice, concrete capabilities, and an explicit 'Use when ...' clause with three natural trigger scenarios. Keyword coverage is good though a few common synonyms (retrieval, chatbot, grounding) are absent.

Dimension	Reasoning	Score
Specificity	"Build Retrieval-Augmented Generation (RAG) systems ... with vector databases and semantic search" plus "integrating LLMs with external knowledge bases" lists several concrete actions. Not 5 because coverage has minor gaps (chunking, reranking, and evaluation capabilities are never mentioned); not 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	Explicitly answers both: what ("Build Retrieval-Augmented Generation (RAG) systems for LLM applications 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	"Retrieval-Augmented Generation (RAG)", "document Q&A", "semantic search", and "knowledge bases" are phrases users would naturally say. A few natural terms are missing (e.g. "retrieval", "chatbot", "grounding"), keeping it below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (RAG / knowledge-grounded LLM apps) with distinct triggers ("knowledge-grounded AI", "document Q&A", "external knowledge bases") and minimal conflict risk with unrelated skills.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (571 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/rag-implementation/SKILL.md
Commit: a65ce00

Reviewed: 6 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.