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.
67
56%
Does it follow best practices?
Impact
83%
2.07xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/llm-application-dev/skills/rag-implementation/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both what the skill does and when to use it, with good trigger term coverage for the RAG domain. Its main weakness is that the 'what' portion is somewhat high-level—it says 'build RAG systems' without enumerating specific concrete actions like chunking, embedding, indexing, or retrieval pipeline configuration. The distinctiveness could also be improved by narrowing scope away from generic LLM terms.
Suggestions
Add more specific concrete actions such as 'chunk documents, generate embeddings, configure retrieval pipelines, implement reranking' to improve specificity.
Narrow the generic terms like 'LLM applications' to reduce potential overlap with other AI/LLM-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (RAG systems) and mentions some components (vector databases, semantic search), but doesn't list multiple concrete actions beyond 'build'. Missing specifics like chunking strategies, embedding generation, retrieval pipeline configuration, or reranking. | 2 / 3 |
Completeness | Clearly answers both 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 an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'RAG', 'Retrieval-Augmented Generation', 'vector databases', 'semantic search', 'document Q&A', 'knowledge bases', 'LLM applications'. These are terms users naturally use when seeking this capability. | 3 / 3 |
Distinctiveness Conflict Risk | While RAG is a specific niche, terms like 'LLM applications' and 'knowledge bases' are broad enough to potentially overlap with general LLM development skills, prompt engineering skills, or broader AI application building skills. The RAG-specific terms help but the scope is somewhat wide. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a comprehensive RAG reference manual dumped into a single file. While the code examples are high quality and executable, the content is far too verbose for a skill file—it catalogs options Claude already knows about, lacks workflow structure with validation steps, and fails to use progressive disclosure to manage its substantial volume of content.
Suggestions
Reduce the SKILL.md to a concise overview (~100 lines) with the Quick Start example and brief pattern summaries, moving vector store configs, chunking strategies, advanced patterns, and evaluation code into separate referenced files.
Add an explicit end-to-end workflow with numbered steps and validation checkpoints (e.g., verify index creation, validate chunk sizes, test retrieval quality before deploying).
Remove catalog-style listings (embedding model tables, vector DB options) that Claude already knows—instead, provide opinionated defaults with brief justification.
Add error handling and feedback loops: what to do when retrieval returns irrelevant results, how to diagnose poor RAG quality, and when to adjust chunk sizes or switch retrieval strategies.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Lists every vector database option, every embedding model, every chunking strategy, every retrieval pattern with full code examples. Much of this is reference material Claude already knows (e.g., what BM25 is, what MMR does, basic LangChain usage). The embedding model table with dimensions and the exhaustive vector store configurations are catalog-style content that bloats the skill significantly. | 1 / 3 |
Actionability | All code examples are concrete, executable, and use real library imports with proper syntax. The Quick Start section provides a complete, runnable LangGraph RAG pipeline, and each advanced pattern includes copy-paste ready code with real class names and parameters. | 3 / 3 |
Workflow Clarity | Despite being a multi-step system (ingest → chunk → embed → store → retrieve → generate), there is no clear end-to-end workflow with validation checkpoints. No guidance on verifying embeddings were stored correctly, no error handling for failed retrievals, no validation that chunks are appropriate size, and no feedback loops for when retrieval quality is poor. | 1 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. All advanced patterns, all vector store configs, all chunking strategies, all optimization techniques, and evaluation metrics are inlined. This content desperately needs to be split into separate reference files (e.g., VECTOR_STORES.md, CHUNKING.md, PATTERNS.md) with the SKILL.md serving as a concise overview. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (543 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
91fe43e
- 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.