RAG

What it does

When your agent uses it

• Building RAG applications
• Creating document Q&A systems
• Integrating AI with knowledge bases

Example prompts

• “Use the rag skill to implement document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation…”
• “/rag”

Requirements

• Pre-approved tools (allowed-tools): Read, Write, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Choose Vector Database
2. 2Select Embedding Model
3. 3Implement Document Processing Pipeline
4. 4Configure Retrieval Strategy
5. 5Build RAG Pipeline
6. 6Evaluate and Optimize

What it can do on your machine

Read from SKILL.md and the folder at commit fe73fb3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Java), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

RAG loads about 1.8k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 539 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from giuseppe-trisciuoglio/developer-kit at commit fe73fb3, republished under its MIT licence (© giuseppe-trisciuoglio). 539 words, ~1,769 tokens.

name

rag

description

Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with knowledge bases.

allowed-tools

Read, Write, Bash

List<Embedding> embeddings = embeddingModel.embedAll(segments);
if (embeddings.isEmpty() || embeddings.get(0).dimension() != expectedDim) {
    throw new IllegalStateException("Embedding generation failed");
}

for (Document doc : documents) {
    int attempts = 0;
    while (attempts < 3) {
        try {
            store.add(embeddingModel.embed(doc).content(), doc.toTextSegment());
            break;
        } catch (EmbeddingException e) {
            attempts++;
            if (attempts == 3) throw new RuntimeException("Failed after 3 retries", e);
        }
    }
}

List<Document> documents = FileSystemDocumentLoader.loadDocuments("/docs");

InMemoryEmbeddingStore<TextSegment> store = new InMemoryEmbeddingStore<>();
EmbeddingStoreIngestor.ingest(documents, store);

DocumentAssistant assistant = AiServices.builder(DocumentAssistant.class)
    .chatModel(chatModel)
    .contentRetriever(EmbeddingStoreContentRetriever.from(store))
    .build();

String answer = assistant.answer("What is the company policy on remote work?");

EmbeddingStoreContentRetriever retriever = EmbeddingStoreContentRetriever.builder()
    .embeddingStore(store)
    .embeddingModel(embeddingModel)
    .maxResults(5)
    .minScore(0.7)
    .filter(metadataKey("category").isEqualTo("technical"))
    .build();

ContentRetriever webRetriever = EmbeddingStoreContentRetriever.from(webStore);
ContentRetriever docRetriever = EmbeddingStoreContentRetriever.from(docStore);

List<Content> results = new ArrayList<>();
results.addAll(webRetriever.retrieve(query));
results.addAll(docRetriever.retrieve(query));

List<Content> topResults = reranker.reorder(query, results).subList(0, 5);

Assistant assistant = AiServices.builder(Assistant.class)
    .chatModel(chatModel)
    .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
    .contentRetriever(retriever)
    .build();

assistant.chat("Tell me about the product features");
assistant.chat("What about pricing for those features?");  // Maintains context

© giuseppe-trisciuoglio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references, assets) in plugins/developer-kit-ai/skills/rag of giuseppe-trisciuoglio/developer-kit.

• SKILL.md
• assets/retriever-pipeline.java
• assets/vector-store-config.yaml
• references/document-chunking.md
• references/embedding-models.md
• references/langchain4j-rag-guide.md
• references/retrieval-strategies.md
• references/vector-databases.md

Open the folder on GitHubat commit fe73fb3