agentleFS
TakaGotoTakaGoto/rag-learning-academy/.claude/skills/glossary/SKILL.md

glossary

Skill24 starsChanged 19 days agoMITView on GitHub

Look up RAG terminology and concepts

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use readme, test-driven-development and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • kasperjungeSkill

    readme

    Generate beautiful, comprehensive README.md files for any codebase. Use when asked to create a README, improve documentation, or when the user says "readme", "/readme", or wants help documenting their project. Analyzes the codebase structure, dependencies, and code to produce professional documentation.

    Also in 3 projects that use this

  • OpenAISkill

    test-driven-development

    Use when implementing any feature or bugfix, before writing implementation code

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user provides a term (e.g., /glossary embeddings), define that term.

    line 16
  2. Very specific:

    If the user provides a module number (e.g., /glossary module 3), list all key terms for that module.

    line 17
  3. Distinctive:

    If no argument is given, present the full glossary organized by category.

    line 18
  4. Distinctive:

    If the learner asks "what does X mean in the context of Y?", tailor the explanation to that specific context.

    line 100
  5. Distinctive:

    If they ask to compare two terms, provide a brief comparison highlighting the key difference.

    line 101
  6. Distinctive:

    If they seem confused, offer the simpler analogy first and build up to the technical detail.

    line 102
  7. Distinctive:

    Keep definitions precise — do not conflate terms that have distinct meanings

    line 112
  8. Distinctive:

    Use consistent terminology throughout (match what the curriculum uses)

    line 113
  9. Distinctive:

    Update examples to match the learner's tech stack when possible

    line 114

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Glossary: RAG Terminology and Concepts

Scope: This skill is a quick-reference dictionary — short, scannable definitions with analogies. For deep, multi-layered explorations of how a concept works and why, use /explain.

An interactive glossary that provides clear, multi-layered definitions of RAG terminology. Designed to be a quick reference that also teaches.

Language awareness: See .claude/LANGUAGE_AWARENESS.md.

Step 1: Determine What to Look Up

  • If the user provides a term (e.g., /glossary embeddings), define that term.
  • If the user provides a module number (e.g., /glossary module 3), list all key terms for that module.
  • If no argument is given, present the full glossary organized by category.

Step 2: Present the Definition

For each term, provide a structured definition with these layers:

One-Line Definition

A concise, precise definition in one sentence. Example: "An embedding is a dense numerical vector that represents the semantic meaning of a piece of text."

Analogy

An everyday analogy that makes the concept intuitive. Example: "Think of embeddings like GPS coordinates for meaning — texts with similar meanings have coordinates that are close together on the map of all possible meanings."

Technical Detail

A deeper technical explanation for learners who want to understand the mechanism. Include relevant details like dimensions, algorithms, or mathematical concepts — but keep it accessible.

Code Example

A minimal code snippet in the learner's chosen language that demonstrates the concept in action:

Generate a minimal, runnable example in the learner's language. For instance, if explaining embeddings, show how to create one using the appropriate library.

Common Misconceptions

One or two things people often get wrong about this concept. Example: "Embeddings are not word-for-word encodings — the same word in different contexts will have different embeddings in contextual models."

Related Terms

Links to other glossary terms that are closely related, so the learner can explore connected concepts.

Curriculum Connection

Which module and lesson covers this concept in depth, so the learner can dive deeper if needed.

Step 3: Glossary Categories

Organize terms into these categories for browsing:

Foundations

  • RAG (Retrieval-Augmented Generation)
  • LLM (Large Language Model)
  • Embedding / Vector Embedding
  • Token / Tokenization
  • Context Window
  • Prompt / Prompt Template

Document Processing

  • Chunking / Chunk
  • Overlap (chunk overlap)
  • Document Loader
  • Metadata
  • Preprocessing / Cleaning

Retrieval

  • Vector Database / Vector Store
  • Similarity Search / Nearest Neighbor
  • Cosine Similarity
  • Top-k Retrieval
  • BM25 / Sparse Retrieval
  • Hybrid Search
  • Re-ranking

Generation

  • Grounding
  • Hallucination
  • Faithfulness
  • System Prompt
  • Few-shot Examples
  • Chain-of-Thought

Evaluation

  • RAGAS
  • Precision / Recall
  • MRR (Mean Reciprocal Rank)
  • Faithfulness Score
  • Answer Relevancy

Advanced Concepts

  • Hypothetical Document Embedding (HyDE)
  • Multi-hop Retrieval
  • Agentic RAG
  • Self-RAG
  • Query Decomposition
  • Recursive Retrieval

Step 4: Interactive Features

  • If the learner asks "what does X mean in the context of Y?", tailor the explanation to that specific context.
  • If they ask to compare two terms, provide a brief comparison highlighting the key difference.
  • If they seem confused, offer the simpler analogy first and build up to the technical detail.

Suggest 2-3 relevant next steps using slash commands:

  • /explain — get a deep-dive explanation if you want to go beyond the definition
  • /lesson — learn about this concept in a structured lesson with hands-on exercises
  • /quiz — test your understanding of the terms and concepts you just reviewed

Guidelines

  • Keep definitions precise — do not conflate terms that have distinct meanings
  • Use consistent terminology throughout (match what the curriculum uses)
  • Update examples to match the learner's tech stack when possible
  • Be honest when terms have multiple definitions in the field — note the ambiguity
  • This should feel like a knowledgeable colleague explaining things, not a textbook

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.