start
Skill24 starsChanged 19 days agoMITView on GitHub
Begin your RAG learning journey — assess your level and pick a learning path
135 other projects use a version of this.
Adopted by
Most recently taken up by
- flavien-ia/hypervibe-harnesstheir own version, first seen Nov 15, 2026
- srinator22/agent-kerneltheir own version, first seen Nov 15, 2026
- librosdeia/builder-method-claude-plugintheir own version, first seen Nov 15, 2026
- willink-oss/willink-claude-kittheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- relai-ai/agent-eval-looptheir own version, first seen Nov 15, 2026
Used with
Projects with it also use setup-engine, team-audio and 10 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.
CoralGameSkillsetup-engine
Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.
Also in 13 projects that use this
CoralGameSkillteam-audio
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Also in 13 projects that use this
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
lilangMaxSkillstory-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 11 projects that use this
- +5 more from CoralGame
- +3 more from lilangMax
Other versions135 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 135
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- anthropics/knowledge-work-plugins★ 36ksame name
- openai/plugins★ 7.8ksame name
- SterlingChin/marvin-template★ 1ksame name
- educlopez/ui-craft★ 441same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- dsifry/metaswarm★ 432same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- ansvisor/ansvisor★ 241same name
- alexeykrol/claude-code-starter★ 194same name
125 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architectureSkill
- audit-contentSkill
- benchmarkSkill
- break-itSkill
- buildSkill
- challengeSkill
- code-reviewSkill
- compareSkill
- debug-ragSkill
- evaluateSkill
- explainSkill
- fixSkill
- glossarySkill
- journalSkill
- lessonSkill
- paper-reviewSkill
- quizSkill
- recapSkill
- roadmapSkill
- sandboxSkill
- triageSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 9 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 122 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Before anything else, give a clear, casual picture of what they're about to learn.
- Distinctive: line 38
Default to Python if they skip or say "whatever."
- Distinctive: line 54
If they pick a track (1, 2, or 3), go to Step 3: Create Learner Profile.
- Distinctive: line 56
If they say "assess me" or similar, go to Step 4: Background Assessment.
- Very specific: line 60
Create the file progress/learner-profile.md with the following structure:
- Distinctive: line 83
Ask the following questions one at a time.
- Distinctive: line 135
Before sending the learner off, give them something tangible.
- Very specific: line 137
Create sandbox/data.txt with 5-8 short paragraphs about RAG basics (use the content from Module 01 as source material)
- Very specific: line 138
Create sandbox/pipeline.[ext] (in their chosen language) that:
- Very specific: line 145
Create sandbox/README.md with run instructions
- Distinctive: line 147
Run the pipeline and show the output: "Here's your first RAG retrieval.
- Distinctive: line 149
If dependency installation is needed, guide them through it first.
- Distinctive: line 161
Keep the tone warm, encouraging, and practical throughout.
“Common” is measured: kept by at least 6 in 10 of the 122 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.
Files
Start: Begin Your RAG Learning Journey
Step 0: Welcome & Context
Before anything else, give a clear, casual picture of what they're about to learn. Follow the project's voice & tone (see CLAUDE.md) — conversational, direct, like a smart friend explaining something cool:
Here's the short version: LLMs are smart but they don't know anything about your data. RAG fixes that. You grab relevant documents, stuff them into the prompt, and suddenly the model can answer questions about your PDFs, your codebase, your product docs — accurately, with sources.
By the end of this, you'll be able to build that system yourself. Not just follow a tutorial — actually understand every piece well enough to debug it when things go wrong (and they will).
Briefly explain the learning structure: 9 modules, 3 guided projects, 17 slash commands. They'll learn by building, not just reading.
Mention the two paths: API path (OpenAI + Anthropic keys, computation in the cloud) or local/free path (Ollama, no cost but needs hardware). If they plan to use local models, add this note:
Heads up: Running LLMs locally with Ollama needs 8-16GB of free RAM. If your machine has 8GB total, close heavy apps (browsers, Docker, IDEs) before running models. If you hit slowdowns or crashes, switch to the API path — local embedding models are lightweight but local LLMs are demanding. You can always mix: use local embeddings with a cloud LLM.
Step 1: Choose Your Programming Language
Present the language options. Wait for the learner to choose before continuing.
What language do you want to code in?
- Python (default) — Best RAG ecosystem. LangChain, LlamaIndex, ChromaDB, RAGAS, sentence-transformers all native. Every exercise works out of the box.
- TypeScript — Solid ecosystem. LangChain.js, ChromaDB client, OpenAI SDK. Most exercises translate directly; a few evaluation tools (RAGAS) need a Python fallback or manual implementation.
- Go — Limited RAG tooling. No LangChain equivalent — you'll build more from scratch, which means you'll learn the internals deeply. Some exercises need adaptation.
- Rust — Very limited RAG tooling. qdrant-client exists, but most RAG libraries are Python/TS. Recommended only if you're already fluent in Rust and want the challenge.
Not sure? Pick Python — you can always switch later by editing your profile.
Default to Python if they skip or say "whatever."
Step 2: Choose Your Track
Present the three tracks and let the learner self-select. Also offer the assessment as an option for those who aren't sure. Wait for the learner to choose before continuing.
Pick your track:
- Beginner — Start from scratch. What RAG is, document processing, embeddings, your first retrieval pipeline. Lots of guided examples. (Modules 1–4)
- Intermediate — You know the basics. Dive into embeddings, vector databases, retrieval strategies, and prompt engineering. More independence, more architecture decisions. (Modules 3–7)
- Advanced — You've built RAG before. Focus on generation quality, evaluation, agentic RAG, GraphRAG, and production deployment. You'll build systems, not just components. (Modules 6–9)
Not sure? I can ask 5 quick questions to help you figure out where you fit. Just say "assess me."
If they pick a track (1, 2, or 3), go to Step 3: Create Learner Profile.
If they say "assess me" or similar, go to Step 4: Background Assessment.
Step 3: Create Learner Profile
Create the file progress/learner-profile.md with the following structure:
# Learner Profile
- **Track**: [Beginner/Intermediate/Advanced]
- **Language**: [Python/TypeScript/Go/Rust]
- **Started**: [today's date]
- **Assessment**: self-selected
## Current Module
Module [first module in track: 01 for Beginner, 03 for Intermediate, 06 for Advanced]
## Completed
(none yet)Also create progress/module-tracker.md initialized with empty checkboxes for every lesson in the assigned track.
Then proceed to Step 7: Next Steps.
Step 4: Background Assessment
Ask the following questions one at a time. Wait for each answer before proceeding.
- Programming experience: "How comfortable are you with [their chosen language]?" (beginner=0 / intermediate=1 / advanced=2)
- ML knowledge: "Have you worked with machine learning concepts like training, inference, or model evaluation?" (none=0 / some exposure=1 / hands-on=2)
- LLM familiarity: "Have you used large language models (ChatGPT, Claude, open-source models) in code — not just chat UIs?" (never=0 / a few times=1 / regularly=2)
- Embeddings awareness: "Do you know what vector embeddings are and how they represent text?" (no idea=0 / heard of them=1 / have used them=2)
- Search/IR background: "Any experience with search engines, information retrieval, or databases?" (none=0 / basic SQL or search=1 / built search systems=2)
Step 5: Score and Place
Sum the points (0-10 range). Place into a track:
| Score | Track | Starting Module | Modules Covered |
| 0-3 | Beginner | Module 01 | 01 → 04 |
| 4-6 | Intermediate | Module 03 | 03 → 07 |
| 7-10 | Advanced | Module 06 | 06 → 09 |
Note: Track modules overlap intentionally — this provides continuity.
Step 6: Create Learner Profile (Assessed)
Present the recommended track. Ask the learner if they want to accept the recommendation or choose a different track.
Create the file progress/learner-profile.md with the following structure:
# Learner Profile
- **Track**: [Beginner/Intermediate/Advanced]
- **Language**: [Python/TypeScript/Go/Rust]
- **Started**: [today's date]
- **Programming level**: [answer]
- **ML knowledge**: [answer]
- **LLM familiarity**: [answer]
- **Embeddings awareness**: [answer]
- **Search background**: [answer]
- **Assessment score**: [total]/10
## Current Module
Module [first module in track]
## Completed
(none yet)Also create progress/module-tracker.md initialized with empty checkboxes for every lesson in the assigned track.
Then proceed to Step 7: Next Steps.
Step 7: Quick-Start Scaffold
Before sending the learner off, give them something tangible. Create a minimal working RAG pipeline so they have code running in their first session:
- Create
sandbox/data.txtwith 5-8 short paragraphs about RAG basics (use the content from Module 01 as source material) - Create
sandbox/pipeline.[ext](in their chosen language) that:- Loads the sample data
- Chunks it (fixed-size, 200 tokens)
- Embeds chunks with a local model (all-MiniLM-L6-v2 for Python/TS)
- Stores in ChromaDB (in-memory)
- Retrieves top-3 chunks for a sample query
- Prints results with similarity scores
- Create
sandbox/README.mdwith run instructions
Run the pipeline and show the output: "Here's your first RAG retrieval. It's basic, but it works. You'll understand every piece of this by the end of Module 2."
If dependency installation is needed, guide them through it first.
Step 8: Next Steps
Tell the learner their profile has been saved. Mention the milestone system: "Your track has milestones — concrete checkpoints that mark real progress. Run /roadmap anytime to see how far you've come."
Suggest next steps:
/lesson— start your first lesson (your sandbox pipeline will make the concepts concrete)/roadmap— view the full curriculum map and track your progress/journal— jot down thoughts or questions as you learn
Keep the tone warm, encouraging, and practical throughout.
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
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.

