Library — DistroSource

Everything digital. One source.

88 resources

Cheat sheet · Beginner · 5 min
Claude patterns cheat sheet
Prompt patterns that work well with Claude. 4 sections, 16 entries.
- Structure
- Reasoning
- Projects
Entries 16Claude
Lab · Beginner · 45 min
Lab: Long document Q&A under scrutiny
Ask Claude questions about a long document and verify every answer against the source.
- You have a fifty-page document and twenty questions a colleague needs answered by tomorrow.
Tasks 3Claude
Project · Intermediate · 4h
Project: A contract review assistant in a project
Set up a Claude project that reviews contracts against your checklist and produces a referenced summary, tested on three real contracts.
- Build a project whose instructions define a review checklist (payment, termination, liability, IP, renewal), an output format with section references and quotes, and a rule that ambiguous clauses are quoted and listed for a lawyer. Test on three contracts; verify every reference.
- Milestone 1: Set up
- Milestone 2: Test
Claude
Learning path · Beginner · 3h
Working with Claude
Get consistent, honest results from Claude for writing, analysis and long documents.
- Use Claude's strengths — long context, structured instructions, careful reasoning — for real work with checkable output.
- Skills: Structuring long inputs with tags, Asking for reasoning before answers, Projects and reusable instructions, Verifying long-document answers
Time 3hClaude
Cheat sheet · Beginner · 5 min
Agent components cheat sheet
The parts of an agent and the rule for each. 4 sections, 16 entries.
- Tools
- Loop
- Contract
Entries 16ClaudeChatGPT
Lab · Intermediate · 1h
Lab: Red-team your agent
Attack a support agent with adversarial inputs and confirm each is refused or handed over.
- Your support agent with an order-lookup tool is about to see real customers. Before it does, you try to make it misbehave.
Tasks 4ClaudeChatGPT
Project · Advanced · 10h
Project: A research agent with sources and a budget
Build a read-only agent that answers questions with cited findings, within a fixed budget, and passes an evaluation set.
- Build an agent with two tools — search and fetch — that answers a question with findings (each with URL and date), inferences (each with reasoning), and gaps. Enforce a budget of fifteen fetches and forty steps in code. Validate the report shape in code and reject uncited findings. Evaluate on twenty questions.
- Milestone 1: Tools and loop
- Milestone 2: Contract and validator
Claude
Learning path · Intermediate · 10h
Build your first production agent
From a single tool call to a budgeted, evaluated, approval-gated agent that can be left running.
- Design, build, evaluate and operate a tool-using agent with side effects gated by a person.
- Skills: Defining tools with schemas and failure returns, Writing a system prompt as a contract, Enforcing budgets in code, Building an evaluation set, Gating side effects
Time 10hClaudeChatGPT
Cheat sheet · Beginner · 5 min
Prompt structure cheat sheet
The parts of a prompt and the rule for each, on one screen. 4 sections, 18 entries.
- Parts
- Examples
- Reuse
Entries 18ChatGPTClaude
Lab · Beginner · 1h
Lab: Prompt surgery
Take a deliberately bad prompt, diagnose each of its faults, and fix them one at a time with evidence.
- A colleague's prompt for writing product descriptions produces inconsistent, padded, sometimes invented output. You have the prompt and ten inputs.
Tasks 4ChatGPTClaude
Project · Intermediate · 8h
Project: A tested prompt library for one job
Build five reusable prompts for one role's recurring tasks, each with variables, a reference run and a ten-case test set.
- Choose one role (support, sales, marketing, ops). Identify its five most repeated writing tasks. For each, produce a prompt template with variables, a filled reference run, and a ten-case test set with rubrics and a recorded pass rate. Deliver as a folder someone in that role could use on Monday.
- Milestone 1: Choose and draft
- Milestone 2: Reference and test
ChatGPTClaude
Learning path · Beginner · 5h
Prompts that hold up
From a one-line request to a reusable prompt with variables, tests and a maintenance routine.
- Write prompts that produce consistent, checkable output for a defined task, and maintain them as models change.
- Skills: Structuring a prompt: role, context, steps, format, constraints, Using examples well, Writing variables and a test set, Diagnosing bad output
Time 5hChatGPTClaude
Cheat sheet · Beginner · 5 min
Language model vocabulary cheat sheet
The terms you will meet, defined plainly. 4 sections, 16 entries.
- Mechanics
- Training
- Behaviour
Entries 16Any assistant
Lab · Beginner · 1h
Lab: Break a model on purpose
Provoke each failure mode deliberately, record the transcript, and write the check that would have caught it.
- You are preparing to roll an assistant out to a team and need a set of reproducible failures to show them, with the check that catches each.
Tasks 4Any assistant
Project · Beginner · 4h
Project: An honest guide to assistants for your team
Write a two-page guide for your team on what your chosen assistant does well, where it fails, and the rules for using it, with every claim tested by you.
- Produce a two-page internal guide for a real team: what the assistant is, three tasks it does well with evidence from your own tests, three ways it fails with examples you produced, and five rules for use. The guide must not contain a claim you did not test yourself.
- Milestone 1: Test the strengths
- Milestone 2: Reproduce the failures
Any assistant
Learning path · Beginner · 5h
How language models actually work
A practical path from what a model is to why it fails, so you use assistants well and explain them honestly.
- Explain what a language model does and does not do, predict where it will fail, and choose when to use one.
- Skills: Explaining tokens, context and prediction, Recognising hallucination and its causes, Choosing tasks that suit a model, Reading a model card
Time 5hAny assistant

Search