A small, useful starting point
Claude resources,
carefully chosen.
Official references, practical studies from this publication, and a short list of tools worth knowing—kept intentionally simple.
No sponsored placements or affiliate links are used on this page. If that changes, it will be clearly disclosed.
Claude basics
Start with the official sources. These are the most reliable places to understand what Claude is and how to use it.
Claude
Use Claude on the web, desktop, or mobile for writing, analysis, learning, and everyday work.
Visit official resource ↗Developer toolClaude Code
Anthropic’s agentic coding tool for understanding codebases, making changes, and running development workflows.
Visit official resource ↗Official documentationAnthropic docs
The primary reference for Claude models, the API, prompt guidance, tools, and platform features.
Visit official resource ↗My useful guides
A practical beginner guide, followed by strong studies from the archive that help you build more dependable agent workflows.
Claude Code: from installation to your first useful workflow
A calm, practical walkthrough for understanding a project, making one safe change, and checking the result.
Start the guide →Claude Blog Study · 3 minSteering Claude Code
Put each Claude Code instruction in the control surface where it naturally belongs. The practical decision is not “how do I phrase this prompt?” It is: should this be always-on context, a scoped rule, a repeatable skill, an isolated subagent task, or a deterministic hook/permission?
Read the study →Claude Prompting Study · 4 minUse Examples Effectively
Examples are one of the most reliable ways to steer Claude's format, tone, and structure. Instead of only describing what a good answer should look like, demonstrate the pattern you want Claude to reproduce. A useful mental model: Instruction → tells Claude the rule.
Read the study →Claude Blog Study · 3 minParallelize the Work, Not the Uncertainty
Key concept: Parallelize independent work, then verify before synthesis.
Read the study →Claude Blog Study · 3 minRisk-Weighted Autonomy
Risk-weighted autonomy: give agents more freedom for routine, reversible, bounded actions and require stronger human review when actions are external, destructive, financial, legally meaningful, production-facing, or difficult to reverse.
Read the study →Tools I recommend
This is a deliberately short list, not a crowded directory. Each tool earns its place by helping with a distinct part of the work.
Claude
A flexible place to think through an idea, revise a draft, analyse material, or turn a rough question into a clearer plan.
Open tool ↗Building with codeClaude Code
Useful when the work lives in a codebase and benefits from an agent that can inspect, edit, and verify the project directly.
Open tool ↗API experimentsAnthropic Console
A practical workspace for testing prompts and model behaviour before committing an idea to an application.
Open tool ↗