Skip to main content
Using Claude

How to Use Claude Projects: Knowledge & Instructions to Cut Repetition

Claude Projects is a workspace that keeps materials and instructions in one place. Learn the difference between knowledge and instructions, how they stack with profile settings, steps, and tips.

By
🌐 This article was machine-translated and may contain inaccuracies. Read the Korean original if in doubt.

Re-uploading the same files and repeating the same explanations every time? Claude Projects is a workspace that keeps your materials and instructions in one place for a specific task or topic. Start a new chat inside a project and Claude automatically references the materials and instructions you've set.

🟢 Model references match the current lineup · model notice · Fable subscription
🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.

Fable 5 and 5.1 subscription (updated September 7, 2026): Claude Fable 5.1, released September 1, 2026, is the current Fable model and Fable 5 is now legacy. Plan terms are the same for both — Max and Team Premium plans include Fable at up to 50% of the weekly usage limit; Pro and Team Standard use usage credits (

🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.
0/M input, $50/M output tokens). The one-time
🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5 / Claude Haiku 4.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.
00 credit applied only to the Fable 5 transition and is not offered for 5.1. Some coding and debugging requests may be answered by an Opus model due to a security classifier (both models). See the Fable 5.1 guide and the Fable 5 availability guide for details.

Using Projects in 4 steps 1. Create by topic/task → 2. Add knowledge upload files → 3. Instructions rules & context → 4. Chat auto-referenced Every chat inside the project automatically references its knowledge and instructions.

What a project is made of

A project has two main parts.

  • Project Knowledge: materials you reference repeatedly — upload PDFs, documents, code, and text.
  • Custom Instructions: the rules and context Claude should follow in this project (tone, format, tech stack, what to avoid). They apply automatically to every chat in the project.

How it differs from profile settings

Account-wide profile settings (global preferences) are different from project instructions.

  • Profile settings = global. "How I work" (tone, format — shared across all chats).
  • Project instructions = this project only. "What I'm working on now" (this project's context and rules).

They stack — your profile loads first, then project instructions add on top. So you don't need to repeat in every project what's already in your profile.

Steps to use

  1. Create a project per task/topic. Use a specific name like "Q1 Product Launch."
  2. Add knowledge: upload the files/docs you'll reference repeatedly.
  3. Write instructions: the rules and context for this project.
  4. Chat: now chats in that project automatically reflect the knowledge and instructions.

Great for

  • Coding: tech stack/coding rules in instructions, key code/specs in knowledge → consistent help.
  • Writing: tone/style in instructions, past pieces/brand guide in knowledge → consistent voice.
  • Per client/workstream: a project per client to keep context separate.
  • Learning/research: gather related docs in one project and ask questions.
Project = knowledge + instructions + chatsKnowledgeuploaded docs/filesevery chat referencesInstructionstone, rules, roleapplies project-wideChatsrelated chatskept in one place→ all three apply in the background to every chatMenus/layout may vary by version · as of 2026.6

Tips

  • Use specific names ("EcoBottle Launch," not "Project 1").
  • Curate materials. Remove stale or irrelevant files. Projects have a context limit (reported to be on the order of ~200K tokens), so too much material can degrade reference quality.
  • Keep instructions concise — core rules only, to cut repeated explanation each chat.

Disclaimer: Availability, project counts, file sizes, and instruction-length limits vary by plan and time and change often (some figures come from unofficial sources, so accuracy isn't guaranteed). Projects are generally described as a paid-plan feature; free availability may vary. Verify the latest in claude.ai and official docs (support.claude.com). This site is not affiliated with Anthropic.

Was this helpful?

Keep reading

Claude's Skills Explore Tab Explained — What 60 Plugins Do, How to Use Them, and Whether They Run Automatically (Sept 2026)

What each plugin listed under Settings → Skills → Explore does, how you call it, and whether it can run with nobody around — based on the SKILL.md files of 60 installed plugins and Anthropic's official docs.

66

Can Claude Really 'One-Click' Write a Web Novel? What's Realistic

There's a hope that feeding Claude a premise is enough to get a finished serialized novel, but the tasks Claude is actually good at and what still needs a human writer are different things. Here's a realistic workflow using real features like Projects and Styles.

38

When Your Claude Character Drifts Mid-Conversation: Keeping Persona Context Stable with Projects

Long conversations can wear down a carefully built character setup. Here's how Claude's project instructions and knowledge features keep a persona consistent over time.

37

How to Save Claude Usage: A Practical Guide for Research and Experimentation

A few small changes to how you chat can meaningfully cut your Claude usage. Here's how project caching, turning off extended thinking, Claude Code commands, and the September 14 weekly limit change all fit together.

90