Organizing Your Work and Knowledge |

Introduction to Projects

Mon, 21 Sep 2026 00:00:00 +0000

TL;DR

Projects are self-contained workspaces with their own memory, chat histories, knowledge bases, and customized instructions. Think of them as dedicated environments for specific work streams.
Project knowledge enhances Claude’s understanding by letting you upload relevant documents that Claude references across all chats within that project. No more re-uploading the same files each time.
Project instructions guide Claude’s behavior—you can specify tone, expertise level, response style, and more. These instructions apply to every conversation within the project.
Projects scale automatically. When your knowledge base approaches context limits, Claude switches to searching your project knowledge and pulling in only what’s relevant, expanding capacity by up to 10x while maintaining response quality.
For Claude for Work users, projects enable collaboration. Share projects with teammates so everyone benefits from the same context, instructions, and accumulated knowledge.

What are Projects?

Projects are ideal for storing knowledge Claude should reference, organizing related chats around a specific topic or work area, and collaborating with team members who need access to the same shared context.

When to use Projects

Projects are particularly valuable when you’re working on something ongoing—not just a one-off question. Consider creating a project when you have a workflow with:

Reference materials you’ll use repeatedly (meeting notes, survey results, reports, historical data, etc.)
Consistent requirements for how Claude should respond (always use formal language, always cite sources, always follow our template)
Team collaboration needs where multiple people should work from the same foundation

Creating Project

Set up your project

Add new project from the left sidebar.
Give your project a descriptive name.
Add a brief description of what you’re working on.
Choose your visibility settings.

Add project instructions

Project instructions tell Claude how to behave across all conversations in this project.

Good project instructions typically include:

Context about what you’re working on
Process instructions
Tone and style preferences
Specific requirements

Saved instructions will apply to every chat in this project and work alongside any user preferences and styles you’ve set.

You can also use project instructions to automate workflows. Think of instructions as programming Claude’s behavior for this project.

For example, “When I upload a meeting transcript, create a structured summary using this template.”

Build your knowledge base

Your project’s knowledge base is where you upload documents that Claude should reference.

What to upload:

Reference documents (brand guidelines, style guides, templates)
Background materials (research reports, meeting notes, requirements docs)
Examples of work you want Claude to emulate
Technical documentation or specifications

Tip

Name your files descriptively. Claude uses file names to understand and retrieve the right information, e.g., “Q4-2024-Brand-Guidelines.pdf” is more helpful than “document1.pdf.”

Note

How projects handle large knowledge bases

Projects automatically scale to handle large amounts through a process called Retrieval Augmented Generation (RAG). At a high level, this means that Claude can automatically find and use the most relevant parts of your uploaded documents when answering, without you needing to tell it which file to look at.

When your project knowledge approaches the context window limit, Claude stops loading everything at once and instead searches your project’s files, retrieving only what’s relevant to your question. This expands your project’s capacity by up to 10x while maintaining response quality.

Best Practices for Projects

Start focused, then expand.

Begin with a specific use case rather than trying to create one project for everything. You can always add more content as you go.

Keep your knowledge base current.

Outdated documents can lead to outdated responses. Review and update your project knowledge periodically.

Write clear instructions.

Be specific about what you want. Vague instructions lead to inconsistent results.

Name your documents descriptively.

(e.g., ‘Q4-2025-Sales-Report.pdf’ not ‘report.pdf’) and group related files together. Claude uses filenames and proximity to understand relationships between documents.

Reference documents by name.

When asking questions, you can mention specific documents to help Claude focus its search: “Based on our Q3 report, what were the top customer concerns?”

Creating with Artifacts

Mon, 21 Sep 2026 00:00:00 +0000

What are Artifacts?

are the outputs you create with Claude: a document, a deck, a design, a dashboard, a prototype.

You can directly see the real thing take shape in a dedicated window alongside your conversation, ready to use and refine.

Claude creates an artifact when you ask for something that stands on its own — something you’ll want to edit, reuse, or share rather than just read once. If you want to ensure Claude creates an artifact, just say so: “Create this as an artifact.”

Designs, Decks, and Living Documents

Claude has a dedicated way to make each of the most common work deliverables:

Claude Design

creates visual work — landing pages, one-pagers, product mockups, interface prototypes.

You can bring in your design system so drafts come back in your brand, and edit directly on the canvas: drag, resize, and align anything.

Claude Slides

creates presentations.

Share the notes, report, or conversation you already have, and Claude outlines, writes, and lays out every slide.
You can edit any slide directly, add your own images, and present without leaving Claude — or export to PowerPoint or PDF when you’re ready.

Claude Docs

creates living documents — rich-text pages you and Claude write together.

Claude drafts in front of you, asks clarifying questions, and explains its choices in comments.
You and your colleagues can edit the same doc at the same time, and changes save as you go.
Claude can also pull data from your connected tools into charts and diagrams right in the page — a snapshot, not a live feed; ask Claude to refresh it when you need the latest.
Export to Google Docs or as a .docx file anytime.

These work together in one conversation, and you can ask for one from another: “turn this doc into a deck,” or “make a one-pager from this deck.”

Creating Artifact

Creating an artifact is as simple as having a conversation. Describe what you want in any conversation with Claude (the composer’s Output menu lets you pick a design, slides, or a doc), or start from the Artifacts tab, where you can pick a design, a deck, or a doc and describe what you need.

Creating an artifact is as simple as having a conversation. Describe what you want in any conversation with Claude (the composer’s Output menu lets you pick a design, slides, or a doc), or start from the Artifacts tab, where you can pick a design, a deck, or a doc and describe what you need.

Working on An Artifact

Once an artifact exists, you have three ways to change it — and you can mix them freely

Edit it directly.

Type straight into a doc, edit any slide, or drag and resize elements on a design canvas. Your edits and Claude’s can land side by side.

Comment for Claude.

Leave a comment on the exact element, slide, or passage you want changed, and Claude makes the change there.

In a doc, @-mention Claude in a comment and it replies explaining what it changed and why.

Just ask.

Keep talking in the conversation and Claude takes the next pass on the artifact, showing you every change it makes.

Tips for Getting the Most from Artifacts

Ask for the deliverable, not just the content.

“Summarize our Q3 results” gets you a chat reply; “turn our Q3 results into a one-page doc for the leadership team” gets you an artifact you can share and keep working on.

Be specific about what you want.

“Build a budget tracker” is good, but “Build a monthly budget tracker where I can input expenses by category, see a pie chart breakdown, and get a warning when I’m over budget” is better.

Describe the end user.

Telling Claude who will use the artifact helps it make appropriate design choices. “This flowchart is for new employees” leads to different results than “This flowchart is for the engineering team.”

Build on work you've already done.

The best artifacts come at the end of a conversation, when Claude already understands the problem.

Refresh data when you need it current.

Charts and diagrams embedded in a doc don’t update on their own — when you want the latest numbers, ask Claude to pull fresh data from your connected tools and update the chart.

Working with Skills

Mon, 21 Sep 2026 00:00:00 +0000

What are Skills?

Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Think of them as expertise packages—they teach Claude how to complete specific tasks in a repeatable way.

Types of Skills

Anthropic Skills

Created and maintained by Anthropic. These include enhanced document creation capabilities for Excel, Word, PowerPoint, and PDF files.
Claude invokes them automatically when relevant, so you don’t need to do anything special to use them.

Custom Skills

Ones you or your organization create for specialized workflows and domain-specific tasks.
For example, you might create a skill that applies your company’s brand guidelines to presentations, structures meeting notes in a specific format, or executes your organization’s data analysis workflows.

Using Skills in Practice

You typically don’t need to think about them—Claude handles skill selection automatically based on your request. When Claude uses a Skill, you’ll see it mentioned in Claude’s chain of thought as it works.

Security considerations

Because Skills can include executable code, it’s important to use them thoughtfully:

Only install custom Skills from trusted sources
Anthropic’s built-in Skills are tested and maintained by Anthropic
Custom Skills you upload are private to your individual account
If you’re installing a custom Skill from an external source, review its contents before use to understand what it does.

Creating Custom Skills

Custom Skills let you teach Claude your specific workflows, brand guidelines, and ways of working—so Claude can apply that knowledge automatically whenever it’s relevant.

The easiest way to create a custom Skill is through conversation with Claude itself. You don’t need to write code or manually create files—Claude handles the technical structure for you.

Start a new chat and tell Claude what you want to create.

For example: “I want to create a skill for writing quarterly business reviews” or “I need a skill that applies our brand guidelines to presentations.
Answer Claude’s questions.

Claude will interview you about your workflow, asking things like: What should this skill do? What makes good output for this type of work? Can you give examples of when you’d use this skill?
Upload reference materials if you have them.

Templates, style guides, brand assets, or examples of work you’re proud of all help Claude understand exactly what you’re looking for.
Save your skill.

When finished, Claude generates a file containing your properly structured skill.

Your custom Skill will appear in your Skills list alongside Anthropic’s built-in Skills. From that point forward, Claude will automatically invoke it whenever you work on relevant tasks—no manual triggering needed.

You can improve your skills with iteration — ask Claude to edit a skill and it will update the files for you.

Skills vs. Projects

projects store knowledge, skills perform tasks.

Projects are knowledge hubs.
- They hold the reference materials Claude needs to understand your work—project specs, meeting notes, research documents.
- When you upload files to a project, Claude draws on that information across every conversation within that project.
Skills are procedural machines.
- They encode how Claude should execute a task—the specific steps, order of operations, and methodology you want followed every time.
- Skills shine when you have repeatable workflows you want Claude to run consistently.

The two features complement each other: The project provides the what (information), the skill provides the how (process). A skill can reference knowledge stored in a project.

	Projects	Skills
Purpose	Store knowledge Claude references	Define processes Claude executes
Best for	Long-term context, reference materials, team collaboration	Repeatable workflows, multi-step tasks, consistent methodology
Example	Customer hub, research buddy, feedback generator	Process guidelines (like brand or legal), Blog drafting, PDF creation
Persistence	Knowledge available across all chats in the project	Instructions applied when the skill is invoked