Not enough people are getting creative with Projects.
I've set up a few that I use all the time, each with its own custom instructions. This lets me organize my chats and easily switch Claude's response persona.
Here's what I have in the custom instructions for each one:
Before I start, here's how you can add custom instructions to a project.
Once you save the instructions, they are applied to all the chats in that specific project.
Personal
Instructions include a little bit about me (who am I, where I live, etc) and my personality type, my general preferences on things, overall personal goals and beliefs.
This is where all my random off-the-cuff chats go.
General work
Instructions include my role at Anthropic, what I do day to day and what I'm working on, the style of my writing and communication (with some examples).
I use this one a lot for things like emails, slack messages, and docs writing.
Fitness
Instructions include physical stats about myself like height and weight. Also includes things like nutrition and activity preferences, and health history.
In this project, Claude is basically like my gp, personal trainer, and nutritionist all-in-one.
Coding
Instructions include all my coding preferences:
- I want Claude to return full code files (no "# rest of the code")
- Comments but only for complicated stuff
- Language preferences (I mainly use python nowadays)
Education
Instructions include my learning style (I prefer diagrams and analogies), what level of explanation I want Claude to respond with (e.g. ELI5), and my preference for Claude to ask me questions to identify what I don't know about a topic.
If you want to quickly set this up, I would just copy the text in this thread, send it to Claude, and ask it to write the custom instructions for each one of these but leave blank spaces for you to fill in your own info.
Let me know what other types of projects y'all have made - I'm trying to source some more cool ideas.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
It was easy to miss all the stuff we shipped at Anthropic this past week given... everything else that happened. A few of my favorites across Claude Code, claude dot ai, and Cowork:
We put together a prompting guide for Claude Opus 4.5 based on extensive internal testing by our research and applied AI teams.
Here's what we've learned so far about getting the best results:
1. The new effort parameter is powerful because it controls approximately how many Claude will use for an output.
You can trade off intelligence for cost/latency with a single dial. Works on all tokens including thinking, responses, and tool calls.
2. Tool triggering rates may change. Opus 4.5 is more responsive to system prompts, so if your old prompts used aggressive language to reduce undertriggering, you may now see overtriggering.
Dial back "CRITICAL: You MUST use this tool" to just "Use this tool when..."
Instead of loading all tool definitions upfront, Claude discovers tools on-demand. Mark tools with defer_loading: true and only pays tokens for tools Claude actually needs.
Up to an 85% token reduction and big boost in accuracy on our MCP evals (79.5% to 88.1%)
Programmatic Tool Calling
Claude orchestrates tools through code instead of individual round-trips. It writes Python, processes outputs in a sandbox, and controls what enters context.
Today we're introducing Skills in claude dot ai, Claude Code, and the API.
Skills let you package specialized knowledge into reusable capabilities that Claude loads on demand as agents tackle more complex tasks.
Here's how they work and why they matter for the future of agents:
At a high level, the best analogy I've heard for Skills is something like Neo learning Kung Fu in seconds in the Matrix.
We're "loading in" specialized knowledge to our general agents at runtime.
At their core, Skills are simple. They're just a folder with a file.
The file starts with a name and description, then contains instructions, code, and resources. This simplicity means anyone can now specialize Claude without building custom agents. SKILL.md
We’re running a “Built with Claude Sonnet 4.5” challenge.
We want to see the coolest things you can build with 4.5 in the next week.
Four winners will receive one year of Claude Max 20x and $1k in Claude API credits.
We will select four winners:
“Keep Coding” Award - most technically impressive implementation
“Keep Researching” Award - most compelling exploration of a topic
“Keep Learning” Award – best educational application
“Keep Creating” Award – most artistic use-
To enter, quote post the first tweet of this thread through October 7 with what you built with Claude 4.5:
- How you built it (prompts, agents, MCP servers, workflows)
- Screenshots or demos
- Must be your own work, built with Claude Sonnet 4.5 (Claude.ai, Claude app, Claude Code, Claude Code SDK)
- We will select winners based on ingenuity, creativity, and community response.
We’ve rolled out another update to Claude Code to help customize your workflows: Hooks.
Hooks are user-defined shell commands that execute at various points in Claude Code’s agent loop.
They give you deterministic control over Claude Code’s behavior to ensure certain actions always happen at certain times.
You can create hooks for:
- Notifications (e.g. via Slack) on prompt completions
- Logging and observability
- Custom permissions and approvals
- Running lints after every write