8 8
9This is a library of prompts to copy into Claude Code. Use it to explore ways of working you haven't tried, or when you're not sure where to start.9This is a library of prompts to copy into Claude Code. Use it to explore ways of working you haven't tried, or when you're not sure where to start.
10 10
11The prompts are collected from various Anthropic guides, including [Common workflows](/docs/en/common-workflows.md), [Best practices](/docs/en/best-practices.md), and [How Anthropic teams use Claude Code](https://claude.com/blog/how-anthropic-teams-use-claude-code). They're starting points rather than scripts. Open **Why this works** under any prompt to see the pattern behind it so you can write your own.11The prompts are collected from various Anthropic guides, including [Common workflows](https://code.claude.com/docs/en/common-workflows.md), [Best practices](https://code.claude.com/docs/en/best-practices.md), and [How Anthropic teams use Claude Code](https://claude.com/blog/how-anthropic-teams-use-claude-code). They're starting points rather than scripts. Open **Why this works** under any prompt to see the pattern behind it so you can write your own.
12 12
13## What makes these prompts work13## What makes these prompts work
14 14
20add rate limiting to the public API and make sure existing tests still pass20add rate limiting to the public API and make sure existing tests still pass
21```21```
22 22
23**Give it a way to check its own work.** Ask for run, test, compare, or verify in the same prompt so Claude iterates instead of stopping after one attempt. To check the finished change against the running app, run [`/verify`](/docs/en/skills#run-and-verify-your-app).23**Give it a way to check its own work.** Ask for run, test, compare, or verify in the same prompt so Claude iterates instead of stopping after one attempt. To check the finished change against the running app, run [`/verify`](https://code.claude.com/docs/en/skills#run-and-verify-your-app).
24 24
25```text wrap theme={null}25```text wrap theme={null}
26write the migration, run it against the dev database, and confirm the schema matches26write the migration, run it against the dev database, and confirm the schema matches
44why is the build failing? @build.log44why is the build failing? @build.log
45```45```
46 46
47**Say how you want the answer.** Name the format, length, or audience so the explanation fits how you'll use it. To make a format the default for every response, set an [output style](/docs/en/output-styles.md).47**Say how you want the answer.** Name the format, length, or audience so the explanation fits how you'll use it. To make a format the default for every response, set an [output style](https://code.claude.com/docs/en/output-styles.md).
48 48
49```text wrap theme={null}49```text wrap theme={null}
50explain how the payment retry logic works as an HTML page with a diagram, then open it in my browser50explain how the payment retry logic works as an HTML page with a diagram, then open it in my browser
51```51```
52 52
53For more on each pattern, see [best practices](/docs/en/best-practices.md).53For more on each pattern, see [best practices](https://code.claude.com/docs/en/best-practices.md).
54 54
55## Where these come from55## Where these come from
56 56
57These prompts are based on patterns from published Anthropic resources. Each card links to its source:57These prompts are based on patterns from published Anthropic resources. Each card links to its source:
58 58
59* [Common workflows](/docs/en/common-workflows.md): step-by-step guides for the core tasks59* [Common workflows](https://code.claude.com/docs/en/common-workflows.md): step-by-step guides for the core tasks
60* [Best practices](/docs/en/best-practices.md): prompting patterns and project setup60* [Best practices](https://code.claude.com/docs/en/best-practices.md): prompting patterns and project setup
61* [How Anthropic teams use Claude Code](https://claude.com/blog/how-anthropic-teams-use-claude-code): real workflows from engineering, product, design, and data teams, with deep dives on [legal](https://claude.com/blog/how-anthropic-uses-claude-legal), [marketing](https://claude.com/blog/how-anthropic-uses-claude-marketing), and [cybersecurity](https://claude.com/blog/how-anthropic-uses-claude-cybersecurity)61* [How Anthropic teams use Claude Code](https://claude.com/blog/how-anthropic-teams-use-claude-code): real workflows from engineering, product, design, and data teams, with deep dives on [legal](https://claude.com/blog/how-anthropic-uses-claude-legal), [marketing](https://claude.com/blog/how-anthropic-uses-claude-marketing), and [cybersecurity](https://claude.com/blog/how-anthropic-uses-claude-cybersecurity)
62* [Scaling agentic coding guide](https://resources.anthropic.com/hubfs/Scaling%20agentic%20coding%20across%20your%20organization.pdf): the enterprise adoption guide62* [Scaling agentic coding guide](https://resources.anthropic.com/hubfs/Scaling%20agentic%20coding%20across%20your%20organization.pdf): the enterprise adoption guide
63 63
65 65
66## Related resources66## Related resources
67 67
68The prompts on this page are starting points. Once one works for your project, the next step is making it repeatable: save it as a [skill](/docs/en/skills.md) so anyone on your team can run it as a `/command`, and record the conventions Claude learned in [CLAUDE.md](/docs/en/memory.md) so every session starts with that context instead of Claude relearning it. For larger or riskier changes, [plan mode](/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) shows you the file list before any edits happen.68The prompts on this page are starting points. Once one works for your project, the next step is making it repeatable: save it as a [skill](https://code.claude.com/docs/en/skills.md) so anyone on your team can run it as a `/command`, and record the conventions Claude learned in [CLAUDE.md](https://code.claude.com/docs/en/memory.md) so every session starts with that context instead of Claude relearning it. For larger or riskier changes, [plan mode](https://code.claude.com/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode) shows you the file list before any edits happen.
69 69
70If you're introducing Claude Code across a team, see [administration](/docs/en/admin-setup.md) for managed settings and policy, and [costs and usage](/docs/en/costs.md) for how this work is billed on your plan.70If you're introducing Claude Code across a team, see [administration](https://code.claude.com/docs/en/admin-setup.md) for managed settings and policy, and [costs and usage](https://code.claude.com/docs/en/costs.md) for how this work is billed on your plan.