Migrate code and API calls from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Update platform-specific model identifiers and address reported prompt behavior issues, such as excessive tool use or unnecessary code complexity.
中文简介正在准备中。当前显示英语简介。
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
安装前可以查看交给 AI 代理的指令内容。
One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.
"high" (see references/effort.md)Identify which platform the codebase uses, then replace model strings accordingly.
Remove the context-1m-2025-08-07 beta header if present—it is not yet supported with Opus 4.5. Leave a comment noting this:
# Note: 1M context beta (context-1m-2025-08-07) not yet supported with Opus 4.5
| Platform | Opus 4.5 Model String |
|---|---|
| Anthropic API (1P) | claude-opus-4-5-20251101 |
| AWS Bedrock | anthropic.claude-opus-4-5-20251101-v1:0 |
| Google Vertex AI | claude-opus-4-5@20251101 |
| Azure AI Foundry | claude-opus-4-5-20251101 |
| Source Model | Anthropic API (1P) | AWS Bedrock | Google Vertex AI |
|---|---|---|---|
| Sonnet 4.0 | claude-sonnet-4-20250514 | anthropic.claude-sonnet-4-20250514-v1:0 | claude-sonnet-4@20250514 |
| Sonnet 4.5 | claude-sonnet-4-5-20250929 | anthropic.claude-sonnet-4-5-20250929-v1:0 | claude-sonnet-4-5@20250929 |
| Opus 4.1 | claude-opus-4-1-20250422 | anthropic.claude-opus-4-1-20250422-v1:0 | claude-opus-4-1@20250422 |
Do NOT migrate: Any Haiku models (e.g., claude-haiku-4-5-20251001).
Opus 4.5 has known behavioral differences from previous models. Only apply these fixes if the user explicitly requests them or reports a specific issue. By default, just update model strings.
Integration guidelines: When adding snippets, don't just append them to prompts. Integrate them thoughtfully:
<code_guidelines>, <tool_usage>) to organize additionsOpus 4.5 is more responsive to system prompts. Aggressive language that prevented undertriggering on previous models may now cause overtriggering.
Apply if: User reports tools being called too frequently or unnecessarily.
Find and soften:
CRITICAL: → remove or softenYou MUST... → You should...ALWAYS do X → Do XNEVER skip... → Don't skip...REQUIRED → remove or softenOnly apply to tool-triggering instructions. Leave other uses of emphasis alone.
Opus 4.5 tends to create extra files, add unnecessary abstractions, or build unrequested flexibility.
Apply if: User reports unwanted files, excessive abstraction, or unrequested features. Add the snippet from references/prompt-snippets.md.
Opus 4.5 can be overly conservative about exploring code, proposing solutions without reading files.
Apply if: User reports the model proposing fixes without inspecting relevant code. Add the snippet from references/prompt-snippets.md.
Apply if: User requests improved frontend design quality or reports generic-looking outputs.
Add the frontend aesthetics snippet from references/prompt-snippets.md.
When extended thinking is not enabled (the default), Opus 4.5 is particularly sensitive to the word "think" and its variants. Extended thinking is enabled only if the API request contains a thinking parameter.
Apply if: User reports issues related to "thinking" while extended thinking is not enabled (no thinking parameter in request).
Replace "think" with alternatives like "consider," "believe," or "evaluate."
See references/prompt-snippets.md for the full text of each snippet to add.
See references/effort.md for configuring the effort parameter (only if user requests it).
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Build specialized agents for Claude Code plugins that handle tasks involving multiple steps. Define when each agent should run, its responsibilities, available tools, and expected output, then validate its configuration and test its behavior.
中文简介正在准备中。当前显示英语简介。
Turn recurring Claude Code tasks into reusable slash commands stored as Markdown files. The guidance covers arguments, file references, tool permissions, shell execution, and plugin integration so commands can run consistent, context-aware workflows.
中文简介正在准备中。当前显示英语简介。
Design new interfaces or reshape existing ones with colors, typography, and layouts grounded in the subject and audience. It guides planning, implementation, and critique, including interface wording, purposeful motion, mobile layouts, and accessibility.
中文简介正在准备中。当前显示英语简介。
Build Claude Code hooks, automated checks triggered by events such as tool use or session start. The guidance covers prompt-based decisions, command scripts, configuration, testing, and debugging for validation and workflow automation.
中文简介正在准备中。当前显示英语简介。
Connect external services to Claude Code plugins through MCP, a protocol that exposes service functions as tools. Get guidance on server configuration, connection methods, authentication, tool permissions, and testing connections and tool calls.
中文简介正在准备中。当前显示英语简介。
Make Claude Code plugin behavior configurable per project using local Markdown files. Learn to store structured settings and notes, read them from hooks or commands, and handle defaults, validation, and user-local configuration.
中文简介正在准备中。当前显示英语简介。