claude-opus-4-5-migration

작성자: anthropic

Claude 모델 문자열과 프롬프트를 Sonnet 4.0, Sonnet 4.5 또는 Opus 4.1에서 Opus 4.5로 마이그레이션합니다. Anthropic API, AWS Bedrock, Google Vertex AI 및 Azure AI Foundry 플랫폼에서 모델 문자열을 업데이트합니다. 지원되지 않는 베타 헤더(예: context-1m-2025-08-07)를 제거하고 "high"로 설정된 effort 매개변수를 추가합니다. 알려진 Opus 4.5 동작 차이(도구 과다 트리거링, 과도한 엔지니어링, 코드 탐색 보수성, 프론트엔드 디자인 및 사고 민감도)에 대한 선택적 프롬프트 조정을 제공합니다...

npx skills add https://github.com/anthropics/claude-code --skill claude-opus-4-5-migration

Opus 4.5 Migration Guide

One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Migration Workflow

  1. Search codebase for model strings and API calls
  2. Update model strings to Opus 4.5 (see platform-specific strings below)
  3. Remove unsupported beta headers
  4. Add effort parameter set to "high" (see references/effort.md)
  5. Summarize all changes made
  6. Tell the user: "If you encounter any issues with Opus 4.5, let me know and I can help adjust your prompts."

Model String Updates

Identify which platform the codebase uses, then replace model strings accordingly.

Unsupported Beta Headers

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

Target Model Strings (Opus 4.5)

PlatformOpus 4.5 Model String
Anthropic API (1P)claude-opus-4-5-20251101
AWS Bedrockanthropic.claude-opus-4-5-20251101-v1:0
Google Vertex AIclaude-opus-4-5@20251101
Azure AI Foundryclaude-opus-4-5-20251101

Source Model Strings to Replace

Source ModelAnthropic API (1P)AWS BedrockGoogle Vertex AI
Sonnet 4.0claude-sonnet-4-20250514anthropic.claude-sonnet-4-20250514-v1:0claude-sonnet-4@20250514
Sonnet 4.5claude-sonnet-4-5-20250929anthropic.claude-sonnet-4-5-20250929-v1:0claude-sonnet-4-5@20250929
Opus 4.1claude-opus-4-1-20250422anthropic.claude-opus-4-1-20250422-v1:0claude-opus-4-1@20250422

Do NOT migrate: Any Haiku models (e.g., claude-haiku-4-5-20251001).

Prompt Adjustments

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:

  • Use XML tags (e.g., <code_guidelines>, <tool_usage>) to organize additions
  • Match the style and structure of the existing prompt
  • Place snippets in logical locations (e.g., coding guidelines near other coding instructions)
  • If the prompt already uses XML tags, add new content within appropriate existing tags or create consistent new ones

1. Tool Overtriggering

Opus 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 soften
  • You MUST...You should...
  • ALWAYS do XDo X
  • NEVER skip...Don't skip...
  • REQUIRED → remove or soften

Only apply to tool-triggering instructions. Leave other uses of emphasis alone.

2. Over-Engineering Prevention

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.

3. Code Exploration

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.

4. Frontend Design

Apply if: User requests improved frontend design quality or reports generic-looking outputs.

Add the frontend aesthetics snippet from references/prompt-snippets.md.

5. Thinking Sensitivity

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."

Reference

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).

anthropic의 다른 스킬

access
anthropic
Discord 채널 접근을 관리합니다 — 페어링 승인, 허용 목록 편집, DM/그룹 정책 설정. 사용자가 페어링 요청, 승인, 허용된 사람 확인 등을 요청할 때 사용합니다.
official
session-report
anthropic
~/.claude/projects 트랜스크립트에서 Claude Code 세션 사용량(토큰, 캐시, 하위 에이전트, 스킬, 고비용 프롬프트)에 대한 탐색 가능한 HTML 보고서를 생성합니다.
official
build-mcp-server
anthropic
이 스킬은 사용자가 "MCP 서버 구축", "MCP 생성", "MCP 통합 만들기", "Claude용 API 래핑", "도구 노출" 등을 요청할 때 사용해야 합니다.
official
cookbook-audit
anthropic
Anthropic Cookbook 노트북을 루브릭에 따라 감사합니다. 노트북 리뷰나 감사가 요청될 때마다 사용하세요.
official
handle-complaint
anthropic
들어오는 고객 불만을 처음부터 끝까지 처리합니다 — 맥락을 파악하고, 응답을 작성하며, 운영상의 수정을 제안합니다. 선택적으로 이메일이나 티켓 ID를 받습니다…
official
use-case-triage
anthropic
처리 활동이 PIA, 필수 GDPR DPIA가 필요한지 또는 진행 가능한지 신속히 판단하여 개인정보 처리방침 충돌을 표시하고 적절한 경로로 안내합니다…
official
board-minutes
anthropic
이사회 또는 위원회 회의록을 사내 형식으로 작성합니다. 캘린더에서 예정된 이사회 및 위원회 회의를 자동으로 감지하고, 안건을 요청한 후…
official
renewal-tracker
anthropic
유지 관리되는 갱신 등록부를 기반으로 취소 마감일이 다가오는 계약을 표시하고 통지 기간이 종료되기 전에 경고합니다. 사용자가 요청할 때 사용합니다.
official