📦
Agent Development
84Build reliable Claude Code agents
Plugin agents can trigger poorly or receive excessive tool access. This skill provides templates and guidance for focused agents with clear behavior.
Documentation View
Skills claude-opus-4-5-migration
📦
claude-opus-4-5-migration
Content revision r2 Safe ⚙️ External commands
Migrate Claude Applications to Opus 4.5
Updating model identifiers and prompts across providers can be inconsistent. This skill guides targeted Opus 4.5 migrations with provider settings and prompt adjustments.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "claude-opus-4-5-migration" from https://skillstore.io/skills/claude-opus-4-5-migration.md and its manifest at https://skillstore.io/api/skills/claude-opus-4-5-migration/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "claude-opus-4-5-migration". Migrate an Anthropic API project from Sonnet 4.5 and review its context header.
Expected outcome:
- Updated eligible Sonnet 4.5 references to the documented Opus 4.5 model.
- Removed the unsupported one-million-token context beta header and added a compatibility note.
- Listed every changed file and setting.
Using "claude-opus-4-5-migration". The migrated assistant calls tools too often.
Expected outcome:
- Reviewed tool-triggering instructions for aggressive emphasis.
- Softened only the relevant mandatory wording while preserving other prompt requirements.
- Explained each prompt adjustment.
Using "claude-opus-4-5-migration". Prepare a Bedrock migration and include effort guidance.
Expected outcome:
- Selected the documented Bedrock target identifier for Opus 4.5.
- Reviewed high-effort configuration and its required beta flag.
- Flagged provider support for verification before deployment.
Security Audit
Safev10 • 7/23/2026 Open versioned report
All 30 static findings are false positives. The six blocker matches are ordinary coding and design guidance, while the 24 command matches are Markdown delimiters, identifiers, or reference links with no execution behavior. No prompt injection or other semantic security risk was found.
3
Files scanned
284
Lines analyzed
0
Review items
0
False positives ignored
Risk Factors
⚙️ External commands (24)
SKILL.md:15 SKILL.md:25 SKILL.md:27-29 SKILL.md:29-35 SKILL.md:35-36 SKILL.md:36-37 SKILL.md:37-38 SKILL.md:38-44 SKILL.md:44 SKILL.md:45 SKILL.md:46 SKILL.md:48-55 SKILL.md:55 SKILL.md:67-68 SKILL.md:68 SKILL.md:69 SKILL.md:70 SKILL.md:71-79 SKILL.md:79-85 SKILL.md:85-91 SKILL.md:91-95 SKILL.md:95-97 SKILL.md:97-103 SKILL.md:103-105
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/claude-opus-4-5-migration/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/claude-opus-4-5-migration?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/claude-opus-4-5-migration?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/claude-opus-4-5-migration/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/claude-opus-4-5-migration.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
anthropics. (2026). claude-opus-4-5-migration security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/claude-opus-4-5-migration/audits/10BibTeX citation
@techreport{anthropics-claude-opus-4-5-migration-2026,
author = {anthropics},
title = {claude-opus-4-5-migration security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/claude-opus-4-5-migration/audits/10},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "claude-opus-4-5-migration security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "anthropics"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/claude-opus-4-5-migration/audits/10"
identifiers:
- type: other
value: "skillstore:claude-opus-4-5-migration:audit:10"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
claude-opus-4-5-migration
Skillstore Score 75
Evidence Confidence High
Skillstore usage 14
Updated
2026-09-09
davila7-claude-opus-4-5-migration
Skillstore Score 75
Evidence Confidence High
Skillstore usage 6
Updated
2026-09-09
dennisliuck-claude-opus-4-5-migration
Skillstore Score 74
Evidence Confidence High
Skillstore usage 7
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: High 41
Architecture
85
Maintainability
87
Content
71
Community
91
Spec Compliance
What You Can Build
Upgrade an Anthropic Application
Update eligible model calls, remove an incompatible context header, and review effort settings in an existing application.
Update Managed Cloud Models
Apply the documented Opus 4.5 identifier for Bedrock, Vertex AI, or Azure AI Foundry.
Tune Migrated Prompts
Address specific Opus 4.5 behavior changes while preserving the existing prompt structure and functional content.
Try These Prompts
Basic Model Upgrade
Migrate [project path] from [supported source model] to Opus 4.5. Update only model identifiers and summarize the changed files.
Provider-Specific Migration
Migrate [project path] to Opus 4.5 on [provider]. Review model identifiers, unsupported headers, and effort configuration, then summarize each change.
Prompt Behavior Adjustment
Review [prompt file] for Opus 4.5 after [reported issue]. Apply only relevant prompt adjustments and explain every modification.
Complete Migration Review
Perform a complete Opus 4.5 migration for [project]. Detect the provider, update eligible models, review headers and effort settings, assess reported prompt issues, and summarize changes.
Best Practices
- Confirm the active provider before replacing model identifiers.
- Apply prompt snippets only for an explicit request or a reproduced behavior issue.
- Review the final diff and verify current model availability before deployment.
Avoid
- Do not migrate Haiku model references with this skill.
- Do not append every prompt snippet without matching a reported issue.
- Do not assume dated model identifiers or beta flags remain current without provider verification.
Frequently Asked Questions
Which source models can this skill migrate?
It supports Claude Sonnet 4.0, Sonnet 4.5, and Opus 4.1 as migration sources.
Does it migrate Claude Haiku models?
No. Haiku models are explicitly excluded.
Which providers are covered?
Target identifiers cover Anthropic API, AWS Bedrock, Google Vertex AI, and Azure AI Foundry. Source mappings cover Anthropic, Bedrock, and Vertex AI.
Will it change prompts automatically?
The default migration changes model identifiers. Prompt adjustments are applied only when requested or when a specific behavior issue is reported.
How does it handle the effort setting?
It documents high effort as the migration default and provides the related beta flag. Lower effort levels remain available for cost or latency needs.
Does the skill verify current provider availability?
No. The guide contains dated identifiers and beta settings, so teams should verify current provider documentation before deployment.
Developer Details
Author
anthropicsLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
c43861a65bb95efcae259cd161c9d6f4dc7eec6f
Maintenance freshness
7/24/2026
Usage
13 downloads · 258 views
File structure
More from anthropics
View all📦
writing-hookify-rules
82Write Hookify Rules for Claude Code
Hook rules can be hard to write correctly across bash, file, stop, and prompt events. This skill gives Claude, Codex, and Claude Code practical guidance for creating and testing Hookify rules.
DevOps & Infrastructure View
📦
Plugin Settings
81Configure Local Plugin Settings
Plugin authors need a safe way to store per-project settings without committing user-specific state. This skill explains a local Markdown and YAML frontmatter pattern for Claude, Codex, and Claude Code plugins.
Documentation View
📦
Plugin Structure
80Build Claude Code Plugin Structures
Plugin authors need a reliable structure before adding commands, agents, skills, hooks, or MCP servers. This skill explains the expected layout, manifest fields, naming rules, and portable path patterns.
Documentation View
📦
example-skill
80Build Effective Claude Code Skills
Skill authors need a clear reference for structuring and describing plugin skills. This guide explains required files, optional resources, frontmatter, activation wording, and practical design guidelines.
Documentation View
📦
frontend-design
79Create Distinctive Frontend Designs
Generic interface patterns can make products feel interchangeable and poorly matched to their users. This skill guides intentional choices in typography, color, layout, motion, copy, and responsiveness.
Design & Creative View
Related Skills
View all📦
senior-prompt-engineer
81Design Better LLM Prompts
by alirezarezvani
Prompt quality often fails because requirements, examples, and evaluation criteria are unclear. This skill helps teams design, test, and review production prompts for Claude, Codex, and Claude Code.
Coding & Development View
📦
tool-design
81Design Reliable Tools for AI Agents
by Asmayaseen
Ambiguous tools cause incorrect calls, wasted context, and poor recovery from errors. This skill provides practical patterns for clear descriptions, schemas, responses, and testing.
Coding & Development View
📦
creating-agents
79Create Claude Code Subagents
by BrendanShields
Teams often need focused agents for review, research, and domain work. This skill provides a structured process and templates for creating Claude Code subagents with scoped tools.
Coding & Development View
📦
context-degradation
78Diagnose Context Degradation in AI Systems
by sickn33
Long conversations and overloaded prompts can reduce model accuracy in ways that are difficult to diagnose. This skill identifies degradation patterns and recommends practical context management strategies.
Coding & Development View
📦
llm-application-dev-prompt-optimize
78Optimize LLM Application Prompts
by sickn33
Weak prompts create inconsistent LLM behavior, higher token costs, and difficult testing. This skill turns rough instructions into structured prompts with evaluation, safety, and deployment guidance.
Coding & Development View
📦
ai-wrapper-product
78Build Reliable AI API Products
by sickn33
Generic AI wrappers often lack clear value, reliable outputs, and cost controls. This skill guides focused product design, implementation patterns, and operational safeguards.
Coding & Development View