claude-opus-4-5-migration

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.

1.75x

Quality

82%

Does it follow best practices?

Impact

91%

1.75x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable migration guide with strong progressive disclosure and lean reference data. The main weakness is the workflow's lack of an explicit validation checkpoint for what is a batch codebase modification.

Suggestions

Add an explicit validation/verification step to the workflow, e.g. after updating model strings, re-search the codebase to confirm no old strings remain and run or prompt the user to run existing tests.

Consolidate the repeated 'Apply if' / 'Add the snippet from references/prompt-snippets.md' phrasing across prompt-adjustment subsections into a single shared instruction to reduce repetition.

Consider inlining a one-line example of each prompt snippet so the most common fixes are actionable without opening references/prompt-snippets.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean—reference tables and Opus 4.5 behavioral notes earn their place—but the prompt-adjustment subsections repeat the 'Apply if'/'Add the snippet from references/prompt-snippets.md' pattern several times and could be tightened.	4 / 5
Actionability	Concrete and mostly executable: copy-paste-ready model strings, a specific find-and-soften replacement table, and exact comment text to insert; the only gap is that prompt snippets are referenced rather than inlined, adding one indirection.	4 / 5
Workflow Clarity	A clear six-step numbered sequence is present, but this is a batch codebase modification with no explicit validation or verification checkpoint (step 5 only summarizes changes), so the batch-operation cap applies.	3 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to real files (references/effort.md and references/prompt-snippets.md), with bulk snippet text appropriately split out and model-string tables kept inline.	5 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities, trigger conditions, and scope boundaries. The only minor gap is a lack of synonyms for the migration action.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—migrating prompts and code, model string updates, and prompt adjustments for behavioral differences—plus an explicit exclusion (no Haiku), giving comprehensive coverage of the migration scope.	5 / 5
Completeness	Explicitly answers both what (migrate prompts/code from named sources to Opus 4.5, handle string and prompt adjustments) and when ('Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms a user would say are present ('update their codebase, prompts, or API calls to use Opus 4.5' plus source model names), but common synonyms like 'upgrade' or 'switch to' are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (migration to Opus 4.5 from three specific source models) with an explicit 'Does NOT migrate Haiku 4.5' boundary, yielding minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/claude-code
Path: plugins/claude-opus-4-5-migration/skills/claude-opus-4-5-migration/SKILL.md
Commit: ae58f7a

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.