CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

93

1.75x
Quality

93%

Does it follow best practices?

Impact

91%

1.75x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

This is a well-crafted migration skill that efficiently presents platform-specific model strings, a clear workflow, and conditional prompt adjustments. Its main weakness is the lack of validation/verification steps in the migration workflow—there's no checkpoint to confirm the migration succeeded before telling the user it's done. The progressive disclosure is excellent, keeping the main file focused while deferring snippet details to reference files.

Suggestions

Add a validation step to the migration workflow (e.g., 'Search again to confirm no old model strings remain' or 'Run existing tests to verify API calls succeed with new model strings') to catch incomplete migrations.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It assumes Claude's competence, avoids explaining what APIs or model strings are, and every section serves a clear purpose. The tables are an efficient way to present model string mappings.

3 / 3

Actionability

Provides exact model strings for all platforms in copy-paste-ready tables, specific beta headers to remove, concrete find-and-replace patterns for prompt adjustments, and clear references to snippet files. The guidance is specific and executable.

3 / 3

Workflow Clarity

The 6-step migration workflow is clearly sequenced, but lacks validation checkpoints. There's no step to verify the migration worked (e.g., run tests, confirm API calls succeed with new model strings). For a migration involving potentially destructive string replacements across a codebase, a validation step is important.

2 / 3

Progressive Disclosure

The skill is well-structured with a clear overview, concise inline content for essential information (model strings, workflow), and appropriate references to separate files for detailed snippets (references/prompt-snippets.md, references/effort.md). References are one level deep and clearly signaled.

3 / 3

Total

11

/

12

Passed

Description

100%

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

This is an excellent skill description that clearly defines what it does (migrates prompts and code between specific model versions), when to use it (when updating to Opus 4.5), and what it excludes (Haiku 4.5). It uses third person voice consistently, includes natural trigger terms, and has a distinct enough niche to avoid conflicts with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: migrating prompts and code, updating model strings, adjusting prompts for behavioral differences. Also specifies source models (Sonnet 4.0, Sonnet 4.5, Opus 4.1) and target model (Opus 4.5), and explicitly excludes Haiku 4.5.

3 / 3

Completeness

Clearly answers both 'what' (migrate prompts and code, handle model string updates and prompt adjustments) and 'when' (explicit 'Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5'). Also includes a negative boundary ('Does NOT migrate Haiku 4.5') which further clarifies scope.

3 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'migrate', 'prompts', 'code', 'API calls', 'Opus 4.5', 'Sonnet 4.0', 'Sonnet 4.5', 'Opus 4.1', 'model string updates', 'codebase', 'update'. These are terms a user would naturally use when wanting to upgrade their model version.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: migration specifically to Opus 4.5 from named source models. The explicit model version names and the exclusion of Haiku 4.5 make it very unlikely to conflict with other skills. This is a narrowly scoped, well-defined task.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/claude-code
Reviewed

Table of Contents

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.