Playbook
0 / 10 complete0%
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
  10. 10
Step 07 of 10 1-3 years (the dominant phase)· advanced

Step 7: Continue Migrating Slices

Migrate remaining capabilities one by one. Track visible progress: % programs migrated, % transactions on new system, MIPS reduction, cost savings realized.

What you're doing in this step

Slice by slice, capability by capability. Each slice gets faster as the team builds expertise and the platform matures. Common patterns: by tenant, by function (customer service → billing → claims), by data domain, or by interface (internal admin first).

Recommended prompts

Use one of these to do the work in your IDE

Open the template to read it in full. Click Copy prompt to grab it (with your stack values pre-filled where they apply) — then paste into Claude Code, Cursor, or wherever you build.

Primary recommendation 0.5 day

Feature Flag Rollout Strategy for Migrations

Use feature flags to safely route traffic between legacy and new systems during migration with controlled rollout and instant rollback.

View template
Template· Template reference document

COBOL to Java/.NET Translation Checklist

Pattern-by-pattern translation guide for COBOL constructs to modern Java or .NET equivalents — including the patterns that don't translate.

Use this when: Working through unfamiliar COBOL idioms in a slice's source programs

coboljavadotnet
View template
Template· Template varies (per procedure)

Stored Procedure to Service Migration

Convert business logic embedded in T-SQL stored procedures into testable, observable application services.

Use this when: A slice has DB2-resident logic that should move to app code

dotnetsql
View template
Template· Template 1-2 days

Data Migration Plan

Plan a safe data migration: schema mapping, ETL strategy, dual-write or one-shot, validation, and cutover with rollback.

Use this when: A slice requires its own data movement plan beyond the global Phase 4 design

View template
Recommended skills

Drop these into Claude Code for this phase

Skills auto-trigger on the right kind of request. Install once; they apply to every prompt that fits.

Skill· Skill 5 min setup

Spec-Driven Builder Skill

Tool-neutral skill that walks developers through PRD → stories → schema → API → tests for any new feature, producing real artifacts at each step. The methodology is identical on every supported tool.

claude-codecopilotcursor
View skill
Skill· Skill 5 min setup

Migration Planner Skill

Flagship migration skill that walks Claude Code through audit → strategy → slicing → cutover for any legacy system migration.

claude-code
View skill
Skill· Skill 5 min setup

Test Generator Skill

Claude Code skill that picks the right test type (unit/integration/E2E) based on context and applies Evoke's testing patterns automatically.

claude-code
View skill
Skill· Skill 5 min setup

Code Reviewer Skill

Claude Code skill that performs comprehensive code review on PRs and diffs, prioritized by severity with concrete fixes.

claude-code
View skill
Recommended MCP configs

Wire these tools into Claude Code first

MCP servers give Claude Code direct access to external systems (Jira, browsers, databases). Configure once.

MCP config· MCP config 10 min setup

Azure DevOps MCP for Evoke

Pre-configured Azure DevOps MCP server for Claude Code — work items, repos, PRs, and pipelines from chat.

claude-codemcp
View config
MCP config· MCP config 10 min setup

GitHub MCP for Evoke

Pre-configured GitHub MCP server for Claude Code — issues, PRs, code search, and Actions from chat.

claude-codemcp
View config
MCP config· MCP config 5 min setup

Filesystem MCP for Evoke

Pre-configured filesystem MCP server for Claude Code — safe, scoped read/write access to project files.

claude-codemcp
View config
MCP config· MCP config 10 min setup

Postgres MCP for Evoke

Pre-configured Postgres MCP server for Claude Code — schema inspection and read-only queries to make database work safer and faster.

claude-codemcppostgres
View config
When you're done

Verify these in your own work before moving on

This is a checklist for you to mentally tick off in your repo and IDE — the site doesn't track it, you do.

  • All capabilities have a modern equivalent
  • Mainframe traffic significantly reduced (target: <10% of original)
  • All scheduled batch migrated
  • All integrations updated
  • All tenants / customers migrated
Common pitfalls

What goes wrong at this step

  • Long-tail capabilities (last 10%) — they take 50% of the time. Budget accordingly
  • Burnout — multi-year projects need rotation. Don't burn out the team that started
  • Scope creep — "while we're rewriting it, let's also..." → no
  • Stalling on rare-but-critical edge cases — edge cases that fire once a year will be discovered the year after the project completes
← Previous step

Command Palette

Search for a command to run...