Playbook
0 / 9 complete0%
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
Step 01 of 9 2-3 weeks· advanced

Step 1: Audit the Legacy App

Reverse-engineer the existing app — tech stack, business logic locations, integrations, and risks — before deciding how to migrate.

What you're doing in this step

Generate a comprehensive audit document covering tech stack, architecture, business logic locations, integration points, auth model, and known issues. The audit is the foundation for every later decision.

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 2-4 hours

Legacy System Audit

Reverse-engineer an existing application: structure, dependencies, integrations, business logic, hidden risks. The starting point for any migration.

View template
Template· Template 30-60 min per program

COBOL Program → Functional Specification

Reverse-engineer a COBOL program into a structured 10-section functional spec — inputs, processing logic, business rules, calculations, outputs, customizations, dependencies.

Use this when: You're auditing COBOL or mainframe code rather than ASP.NET

cobolmainframedb2vsamcics
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

Legacy Code Analyzer Skill

Claude Code skill that reads legacy .NET code (WebForms, VB.NET, classic ASP) and explains what it does — the foundation for any migration.

claude-codedotnet
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
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 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
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
MCP config· MCP config 10 min setup

Confluence MCP for Evoke

Pre-configured Atlassian Confluence MCP server for Claude Code — search, read, and write internal documentation pages from chat.

claude-codemcp
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.

  • Audit document at /docs/migration/audit.md
  • Tech stack inventory complete (all components, versions, EOL status)
  • Business logic locations mapped (stored procs, code-behind, triggers — all explicit)
  • Integration map documented (every external system, internal system, scheduled job)
  • Auth model documented end-to-end
  • Top 10 risks identified
  • Strategic recommendation made (strangler fig vs big-bang vs lift-shift)
Common pitfalls

What goes wrong at this step

  • Auditing only the code — you miss the stored procedures, triggers, SQL Agent jobs, BizTalk orchestrations
  • Trusting docs — they're stale. Code is truth.
  • Skipping operator interviews — the team that runs the app at 3am knows things developers don't
  • Underestimating integration coupling — every API call has hidden dependencies until you migrate
← Back to intake

Command Palette

Search for a command to run...