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 4-6 weeks· advanced

Step 1: Discovery and Source Inventory

Profile every major source system, document quality issues, identify downstream consumers, and capture stakeholder pain points. This is a stakeholder conversation, not just a tech audit.

What you're doing in this step

Generate a comprehensive data-source inventory. Profile each source (volumes, schemas, DQ issues). Talk to source-system owners, BI / analyst teams, business stakeholders, the data engineering team if one exists, and compliance / security. Capture pain points with root-cause analysis — they're the point of discovery.

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 1-2 weeks per major source system

Data Source Inventory & Profiling

Discovery template for ETL projects: inventory all data sources, profile their structure and quality, and document downstream dependencies.

azureadffabricpyspark
View template
Template· Template 2-4 hours

Legacy System Audit

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

Use this when: You're replacing a legacy warehouse and want a more general audit framework alongside the source profiling

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

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 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 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

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.

  • Source-system inventory complete (all systems documented)
  • Per-system profiling done (volumes, schemas, data quality)
  • Downstream consumer inventory (who uses what, how often)
  • Pain points captured with root-cause analysis
  • Top 10 risks identified
  • Strategic recommendations documented
Common pitfalls

What goes wrong at this step

  • Skipping stakeholder interviews — the audit document misses what people actually do with data
  • Auditing only formal systems — spreadsheets, MS Access, custom Python scripts all carry data
  • Trusting docs over reality — profile actual data; documentation lies
  • Underestimating consumer count — reports nobody mentioned but everybody depends on
  • Hiding data-quality findings — they're the point of discovery; surface them
← Back to intake

Command Palette

Search for a command to run...