Slash Command292 repo starsupdated 2d ago

workflow-technical-discovery

The workflow-technical-discovery command systematically evaluates technical feasibility and documents architecture decisions through three sequential steps: creating a spike summary that captures time-boxed exploration results, developing an architecture decision record that details context and options considered, and producing design rationale that explains reasoning and trade-offs. Use this workflow when investigating complex technical challenges that require documented decision-making for future reference and team alignment.

View source Repository: pm-skills

Install in Claude Code

Copy

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/product-on-purpose/pm-skills/HEAD/commands/workflow-technical-discovery.md -o ~/.claude/commands/workflow-technical-discovery.md

Then start a new Claude Code session; the slash command loads automatically.

Definition

workflow-technical-discovery.md

Run the Technical Discovery workflow to evaluate technical feasibility and document architecture decisions.

This workflow uses multiple skills in sequence. For each step, read the skill instructions and follow them to create the artifact.

## Workflow Steps

### Step 1: Spike Summary

Use the `develop-spike-summary` skill from `skills/develop-spike-summary/SKILL.md`.

Document the results of a time-boxed technical exploration.

### Step 2: Architecture Decision Record

Use the `develop-adr` skill from `skills/develop-adr/SKILL.md`.

Record the architecture decision with context, options considered, and consequences.

### Step 3: Design Rationale

Use the `develop-design-rationale` skill from `skills/develop-design-rationale/SKILL.md`.

Document the reasoning behind design decisions, alternatives considered, and trade-offs.

## Output

Create all three artifacts in sequence, ensuring each builds on the previous.

Reference the Technical Discovery workflow at `_workflows/technical-discovery.md` for additional guidance.

Context from user: $ARGUMENTS