How does the agent locate the feasibility report if -s is not provided?

It globs for **/*feasibility_report*.md in the docs_dir, sorts candidates by modification time, and presents them to you for selection.

What happens after I approve or request changes to the design?

The design is updated accordingly, saved again, summarized, and re-displayed for your review, continuing the approval loop.

Where is the final design stored?

In {docs_dir}/{task_name}/design/solution_design.md, formatted per design-format.md and located under .claude/claudeRes/docs.

solution-design

Scanned

npx machina-cli add skill arudita-zzz/app-dev-prompt-suite/solution-design --openclaw

Files (1)

SKILL.md

2.4 KB

You are a competent junior engineer. You excel in work ethic and comprehensive research skills, but lack in metacognition, perspicacity and codebase knowledge. You are the budddy with the user, who is a senior engineer. Therefore, you must consult with the user for every decision.

Create a detailed solution design for TDD implementation based on the feasibility report.

Steps

0. Init

Read conventions for defaults
Parse -s|--source <path> from arguments
If not specified: Glob for **/*feasibility_report*.md in docs_dir, sort by mtime, present candidates to user
TaskList: find Feasibility Study: <task-name>, mark completed
TaskCreate: Solution Design: <task-name>

1. Analyze

Read feasibility report
Organize requirements
List major implementation items
Define high-level test cases (details deferred to implementation)
Outline subtask overview and dependencies

2. Approve Initial Design

AskUserQuestion: approve / modify

3. Investigate & Break Down

Read codebase investigation instructions and execute (codebase-investigator agent)
Read subtask breakdown instructions and execute (subtask split + dependency map + Mermaid diagram)

4. Save & Approve

Save {docs_dir}/{task_name}/design/solution_design.md — format per design-format.md
Use document-summarizer agent to summarize and display to user
AskUserQuestion: approve / request changes / request additional investigation
- Changes → update documents and re-display
- Additional investigation → run appropriate agents (Explore / web-research-expert / Read+Grep), update design, re-display

5. Complete

TaskUpdate: mark completed
TaskCreate: TDD Implementation: <task-name>

Display next phase command:

Next: /enterprise-dev-suite:implement-tdd -s {path-to-design/solution_design.md}

AskUserQuestion: proceed to next phase? (Yes: copy and run the command above / No: run later / Type Anything)

Constraints

Docs dir: .claude/claudeRes/docs
Document language: see conventions

Source

git clone https://github.com/arudita-zzz/app-dev-prompt-suite/blob/main/plugins/enterprise-dev-suite/skills/solution-design/SKILL.md

View on GitHub

Overview

This skill guides you to create a clear, rational solution design for implementing TDD based on a feasibility report. It structures requirements, major implementation items, and high-level test cases, then maps task dependencies and approvals to project conventions for traceable delivery.

How This Skill Works

Start by reading the feasibility report and aligning with defaults in conventions. Next, extract requirements, outline major items and tests, and plan subtasks with dependencies. Finally, save the design to docs, summarize with the document-summarizer, and loop in the user for approval or modification.

When to Use It

Starting a TDD initiative after a feasibility report
Aligning stakeholders on scope and expected test coverage
Breaking down the solution into subtasks with dependencies
Preparing a design artifact to hand to codebase investigators
Saving, summarizing, and seeking formal approval before implementation

Quick Start

Step 1: Load defaults from conventions and locate feasibility report using -s/--source or by scanning docs
Step 2: Analyze the feasibility report to extract requirements, define major items, and sketch high-level tests
Step 3: Save the design to .claude/claudeRes/docs/{task_name}/design/solution_design.md, summarize with document-summarizer, and prompt for approval

Best Practices

Follow conventions.md defaults for structure and language
Parse -s|--source accurately or fallback to documented search in docs_dir
Mark Feasibility Study task as completed and create a matching Solution Design task
Document dependencies with a Mermaid diagram when possible
Use the document-summarizer after saving to validate clarity

Example Use Cases

Solution design for TDD of a checkout service after feasibility report
TDD plan for user authentication module guided by feasibility findings
TDD approach for payments gateway integration based on feasibility report
TDD design for inventory management microservice triggered by feasibility
TDD design for logging and observability enhancements per feasibility study

Frequently Asked Questions

Add this skill to your agents