- Home
- Skills
- Arjenschwarz
- Agentic Coding
- Starwave Design
starwave-design_skill
- Python
16
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill arjenschwarz/agentic-coding --skill starwave-design- SKILL.md5.1 KB
Overview
This skill generates a comprehensive feature design document from an approved requirements file. It verifies the feature folder and requirements.md, conducts targeted research, produces specs/{feature_name}/design.md, and enforces decision and review workflows to ensure traceability and testability. The design includes architecture, components, data models, error handling, and a testing strategy including property-based testing where appropriate.
How this skill works
The skill locates specs/{feature_name}/requirements.md and follows any decisions in decision_log.md. If the folder or requirements file is missing it prompts the user to provide the feature name or to run the requirements step first. It performs research (linked in conversation), synthesizes findings into the document, writes specs/{feature_name}/design.md, updates specs/{feature_name}/decision_log.md, and runs automated peer reviews and design-critic tools before asking the user for approval.
When to use it
- You have an approved requirements.md and need a full design doc
- Preparing for implementation or handoff to engineers
- Needing research-driven tradeoffs documented alongside designs
- When acceptance criteria must map to tests and architecture
- Before creating tickets or implementation plans
Best practices
- Ensure requirements.md is complete and stored at specs/{feature_name}/requirements.md before starting
- Keep decision_log.md up to date so design follows prior decisions
- Answer targeted technical questions when prompted to enable focused tradeoffs
- Review and approve design iterations explicitly after each change
- Use the provided testing guidance to align tests with acceptance criteria
Example use cases
- Design a new API endpoint with data model, error handling, and PBT candidates
- Define architecture and component interfaces for a background processing feature
- Translate user-facing feature requirements into developer-facing implementation plans
- Produce a test strategy that identifies when property-based testing improves coverage
FAQ
If the folder can’t be found the skill will ask: "I can't find the feature, can you provide it again?"
Can I request changes after the initial design?
Yes. The skill will iterate on the design, incorporate feedback, update design.md and decision_log.md, and ask for explicit approval after each iteration.