sdd-walkthrough Skill
Use when about to orchestrate a subagent-driven-development execute-plan session — provides 5 realistic task scenarios with Amplifier delegate() patterns, modelrole selection, status handling (DONE, DONEWITHCONCERNS, NEEDSCONTEXT), and fix loops for spec and quality issues Published by microsoft in amplifier-bundle-superpowers.
What is sdd-walkthrough Skill?
Use when about to orchestrate a subagent-driven-development execute-plan session — provides 5 realistic task scenarios with Amplifier delegate() patterns, modelrole selection, status handling (DONE, DONEWITHCONCERNS, NEEDSCONTEXT), and fix loops for spec and quality issues Published by microsoft in amplifier-bundle-superpowers. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Developers using amplifier-bundle-superpowers
Technical details
- Install or run with Copy skill directory
When to use sdd-walkthrough Skill
- Use it for developers using amplifier-bundle-superpowers.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/amplifier-bundle-superpowers
- Skill file: skills/sdd-walkthrough/SKILL.md
What it does
Use when about to orchestrate a subagent-driven-development execute-plan session — provides 5 realistic task scenarios with Amplifier delegate() patterns, modelrole selection, status handling (DONE, DONEWITHCONCERNS, NEEDSCONTEXT), and fix loops for spec and quality issues
Skill instructions
SDD Walkthrough Purpose: Load this when about to orchestrate an execute-plan session. Provides concrete worked examples of all five common task outcomes so you know exactly what delegate() calls to make and how to respond to each reviewer verdict. Why This Skill Exists The subagent-driven-development skill describes the process. This skill shows it in action — real delegate() call syntax, realistic reviewer responses, and the decisions an orchestrator makes at each step. Reference it before you start so the patterns are fresh when edge cases appear. Scenarios Covered | | Task | Outcome Pattern | Key Technique | |---|------|-----------------|---------------| | 1 | Validate email format | Happy path: DONE → spec PASS → quality PASS | contextdepth='none', modelrole='coding' | | 2 | Domain reachability check | Spec gap caught: impl raises instead of returns False | Re-delegate with specific gap description | | 3 | In-memory rate limiter | DONEWITHCONCERNS: multi-worker incompatibility | No
Explore related resources
Frequently asked questions
What is sdd-walkthrough?
sdd-walkthrough is a open-source AI agent skill with Copy skill directory. Use when about to orchestrate a subagent-driven-development execute-plan session — provides 5 realistic task scenarios with Amplifier delegate() patterns, modelrole selection, status handling (DONE.
Who is sdd-walkthrough best for?
sdd-walkthrough is best for reusing agent instructions, scripts, and references.
How do I install sdd-walkthrough?
Install or run sdd-walkthrough using Copy skill directory. Check sdd-walkthrough for the latest setup command.
Is sdd-walkthrough actively maintained?
sdd-walkthrough may need a closer maintenance check before production use.
Auto-fetched from GitHub.
