sdd-propose
Skill10 starsChanged 21 days agoMITView on GitHub
Solution proposals with tradeoff analysis for spec-driven development
Files
SDD Propose Skill
Generate and evaluate solution options before committing to a design. This skill produces a tradeoff table that the team can use to choose the best approach.
Steps
- Review the exploration report: Understand constraints and context.
- What must not change (API contracts, data formats)?
- What are the performance/security requirements?
- What areas of the codebase will be affected?
- Generate 2-4 solution options: Propose meaningfully different approaches.
- Option 1: Minimal change (least disruption, may be limited)
- Option 2: Standard approach (industry-standard pattern)
- Option 3: Clean-slate (ideal design, higher effort)
- Option 4 (optional): Hybrid or incremental migration
- Evaluate each option: Analyze tradeoffs honestly.
For each option, assess:
- Effort: person-hours or story points
- Risk: probability and severity of breaking changes
- Reversibility: how hard is it to undo if it goes wrong?
- Testability: how easily can this be tested?
- Maintainability: how easy to extend or modify in future?
- Alignment with constraints: does it fit all requirements?
- Produce a recommendation: Choose one option with reasoning.
- State which option you recommend and why
- Acknowledge the main tradeoff you are accepting
- Note any blocking assumptions that must be validated first
- List open questions: Flag anything that must be decided externally.
- Questions for the product owner (scope/priority)
- Technical unknowns requiring a spike
- Dependencies on other teams or systems
Output Format
## Proposals: <feature/change>
### Option 1: <name>
**Summary**: <one sentence description>
**Effort**: <estimate>
**Risk**: <low|medium|high> (<reason>)
**Reversibility**: <easy|hard|irreversible>
**Testability**: <easy|medium|hard>
**Pros**: <bullet list>
**Cons**: <bullet list>
### Option 2: <name>
...
### Tradeoff Table
| Option | Effort | Risk | Reversible | Testable |
|--------|--------|------|------------|---------|
| Option 1 | | | | |
| Option 2 | | | | |
### Recommendation
**Recommended**: Option <N>. <rationale in 2-3 sentences>
### Open Questions
1. <question>Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Maicololiveras/praxisgenai-agent-orchestrator★ 1same name
- svg153/skills★ 1same name
- callingcard1973/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- code-reviewSkill
- context-disciplineSkill
- find-skillsSkill
- pr-descriptionSkill
- sdd-applySkill
- sdd-designSkill
- sdd-exploreSkill
- sdd-proposeSkill
- sdd-specSkill
- sdd-tasksSkill
- sdd-verifySkill
- squadai-init-playbookSkill
- testingSkill
- code-reviewSkill
- context-disciplineSkill
- find-skillsSkill
- pr-descriptionSkill
- sdd-applySkill
- sdd-designSkill
- sdd-exploreSkill
- sdd-specSkill
- sdd-tasksSkill
- sdd-verifySkill
- squadai-init-playbookSkill
- testingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

