sdd-planning
Skill198 starsChanged 5 months agoMITView on GitHub
Generate technical plans from specifications. Use when creating architecture documents, designing system components, or preparing for implementation.
In this repository6 other files it gives its agents.
- .cursor/rules/sdd-system.mdcCursor rule
- sdd-auditSkill
- sdd-evolveSkill
- sdd-implementationSkill
- sdd-memorySkill
- sdd-researchSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
After research is complete
- Very specific: line 20
Read spec.md, note functional/non-functional requirements, review research findings.
- Distinctive: line 65
Use the ask question tool for architectural decisions with significant tradeoffs
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SDD Planning Skill
Transform specifications into actionable technical plans.
When to Use
- Spec exists but plan doesn't
- Designing system architecture
- Breaking down features into components
- After research is complete
Planning Protocol
Step 1: Understand Requirements
Read spec.md, note functional/non-functional requirements, review research findings.
Step 2: Design Architecture
Identify components, define responsibilities, design interfaces, plan data flow.
Step 3: Select Technology
Evaluate against requirements, consider existing stack, document rationale.
Step 4: Plan Implementation
Break into phases (Setup → Core → Integration → Polish), identify dependencies, estimate effort.
Step 5: Assess Risks
Identify technical risks, plan mitigations, note assumptions.
Output Format
Generate plan.md with:
# Technical Plan: [Task ID]
## Overview
## Architecture (Mermaid diagram)
## Components (table: name, responsibility, dependencies)
## Technology Stack (with rationale)
## API Design
## Data Models
## Security Considerations
## Performance Targets
## Implementation Phases (Setup → Core → Integration → Polish)
## Risks (probability, impact, mitigation)
## Testing Strategy (unit, integration, E2E)
## Open QuestionsReferences
assets/diagram-templates.md— Architecture diagram patterns (Mermaid templates)references/estimation-heuristics.md— Task sizing guidelines, common pitfalls, and estimation by task type.sdd/templates/decision-matrix.md— When to use Brief vs Full SDD planning
Integration
- Input from:
sdd-researchskill,sdd-explorersubagent - Output to:
/taskscommand,sdd-implementersubagent - Use the ask question tool for architectural decisions with significant tradeoffs
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.