Automated summary
This skill orchestrates design document creation by generating a skeleton, delegating each section to specialist skills (frontend, UI/UX, security, performance), and then merging their outputs.
Strengths
- Breaks design work into explicit phases: skeleton, parallel specialists, merge
- Requirement traceability through @derives annotations and a REQ-to-section mapping table
- Includes a decisions log and a cross-cutting concerns table with owner and reviewer per concern
- Bootstraps a YAML state file that tracks the status of each section
Limitations
- The skill makes no design decisions itself and depends entirely on the referenced specialist skills being available
- The provided text is truncated at the merge phase, so the detailed merge steps are not described
- Assumes a specific file layout and spec format (packages/{package}/spec/, .sdd/state.yaml)
Use it when starting the design phase of a package and you need a structured document covering architecture, UI/UX, security, and performance.
Avoid it when the specialist skills are not installed, or for a small change that does not warrant a multi-section design document.
Security analysis
SafeThe skill is a pure documentation-orchestration workflow: it reads a requirements file, scaffolds a design markdown skeleton, delegates sections to named specialist skills, merges outputs, and records progress in a YAML state file. No shell execution, network calls, credential handling, obfuscated payloads, or destructive file operations appear anywhere. The only side effects are creating/updating files under packages/{package}/spec/ and .sdd/state.yaml, which is consistent with its stated purpose. No allowed-tools are declared, so the agent's default permissions bound its behavior.
No concerns found
How this analysis is madeExamples
Start the design phase for packages/auth and create the design skeleton from its requirements document.Merge the design sections produced by the specialists into packages/auth/spec/auth.design.md and resolve any conflicts.Read the requirements for packages/core and fill in the @derives annotations for each section of the design skeleton.name: sdd-design description: | Orchestrate design document creation using specialist skills. Use when: starting design phase, merging specialist outputs, resolving design conflicts. Triggers: "create design", "design phase", "merge design", "design skeleton"
SDD Design Orchestrator
Coordinate specialist skills to produce a complete design document.
Role
| Do | Don't | |----|-------| | Create skeleton structure | Write implementation details | | Assign sections to specialists | Make design decisions | | Map REQs to sections | Choose libraries or patterns | | Merge specialist outputs | Override specialist decisions | | Resolve conflicts between specialists | Skip specialist review |
Specialists
| Skill | Domain | Invocation | |-------|--------|------------| | sdd-design-frontend | Component architecture, state, patterns | After skeleton | | sdd-design-uiux | Layout, responsive, accessibility | After skeleton | | sdd-design-security | Threats, sandboxing, validation | After skeleton | | sdd-design-perf | Bundle size, lazy loading, caching | After skeleton |
Workflow
Phase 1: Skeleton
│
├─→ Phase 2: Specialists (parallel)
│ ├── frontend
│ ├── uiux
│ ├── security
│ └── perf
│
└─→ Phase 3: Merge
Instructions
Phase 1: Create Skeleton
-
Read requirements document
packages/{package}/spec/{package}.requirements.md -
Create design file
packages/{package}/spec/{package}.design.md -
Write skeleton using template:
---
title: "{Package} Design"
author: Claude
date: {YYYY-MM-DD}
version: 1.0.0
status: draft
depends_on:
- packages/{package}/spec/{package}.requirements.md@{version}
---
# {Package} Design
## Overview
Brief description of the design approach.
@derives: (list all REQ IDs)
**Status:** draft
## Component Architecture
@derives: {REQ-IDs}
<!-- sdd-design-frontend writes this section -->
**Status:** pending
## UI/UX Design
@derives: {REQ-IDs}
<!-- sdd-design-uiux writes this section -->
**Status:** pending
## Security Considerations
@derives: {REQ-IDs}
<!-- sdd-design-security writes this section -->
**Status:** pending
## Performance Strategy
@derives: {REQ-IDs}
<!-- sdd-design-perf writes this section -->
**Status:** pending
## Decisions Log
| ID | Decision | Rationale | Owner |
|----|----------|-----------|-------|
| | | | |
## Cross-Cutting Concerns
> **Note:** Extension to sdd-guidelines for specialist coordination.
| Concern | Primary | Reviewer | Status |
|---------|---------|----------|--------|
| Accessibility | uiux | frontend | pending |
| Error handling | frontend | security | pending |
| Loading states | uiux | perf | pending |
- Initialize state file
# .sdd/state.yaml (add to existing)
documents:
design:
status: draft
sections:
component-architecture:
status: pending
owner: sdd-design-frontend
uiux:
status: pending
owner: sdd-design-uiux
security:
status: pending
owner: sdd-design-security
perf:
status: pending
owner: sdd-design-perf
-
Map REQs to sections
Read each requirement and determine which section(s) address it:
| Section | Typical REQs | |---------|--------------| | Component Architecture | Structure, data flow, patterns | | UI/UX Design | Layout, interaction, responsive | | Security | User input, code execution, XSS | | Performance | Loading, bundle size, caching |
-
Fill @derives for each section
Phase 2: Invoke Specialists
Invoke all specialists in parallel. Each specialist:
- Reads the skeleton
- Reads assigned REQs
- Writes their section
- Adds decisions to Decisions Log
Invocation format:
Use sdd-design-{specialist} to write the {Section Name} section
for packages/{package}/spec/{package}.design.md
Phase 3: Merge
After all specialists complete:
-
Collect outputs
- Each specialist's section content
- Decisions added to log
-
Check conflicts
| Conflict Type | Detection | Resolution | |---------------|-----------|------------| | Library choice | Same need, different lib | Perf wins unless security concern | | Pattern choice | Same problem, different pattern | Frontend decides | | Layout vs Perf | UX wants X, Perf says too heavy | UX for primary flow, Perf for edge | | Any vs Security | Security flags risk | Security wins, find alternative |
-
Review cross-cutting concerns
For each concern:
- Primary owner wrote the approach
- Reviewer validates from their perspective
- Mark status:
approvedorneeds-revision
-
Ensure consistency
- Terminology matches across sections
- No contradicting decisions
- All REQs have @derives coverage
-
Update status
- If no conflicts:
status: verified - If unresolved:
status: blocked+ note
- If no conflicts:
Example: react-sample
Skeleton REQ Mapping
| Section | REQs | |---------|------| | Component Architecture | REQ-REACT-001, 002, 003, 004 | | UI/UX Design | REQ-REACT-002, 003, 005 | | Security Considerations | REQ-REACT-004 | | Performance Strategy | REQ-REACT-003, 004 |
Cross-Cutting for react-sample
| Concern | Primary | Reviewer | Notes | |---------|---------|----------|-------| | Accessibility | uiux | frontend | Keyboard nav for playground | | Error handling | frontend | security | Editable code errors | | Loading states | uiux | perf | Code viewer lazy load | | Code display | frontend | perf | Syntax highlighter choice | | User input | frontend | security | Props playground inputs |
Verification
After merge:
- [ ] All REQs appear in at least one @derives
- [ ] No section has placeholder comments
- [ ] Decisions Log has entries from each specialist
- [ ] Cross-cutting concerns all
approved - [ ] No contradicting decisions
- [ ] Frontmatter complete (title, version, depends_on)
Conflict Escalation
If specialists can't resolve:
- Document both options in Decisions Log
- Set decision status to
escalated - Flag for human review:
> ⚠️ **Escalated:** {description} > Options: A) {option1} B) {option2} > Blocked until human decision.
References
- reference/section-templates.md — Detailed section structures
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/sdd-design-orchestrator-mm78no5w' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/sdd-design-orchestrator-mm78no5w/download' --output '.skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md.part' && mv '.skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md.part' '.skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md' && test -s '.skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/sdd-design' && cp -R '.skill-downloads/sdd-design-orchestrator-mm78no5w' '.claude/skills/sdd-design'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/sdd-design-orchestrator-mm78no5w'openskills read 'sdd-design-orchestrator-mm78no5w'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/sdd-design-orchestrator-mm78no5w/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.