retrofit-design
Create design documentation from existing implementation
What this skill does
# Retrofit Design
Create design documentation from existing implementation code.
## Input
Feature path: $ARGUMENTS (e.g., "auth/login" for docs/feature-specs/auth/login.md)
## Context
**You must load the following skills and read the following files before proceeding.**
### Skills
- `katachi:retrofit-existing` - Retrofit workflow
### Feature documentation
- `docs/feature-designs/README.md` - Feature design index
- Read feature-specs/$ARGUMENTS.md (feature path) for spec context
### Retrofitted spec
- `docs/feature-specs/$ARGUMENTS.md` - The feature specification (created by retrofit-spec, e.g., auth/login.md)
### Project decisions
- `docs/architecture/README.md` - Architecture decisions (ADRs)
- `docs/design/README.md` - Design patterns (DES)
### Existing design (if present)
- `docs/feature-designs/$ARGUMENTS.md` - Current design to update or create
### Vision (if present)
- `docs/planning/VISION.md` - Project context for inference
### Reference Guides
- `${CLAUDE_PLUGIN_ROOT}/skills/framework-core/references/technical-diagrams.md` - Technical diagram guidance
- `${CLAUDE_PLUGIN_ROOT}/skills/framework-core/references/code-examples.md` - Code snippet guidance
## Pre-Check
Verify prerequisites:
- Feature spec exists at `docs/feature-specs/$ARGUMENTS.md`
- Implementation code exists for this feature
- If spec doesn't exist, suggest running `/katachi:retrofit-spec` first
## Process
### 0. Check Existing State
If `docs/feature-designs/$ARGUMENTS.md` exists:
- Read current design
- Summarize: design approach, key decisions, modeling choices
- Ask: "What aspects need refinement? Or should we re-analyze the code?"
- Enter iteration mode as appropriate
If no design exists: proceed with creation
Update status:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py status set $ARGUMENTS "⧗ Design"
```
### 1. Research Phase (Silent)
- Read retrofitted spec (`docs/feature-specs/$ARGUMENTS.md`)
- Extract the source code path from spec's "Retrofit Note"
- Read the implementation code
- Read ADR index (`docs/architecture/README.md`)
- Read DES index (`docs/design/README.md`)
- Read VISION.md if exists
- Build complete understanding of what was built and why
### 2. Dispatch Codebase Analyzer
```python
Task(
subagent_type="katachi:codebase-analyzer",
prompt=f"""
Analyze this code to create a design document.
## Analysis Type
design
## Retrofitted Spec
{spec_content}
## Implementation Code
{code_content}
## Project Context
{vision_content if exists else "Infer from code"}
## Existing ADR Index
{adr_index}
## Existing DES Index
{des_index}
"""
)
```
### 3. Present Draft Design
Show the agent's draft design document.
Highlight uncertainties and assumptions made during inference.
Ask: "What needs adjustment in this inferred design?"
### 4. Iterate Based on Feedback
Apply user corrections:
- Clarify problem context
- Adjust modeling
- Correct data flow
- Add missing decisions
- Fix rationale
Re-present updated sections if significant changes.
Repeat until user approves the core design.
### 5. Integrated Decision Discovery
Review the Key Decisions section for ADR/DES candidates.
Present discovered decisions:
```
"I identified these undocumented decisions while analyzing the design:
1. **[Decision Name]** (architectural choice)
[Brief description]
Recommendation: Create ADR
2. **[Pattern Name]** (repeatable pattern)
[Brief description]
Recommendation: Create DES
3. **[Minor Choice]** (design choice)
[Brief description]
Recommendation: Document inline only
Which decisions should become formal ADR/DES documents?"
```
For each decision the user agrees to document:
```python
# Spawn retrofit-decision inline
Task(
subagent_type="katachi:codebase-analyzer", # Initial analysis
prompt=f"""
Analyze this code to document a specific decision.
## Analysis Type
decision
## Topic
{decision_topic}
## Relevant Code
{code_related_to_decision}
## Project Context
{vision_content}
"""
)
```
After each ADR/DES is created:
- Capture the assigned ID (ADR-XXX or DES-XXX)
- Update the design document to reference it
### 6. External Validation
Dispatch the design-reviewer agent:
```python
Task(
subagent_type="katachi:design-reviewer",
prompt=f"""
Review this retrofitted feature design.
## Feature Spec (Retrofitted)
{spec_content}
## Completed Design
{design_content}
## ADR Index Summary
{adr_summary}
## DES Index Summary
{des_summary}
Note: This design was inferred from existing code.
"""
)
```
Review agent findings with user.
Discuss which recommendations to accept.
### 7. Finalize with Iteration Check
Ask: "Should we iterate based on validation feedback, or is the design complete?"
If gaps to address → refine relevant sections (go back to step 4)
If complete → finalize document
Write design to `docs/feature-designs/$ARGUMENTS.md`:
```markdown
# Design: [FEATURE-ID] - [Feature Name]
**Feature Spec**: [../feature-specs/FEATURE-ID.md](../feature-specs/FEATURE-ID.md)
**Status**: Approved
## Retrofit Note
This design was created from existing code at `[path from spec]`.
Original implementation date: [from git history or "Unknown"]
Decisions documented during retrofit: [ADR-XXX, DES-YYY, ...]
---
## Purpose
This document captures the design rationale inferred from the existing implementation.
## Problem Context
[Inferred from what the code solves]
## Design Overview
[High-level approach extracted from code]
## Modeling
[Entities/relationships from code structure]
## Data Flow
[Traced from execution paths]
## Key Decisions
### [Decision Name]
**Choice**: [What the code shows]
**Why**: [Inferred rationale]
**Related**: [ADR-XXX if created during retrofit]
## System Behavior
[Documented from code paths]
## Notes
- Assumptions made during analysis: [list]
```
Update status:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py status set $ARGUMENTS "✓ Design"
```
### 8. Summary and Next Steps
```
"Design retrofitted for existing code:
File: docs/feature-designs/$ARGUMENTS.md
Status: ✓ Design
Decisions created: [ADR-XXX, DES-YYY, ...]
The feature now has both specification and design documentation.
You can now:
- Retrofit another spec: /katachi:retrofit-spec <path>
- Retrofit another design: /katachi:retrofit-design <ID>
- Document additional decisions: /katachi:retrofit-decision <topic>
- Run gap analysis: /katachi:analyze"
```
## Workflow
**This is a collaborative process:**
- Research silently (code, spec, ADRs, DES)
- Draft design from code analysis
- Present and iterate with user
- Discover and document ADR/DES patterns inline
- Validate with design-reviewer agent
- Finalize after user approval
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.