MVPavan/via / .claude/skills/design-evolve
design-evolve
VerifiedUse when integrating supplied discussions or decisions into a self-contained next version of existing design documents.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
| agents/openai.yaml | config | 42 B |
| references/integration.md | markdown | 1.5 KB |
references/integration.md
View on GitHub# Large-set integration mechanics
Maintain a compact concept map: source file/section, maturity, affected target
sections, decision, exclusions and unresolved conflicts. The map is an evidence
artifact, not an independent task tracker. Keep durable work status in Beads.
For large files, read concept-relevant sections with enough surrounding context
to preserve invariants. Assign independent readers clear sections and require
exact source pointers; inspect consequential source text before integrating.
Multiple writers must own disjoint target files or run sequentially.
Mirror the source core layout and filename convention under the target version.
Copy untouched documents so the set remains complete. Check all forms of old
version identifiers and filenames with search; review legitimate historical
references rather than blindly replacing version numbers in technical content.
Preserve heading hierarchy, invariant identifiers, table meanings and link targets.
Distill implementation guides into design decisions only when their meaning is
clear. Comparison notes supply the selected decision and rationale; preserve full
analysis only when requested. New subsystem documents need authorized scope and
source-backed content, not invented details to fill a template.
Useful handoff fields: integrated concept, affected files, source decisions,
verification, unresolved/deferred items. A provenance/history section may reference
prior versions; the operative design must contain all its required content.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |