data-ai MCP Server
Claude Code skills, architectural principles, and alternative approaches for AI-assisted development
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Non-blocking nudge: substantive build/refactor ask + no plan artifact in the project -> one-line "freeze acceptance criteria first" reminder (max once/day)
Focus
`frontend-design`
Blocks commits/PRs carrying `Co-Authored-By: Claude` footers (see [rules/no-claude-attribution.md](rules/no-claude-attribution.md))
UNet, DiT, Flow Matching, Flux architectures, LoRA, schedulers, memory optimization
Event
Skill
`ios-development`
Approaches Compared
Reverse-engineer images into reproducible prompts
Blocks closing with OPEN problems lacking a valid deferral reason
Verifies a destructive operation actually completed (object really gone)
When to use
`workflow-orchestration`
LoRA training for FLUX.2 Klein 9B and Qwen Image Edit
Prompt engineering for FLUX.2 Klein
`plan-swarm-review`
`video-post-production`
`article-structure-review`
`gemini-delegate`
Question it answers
Surfaces pending tasks from `.claude/task-inbox/`
Demands a fresh handoff before context compaction; writes an AUTO-DRAFT fallback if none exists
VLM + segmentation: SAM2/3, Florence-2, YOLO-World