// Spec-Driven Product Development - A 3-phase methodology (Research, Spec, Implementation) for building software from structured specifications.
Answer questions about Claude Code / Anthropic agent design patterns (CLAUDE.md layering, skills anatomy, progressive disclosure, memory-first, orchestration, sub-agents, worktree isolation, Karpathy loop). Primary backend is a NotebookLM RAG over Anthropic design notebooks; falls back to bundled references when the notebook is not registered.
INTERNAL ONLY. Forked write-capable variant of the public notebooklm skill. Adds programmatic source ingestion (add_source) for the X/YouTube → NotebookLM pipeline (#119). Headless, non-interactive, cron-driven. NEVER ship publicly.
Documentation harvesting agent for crawling and extracting content from documentation websites. Use for crawling documentation sites and extracting all pages about a subject, building offline knowledge bases from online docs, harvesting API references, tutorials, or guides from documentation portals, creating structured markdown exports from multi-page documentation, and downloading and organizing technical docs for embedding or RAG pipelines. Supports recursive crawling with depth control, content filtering, and structured output.
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, cr...
Generates images via Openrouter API using AI image models. Supports two modes: test (cheap model for iteration) and production (high-quality model for final output). Handles prompt construction, API calls, base64 decoding, and file saving. Supports reference images (logos, mascots) for brand-consistent generation.
Intelligent token optimization through Qdrant-powered semantic caching and long-term memory. Use for (1) Semantic Cache - avoid LLM calls entirely for semantically similar queries with 100% token savings, (2) Long-Term Memory - retrieve only relevant context chunks instead of full conversation history with 80-95% context reduction, (3) Hybrid Search - combine vector similarity with keyword filtering for technical queries, (4) Memory Management - store and retrieve conversation memories, decisions, and code patterns with metadata filtering. Triggers when needing to cache responses, remember past interactions, optimize context windows, or implement RAG patterns.
| name | spdd |
| description | Spec-Driven Product Development - A 3-phase methodology (Research, Spec, Implementation) for building software from structured specifications. |
A structured methodology for building software through three sequential phases:
1-research.md) — Codebase analysis and technical cartography2-spec.md) — Product specification and architecture design3-implementation.md) — Code generation following the spec1-research.md — Codebase Research Agent instructions2-spec.md — Specification writing methodology3-implementation.md — Implementation execution guidelinesAdapted for @techwavedev/agi-agent-kit Original source: antigravity-awesome-skills
Retrieve prior Architecture Decision Records (ADRs), trade-off analyses, and system design rationale. Critical for maintaining consistency across long-running projects.
# Check for prior architecture/design context before starting
python3 execution/memory_manager.py auto --query "architecture decisions and trade-off analysis for Spdd"
After completing work, store architecture/design decisions for future sessions:
python3 execution/memory_manager.py store \
--content "Architecture: event-driven microservices with CQRS, Pulsar for messaging, Qdrant for semantic search" \
--type decision --project <project> \
--tags spdd architecture
Broadcast architecture decisions to ALL agents so implementation stays aligned with the chosen patterns.
python3 execution/cross_agent_context.py store \
--agent "<your-agent>" \
--action "Completed architecture review — ADR documented, trade-offs analyzed, team aligned" \
--project <project>
Register architecture tasks in the Control Tower so all agents across machines know the current system design and constraints.