Consolidate 35 skills into 10 umbrella skills

Consolidates all standalone skills into 10 umbrella skills to reduce
cognitive load and improve agent navigation:

1. constructive - Platform core (safegres, services-schemas, deployment, server-config, functions, cnc-execution-engine, constructive-env)
2. pgpm - stays as-is + absorbs github-workflows-pgpm as CI/CD reference
3. constructive-graphql - codegen, sdk-search, graphql-query, search, pagination
4. constructive-starter-kits - boilerplate-pgpm-init, boilerplate-nextjs-app, boilerplate-authoring
5. constructive-frontend - constructive-ui, crud-stack, meta-forms
6. constructive-testing - pgsql-test, drizzle-orm-test, supabase-test, drizzle-orm, pgsql-parser-testing
7. constructive-ai - pgvector-rag, github-workflows-ollama
8. constructive-tooling - constructive-pnpm, inquirerer-cli, readme-formatting
9. graphile-search - stays as-is (plugin internals, team-level)
10. fbp - fbp-types, fbp-spec, fbp-evaluator, fbp-graph-editor

Also deletes planning-blueprinting (not ours).
Updates AGENTS.md and CLAUDE.md with new skill structure.

Author: pyramation

AGENTS.md

@@ -6,7 +6,22 @@ This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, e
 
 ## Repository Overview
 
-A collection of skills for different ai agents for working with Constructive tooling. Skills are packaged instructions and scripts that extend agents' capabilities.
+A collection of skills for AI coding agents working with Constructive tooling. Skills are organized into **10 umbrella skills** that consolidate related functionality:
+
+| Skill | Absorbs | Purpose |
+|-------|---------|---------|
+| **constructive** | safegres, services-schemas, deployment, server-config, functions, cnc-execution-engine, constructive-env | Platform core |
+| **pgpm** | github-workflows-pgpm | Database migrations, CLI, Docker, CI/CD |
+| **constructive-graphql** | graphql-codegen, sdk-search, graphql-query | Codegen, runtime queries, search, pagination |
+| **constructive-starter-kits** | boilerplate-pgpm-init, boilerplate-nextjs-app, boilerplate-authoring | Project scaffolding via `pgpm init` |
+| **constructive-frontend** | constructive-ui, crud-stack, meta-forms | UI components, Stack cards, dynamic forms |
+| **constructive-testing** | pgsql-test, drizzle-orm-test, supabase-test, drizzle-orm, pgsql-parser-testing | All test frameworks |
+| **constructive-ai** | pgvector-rag, github-workflows-ollama | RAG pipelines, embeddings, Ollama CI |
+| **constructive-tooling** | constructive-pnpm, inquirerer-cli, readme-formatting | Dev tools |
+| **graphile-search** | *(standalone)* | Unified search plugin internals (team-level) |
+| **fbp** | fbp-types, fbp-spec, fbp-evaluator, fbp-graph-editor | Flow-Based Programming toolkit |
+
+Each umbrella skill has a `SKILL.md` router and a `references/` directory with detailed topic-specific documentation.
 
 ## Creating a New Skill
 

CLAUDE.md

@@ -6,13 +6,20 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 A collection of skills for AI coding agents working with Constructive tooling. Skills are packaged instructions and scripts that extend agent capabilities for GraphQL development workflows, following the [Agent Skills](https://agentskills.io/) format.
 
-## Available Skills
-
-### constructive-graphql-codegen
-
-Generate and use type-safe React Query hooks or Prisma-like ORM client from PostGraphile GraphQL endpoints.
-
-**Triggers**: "generate GraphQL hooks", "generate ORM", "set up codegen", "use generated hooks", "query with ORM", "fetch data"
+## Available Skills (10 Umbrella Skills)
+
+| Skill | Description |
+|-------|-------------|
+| **constructive** | Platform core — security model (Safegres), services/schemas, deployment, server config, cloud functions, env config, CNC CLI |
+| **pgpm** | PostgreSQL Package Manager — migrations, CLI, Docker, CI/CD workflows |
+| **constructive-graphql** | Unified GraphQL — codegen (hooks, ORM, CLI), runtime queries, search (all algorithms), pagination |
+| **constructive-starter-kits** | Project scaffolding — `pgpm init` templates, Next.js app boilerplate, custom template authoring |
+| **constructive-frontend** | UI components (50+ on Base UI + Tailwind v4), CRUD Stack cards, dynamic `_meta` forms |
+| **constructive-testing** | All test frameworks — pgsql-test, drizzle-orm-test, supabase-test, Drizzle ORM patterns, pgsql-parser |
+| **constructive-ai** | AI capabilities — pgvector RAG pipelines, embeddings, Ollama CI/CD |
+| **constructive-tooling** | Dev tools — pnpm workspaces, inquirerer CLI framework, README formatting |
+| **graphile-search** | Unified search plugin internals — SearchAdapter, tsvector/BM25/trgm/pgvector adapters (team-level) |
+| **fbp** | Flow-Based Programming — types, spec, evaluator, graph editor |
 
 ## Commands
 

skills/constructive-ai/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: constructive-ai
+description: "AI and vector search capabilities — pgvector RAG pipelines (embeddings, similarity search, agentic kits), and Ollama CI/CD workflows for running LLM models in GitHub Actions. Use when building RAG pipelines, working with embeddings, running Ollama in CI, or implementing AI-powered search."
+metadata:
+  author: constructive-io
+  version: "1.0.0"
+---
+
+# Constructive AI
+
+Build AI-powered features with pgvector RAG pipelines and Ollama CI/CD workflows.
+
+## When to Apply
+
+Use this skill when:
+- Building RAG (Retrieval-Augmented Generation) pipelines
+- Working with vector embeddings and similarity search
+- Setting up Ollama LLM models in CI/CD
+- Implementing AI-powered search or agentic workflows
+
+## pgvector RAG
+
+Build end-to-end RAG pipelines: embed documents → store in pgvector → similarity search → feed to LLM.
+
+See [pgvector-rag.md](./references/pgvector-rag.md) for the full RAG pipeline guide.
+
+## Ollama CI/CD
+
+Run Ollama LLM models in GitHub Actions for testing and validation.
+
+See [ollama-ci.md](./references/ollama-ci.md) for CI workflow configuration.
+
+## Reference Guide
+
+| Reference | Topic | Consult When |
+|-----------|-------|--------------|
+| [pgvector-rag.md](./references/pgvector-rag.md) | RAG pipeline overview | Building end-to-end RAG systems |
+| [rag-embeddings.md](./references/rag-embeddings.md) | Embedding generation | Creating and storing vector embeddings |
+| [rag-similarity-search.md](./references/rag-similarity-search.md) | Similarity search | Querying vectors, distance metrics |
+| [rag-rag-pipeline.md](./references/rag-rag-pipeline.md) | Full RAG pipeline | Document ingestion → retrieval → generation |
+| [rag-setup.md](./references/rag-setup.md) | pgvector setup | Installing pgvector, creating indexes |
+| [rag-ollama.md](./references/rag-ollama.md) | Ollama integration | Using Ollama for local LLM inference |
+| [rag-agentic-kit.md](./references/rag-agentic-kit.md) | Agentic kit patterns | Building AI agents with RAG |
+| [ollama-ci.md](./references/ollama-ci.md) | Ollama GitHub Actions | Running LLM models in CI/CD |
+
+## Cross-References
+
+- `graphile-search` — Unified search plugin (includes pgvector adapter)
+- `constructive-graphql` — Search via codegen SDK (pgvector queries)
+- `pgpm` — Database migrations for vector tables