Merge pull request #8 from pinecone-io/arjun-fts

Skill name updates with FTS!

Author: arjunpatel7

.cursor-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "pinecone",
-  "description": "Pinecone vector database integration for Cursor. Create and manage indexes, upsert data, and run semantic searches via the Pinecone MCP server. Build document Q&A assistants with citations, or get started fast with /quickstart. Great for semantic search, RAG, and agentic AI apps.",
+  "description": "Pinecone vector database integration for Cursor. Create and manage indexes, upsert data, and run semantic searches via the Pinecone MCP server. Build document Q&A assistants with citations, or get started fast with /pinecone-quickstart. Great for semantic search, RAG, and agentic AI apps.",
   "version": "1.0.0",
   "author": {
     "name": "Pinecone"

.github/workflows/contextualize-skills.yml

@@ -88,7 +88,7 @@ jobs:
           - Each skill lives in \`skills/<skill-name>/SKILL.md\`
           - SKILL.md requires YAML frontmatter with \`name\` (lowercase kebab-case, must match folder name) and \`description\`
           - Skills can include \`scripts/\`, \`references/\`, and \`assets/\` subdirectories
-          - Folder names must NOT have a \`pinecone-\` prefix
+          - Folder names MUST be prefixed with \`pinecone-\` (e.g. \`pinecone-quickstart\`, \`pinecone-cli\`). Add the prefix if it's missing.
           - Only \`.md\` files should be modified — never touch \`.py\` scripts
 
           ## Steps
@@ -111,8 +111,13 @@ jobs:
              - Do NOT modify .py files in scripts/ directories — leave them exactly as they are
              - Do not change the meaning or content of the skills
              - Only change structure, formatting, field names, or terminology as needed
-          3. Rename skill directories to strip the \`pinecone-\` prefix if present.
-             Use \`mv skills/pinecone-foo skills/foo\` for each directory that has the prefix.
+          3. Rename skill directories to ADD the \`pinecone-\` prefix if missing.
+             For each \`skills/<name>\` that does not start with \`pinecone-\`, run
+             \`git mv skills/<name> skills/pinecone-<name>\` and update the \`name:\`
+             field in that skill's \`SKILL.md\` frontmatter to match the new folder.
+             Also update any cross-references (slash commands like \`/<name>\`,
+             sibling-skill paths like \`../<name>/scripts/...\`, and "the <name> skill"
+             prose) to the prefixed form.
           4. Validate against the Cursor plugin submission checklist:
              - .cursor-plugin/plugin.json exists and is valid JSON
              - Plugin \`name\` is lowercase kebab-case

.gitignore

@@ -12,5 +12,8 @@ Thumbs.db
 # Contextualization artifacts
 .contextualize-summary.md
 
+# Cursor agent logs
+.cursor-logs/
+
 # Local dev docs
 REPO_MAINTENANCE.md

README.md

@@ -10,13 +10,14 @@ Skills are specialized agent capabilities invoked automatically by Cursor Agent
 
 | Skill | What it does |
 |-------|-------------|
-| `/quickstart` | Step-by-step onboarding — create an index, upload data, and run your first search. Choose between a **Database** path (vector search) or **Assistant** path (document Q&A). |
-| `/query` | Search integrated indexes using natural language text via the Pinecone MCP server. |
-| `/cli` | Use the Pinecone CLI (`pc`) for terminal-based index and vector management. |
-| `/assistant` | Create, manage, and chat with Pinecone Assistants for document Q&A with citations. Includes scripts for uploading files, syncing changes, and retrieving context. |
-| `/mcp` | Reference documentation for all Pinecone MCP server tools and their parameters. |
-| `/docs` | Curated links to official Pinecone documentation, organized by topic. |
-| `/help` | Overview of all available skills and what you need to get started. |
+| `/pinecone-quickstart` | Step-by-step onboarding — create an index, upload data, and run your first search. Choose between a **Database** path (vector search) or **Assistant** path (document Q&A). |
+| `/pinecone-query` | Search integrated indexes using natural language text via the Pinecone MCP server. |
+| `/pinecone-cli` | Use the Pinecone CLI (`pc`) for terminal-based index and vector management. |
+| `/pinecone-assistant` | Create, manage, and chat with Pinecone Assistants for document Q&A with citations. Includes scripts for uploading files, syncing changes, and retrieving context. |
+| `/pinecone-full-text-search` | Create, ingest into, and query a Pinecone full-text-search (FTS) index using the preview API. |
+| `/pinecone-mcp` | Reference documentation for all Pinecone MCP server tools and their parameters. |
+| `/pinecone-docs` | Curated links to official Pinecone documentation, organized by topic. |
+| `/pinecone-help` | Overview of all available skills and what you need to get started. |
 
 ### MCP Server
 
@@ -33,14 +34,15 @@ Several skills include Python scripts (run via [`uv`](https://docs.astral.sh/uv/
 
 | Script | Skill | Purpose |
 |--------|-------|---------|
-| `upsert.py` | quickstart | Seed an index with sample data |
-| `quickstart_complete.py` | quickstart | Standalone end-to-end quickstart |
-| `create.py` | assistant | Create a new Pinecone Assistant |
-| `upload.py` | assistant | Upload files to an assistant |
-| `chat.py` | assistant | Chat with an assistant |
-| `context.py` | assistant | Retrieve context snippets from an assistant |
-| `list.py` | assistant | List all assistants in your account |
-| `sync.py` | assistant | Sync local files to an assistant |
+| `upsert.py` | pinecone-quickstart | Seed an index with sample data |
+| `quickstart_complete.py` | pinecone-quickstart | Standalone end-to-end quickstart |
+| `create.py` | pinecone-assistant | Create a new Pinecone Assistant |
+| `upload.py` | pinecone-assistant | Upload files to an assistant |
+| `chat.py` | pinecone-assistant | Chat with an assistant |
+| `context.py` | pinecone-assistant | Retrieve context snippets from an assistant |
+| `list.py` | pinecone-assistant | List all assistants in your account |
+| `sync.py` | pinecone-assistant | Sync local files to an assistant |
+| `ingest.py` | pinecone-full-text-search | Bulk-ingest a prepared JSONL into an FTS index |
 
 ## Installation
 
@@ -73,7 +75,7 @@ Or install directly from the marketplace: [cursor.com/marketplace/pinecone](http
 
 1. Install the plugin from the [Cursor Marketplace](https://cursor.com/marketplace)
 2. Add `PINECONE_API_KEY=your-key` to a `.env` file at your workspace root (Cursor will load it into the MCP server via `envFile`)
-3. Open Cursor Agent chat and type `/quickstart` to get started
+3. Open Cursor Agent chat and type `/pinecone-quickstart` to get started
 4. Verify the MCP server is connected: Cursor Settings > Features > Model Context Protocol
 
 ## Verifying the installation

skills/assistant/.gitkeep skills/pinecone-assistant/.gitkeepskills/assistant/.gitkeep renamed to skills/pinecone-assistant/.gitkeep

@@ -1,5 +1,5 @@
 ---
-name: assistant
+name: pinecone-assistant
 description: Create, manage, and chat with Pinecone Assistants for document Q&A with citations. Handles all assistant operations - create, upload, sync, chat, context retrieval, and list. Recognizes natural language like "create an assistant from my docs", "ask my assistant about X", or "upload my docs to Pinecone".
 ---