moss
Moss real-time semantic search API for conversational and voice AI agents. Use when user mentions "Moss", "moss.dev", "real-time semantic search", "voice agent retrieval", or "low-latency RAG".
What this skill does
# Moss
[Moss](https://www.moss.dev) is a real-time semantic search runtime for conversational and voice AI agents. Indexes and queries live next to the agent (server, browser, or device) so retrieval lands in under 10 ms.
> Official docs: `https://docs.moss.dev/docs/start/quickstart`
---
## When to Use
Use this skill when you need to:
- Build a low-latency retrieval layer for a voice or chat agent
- Manage a Moss index (create, add docs, search, update, delete)
- Bulk-load knowledge base content into a Moss project
- Inspect or list the indexes that already exist in a Moss project
---
## Prerequisites
Connect the **Moss** connector at [app.vm0.ai/connectors](https://app.vm0.ai/connectors).
> **Troubleshooting:** If requests fail, run `zero doctor check-connector --env-name MOSS_PROJECT_KEY` or `zero doctor check-connector --url https://api.moss.dev/v1/indexes --method GET`
## Environment Variables
| Variable | Description |
|---|---|
| `MOSS_PROJECT_ID` | Moss project identifier (paired with the project key) |
| `MOSS_PROJECT_KEY` | Moss project API key |
Both values come from the Moss portal — pair them on every request.
---
## How to Use
Base URL: `https://api.moss.dev`
Every request includes both the project id and the project key. Moss accepts them as headers (`X-Moss-Project-Id` + `Authorization: Bearer …`); the SDK passes them through the same way.
### 1. List indexes in a project
```bash
curl -s -X GET "https://api.moss.dev/v1/indexes" --header "X-Moss-Project-Id: $MOSS_PROJECT_ID" --header "Authorization: Bearer $MOSS_PROJECT_KEY"
```
### 2. Create an index
Write to `/tmp/moss_index.json`:
```json
{
"name": "support-kb",
"description": "Support knowledge base"
}
```
```bash
curl -s -X POST "https://api.moss.dev/v1/indexes" --header "X-Moss-Project-Id: $MOSS_PROJECT_ID" --header "Authorization: Bearer $MOSS_PROJECT_KEY" --header "Content-Type: application/json" -d @/tmp/moss_index.json
```
### 3. Add documents to an index
Replace `<index-name>` with the index you created above.
Write to `/tmp/moss_docs.json`:
```json
{
"docs": [
{ "text": "How do I track my order?" },
{ "text": "What is the refund policy?" }
]
}
```
```bash
curl -s -X POST "https://api.moss.dev/v1/indexes/<index-name>/docs" --header "X-Moss-Project-Id: $MOSS_PROJECT_ID" --header "Authorization: Bearer $MOSS_PROJECT_KEY" --header "Content-Type: application/json" -d @/tmp/moss_docs.json
```
### 4. Semantic search
Replace `<index-name>` with your index.
Write to `/tmp/moss_query.json`:
```json
{
"query": "how do refunds work?",
"top_k": 5
}
```
```bash
curl -s -X POST "https://api.moss.dev/v1/indexes/<index-name>/search" --header "X-Moss-Project-Id: $MOSS_PROJECT_ID" --header "Authorization: Bearer $MOSS_PROJECT_KEY" --header "Content-Type: application/json" -d @/tmp/moss_query.json | jq '.results[] | {score, text: .doc.text}'
```
### 5. Delete an index
Replace `<index-name>` with the index to remove.
```bash
curl -s -X DELETE "https://api.moss.dev/v1/indexes/<index-name>" --header "X-Moss-Project-Id: $MOSS_PROJECT_ID" --header "Authorization: Bearer $MOSS_PROJECT_KEY"
```
---
## Guidelines
1. Pair `MOSS_PROJECT_ID` and `MOSS_PROJECT_KEY` on every request — Moss scopes credentials per project, not per token.
2. Keep indexes small and topical; Moss is optimised for hot, conversational retrieval, not for archival search.
3. Prefer the Python or TypeScript SDK (`MossClient(PROJECT_ID, PROJECT_KEY)`) when you control the runtime — it streams updates and packages indexes for browser/device deployment automatically.
4. For voice agents, run the search call in parallel with model thinking so the <10 ms latency budget is preserved.
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.