usemoss/moss/zo-skill
Claude Code and agent skill by usemoss/moss
- community
Checking that the SKILL.md file is still in the repository.
Sub-10ms semantic search for Zo via Moss. Create indexes, add documents, and query them with semantic and keyword search. Use when users want to search through documents, knowledge bases, or any text content.
Install
npx vskill@latest install usemoss/moss/zo-skillSKILL.md
Moss Search
Sub-10ms semantic search. Run from anywhere:
Commands
load-index
Download an index into memory for sub-10ms local queries. Always call this before searching an index for the first time.
Examples:
search
Search a loaded index. Sub-10ms after load-index.
Examples:
create-index
Create a new index with initial documents.
Example:
list-indexes
List all available indexes.
add-docs
Add documents to an existing index.
Example:
delete-docs
Delete documents by ID.
get-docs
Retrieve documents from an index.
delete-index
Delete an entire index.
For Zo
On every new conversation
- Run
moss.sh list-indexesto see what indexes are available. - Run
moss.sh load-index <index>for each index the user is likely to need. - Run
moss.sh search <index> "<keywords>"to surface relevant context from the user's first message. - Weave relevant results into your response naturally.
Skip the startup load for vague openers like "hey" or "what's up".
When to search
- User asks about information that might be in an indexed collection
- User references prior documents, notes, or knowledge base content
- You are about to give advice and relevant indexed context may exist
- Earlier search results were weak — try 2-3 alternate keyword queries
When to create/update indexes
- User explicitly asks: "index this", "add this to search", "create an index"
- User provides documents, notes, or data they want searchable
- User wants to build a knowledge base or FAQ
Using search results
- Use relevant results naturally — cite them inline
- If a result conflicts with what the user says, mention it: "The indexed docs say X — has that changed?"
- If no relevant results are found, proceed normally
Behavior summary
| User signal | Action | |
|---|---|---|
| New conversation starts | moss.sh list-indexes then moss.sh load-index + moss.sh search relevant indexes | |
| "Search for..." / "Find..." / "Look up..." | moss.sh search <index> "<query>" (load-index first if not loaded) | |
| "Index this" / "Add to search" | moss.sh add-docs <index> '<docs>' | |
| "Create an index" / "New collection" | moss.sh create-index <name> '<docs>' | |
| "Delete this document" | moss.sh delete-docs <index> '["id"]' | |
| "Remove this index" | moss.sh delete-index <index> | |
| "What indexes do I have?" | moss.sh list-indexes | |
| "Show me the documents in..." | moss.sh get-docs <index> |
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/zo-computer/zo-skill/SKILL.md
Popularity
- Repository stars
- 438
- Repository forks
- 56
- 7-day trend score
- 30
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/usemoss/moss/zo-skill)