← Back to Skills Marketplace
Moss
by
Keshav Arora
· GitHub ↗
· v1.0.3
913
Downloads
1
Stars
2
Active Installs
4
Versions
Install in OpenClaw
/install moss
Description
Documentation and capabilities reference for Moss semantic search. Use for understanding Moss APIs, SDKs, and integration patterns.
Usage Guidance
This skill appears to be a docs/reference pack for the Moss API and the requested env vars make sense for that purpose. Before enabling or providing credentials: (1) treat MOSS_PROJECT_KEY as sensitive — only provide it if you trust the skill/agent and understand what calls it will make; (2) review the 'Voice Agent Context Injection' and any workflows that send conversational or audio data to the Moss service to ensure you explicitly consent to that data being uploaded; (3) note there is no homepage/source URL in the package metadata — if you need higher assurance, ask the publisher for an official repo or homepage and verify the service owner before sharing project keys; (4) because it’s instruction-only, there’s no installer risk, but credentials you provide would allow the skill to call the external Moss API, so limit scope and rotate keys if you later disable the skill.
Capability Analysis
Type: OpenClaw Skill
Name: moss
Version: 1.0.3
The skill bundle is a documentation-only resource for the Moss semantic search platform. It provides the agent with API references, SDK usage patterns (JavaScript/Python), and configuration requirements for environment variables (MOSS_PROJECT_ID, MOSS_PROJECT_KEY). No malicious code, data exfiltration, or prompt injection attempts were identified in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
The name and description describe Moss API/SDK documentation. The skill only declares two environment variables (MOSS_PROJECT_ID and MOSS_PROJECT_KEY) that are the expected credentials for interacting with the Moss service; no unrelated binaries, install steps, or unrelated credentials are requested.
Instruction Scope
SKILL.md is an instruction-only doc describing API endpoints, SDK methods, and workflows (create/index/query/addDocs/etc.). It indicates use of project credentials to call Moss endpoints (base URL: https://service.usemoss.dev/v1). The doc references an opt-in 'Voice Agent Context Injection' integration pattern — any workflow that sends user conversations or audio to the service is expected for indexing/context injection but should be explicitly consented to by users. No instructions were found that ask the agent to read unrelated local files or exfiltrate system secrets beyond the declared env vars.
Install Mechanism
No install spec and no code files are present. This is the lowest-risk install model (instruction-only); nothing will be written to disk by an installer.
Credentials
The only declared env vars are MOSS_PROJECT_ID and MOSS_PROJECT_KEY (primary credential). Both are appropriate and proportional for a client that will call the Moss service. The primary credential is marked secret in metadata and should be treated as such.
Persistence & Privilege
The skill is not always-enabled and uses normal autonomous invocation settings. It does not request persistent system-wide configuration or other skills' credentials.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install moss - After installation, invoke the skill by name or use
/moss - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- No user-facing changes in this release.
- Version bump to 1.0.3 with no file modifications.
v1.0.2
- Updated documentation URL from https://docs.usemoss.dev to https://docs.moss.dev
- Clarified REST API base URL and routes (now `POST /v1/manage` at `https://service.usemoss.dev/v1`)
- Expanded and detailed REST API `action` table, including async index build operations
- Specified that hybrid search blending (`alpha` parameter) is available only in the Python SDK
- Improved authentication instructions for REST API with full example
- Made skills, SDK method names, and parameter conventions more precise and aligned with current SDKs
v1.0.1
- Updated SKILL.md to specify primary environment variables, including MOSS_PROJECT_KEY as the primary credential.
- Clearly documented required environment variables with descriptions under metadata.
- Clarified that voice agent context injection is an opt-in integration pattern, not automatic behavior.
v1.0.0
Initial release providing documentation and feature reference for Moss semantic search.
- Details full set of capabilities: index management, document operations, search modes, and embedding models.
- Outlines SDK methods for JavaScript and Python, with example workflows for semantic, hybrid, and offline-first search.
- Describes integration steps, auth requirements, API actions, and package installation instructions.
- Includes best practices for chunking, query parameters, model selection, and common errors.
- Reference for voice agent frameworks and context injection workflows.
Metadata
Frequently Asked Questions
What is Moss?
Documentation and capabilities reference for Moss semantic search. Use for understanding Moss APIs, SDKs, and integration patterns. It is an AI Agent Skill for Claude Code / OpenClaw, with 913 downloads so far.
How do I install Moss?
Run "/install moss" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Moss free?
Yes, Moss is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Moss support?
Moss is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Moss?
It is built and maintained by Keshav Arora (@coderomaster); the current version is v1.0.3.
More Skills