Skill UI

OpenViking Code Repository Search exposes `ov` terminal commands for scoped semantic, keyword, and glob searches across viking:// resources, lets you read directory summaries/files, and manage indexed repositories (add/remove) with documented error handling.

Recall and persist long-term semantic memory via OpenViking MCP tools. Use at task start to retrieve relevant prior knowledge, and during/after work to store durable facts, preferences, decisions, and lessons. Ideal for coding, configuration, debugging, multi-step tasks, and tool-based workflows. Not for casual chat or simple trivia.

This skill allows agents to ingest external resources (local files, URLs, repositories) using `ov add-resource`, and to create long-lasting searchable memories from conversations using `ov add-memory`. It is essential for building a comprehensive, persistent knowledge base for the OpenViking context database, ensuring that learned insights and external data remain available across sessions and interactions. Use when external knowledge injection or context persistence is required.

Use the OpenViking CLI to search memories, skills, and resources with semantic and literal queries across directories, surfacing context-aware results whenever agents need stored knowledge or documentation.

A comprehensive guide for deploying, configuring, and maintaining the OpenViking server in production environments. It covers service configuration management, environment setup using `uv` for virtual environments, reliable startup procedures using `nohup`, graceful shutdown methods, and critical data cleanup workflows. This resource is essential for DevOps engineers and system administrators managing OpenViking services.

A comprehensive skill designed to guide users through the installation and configuration of the OpenViking long-term memory plugin for OpenClaw. It enables the agent to automatically capture facts from conversations and recall relevant context across sessions (auto-capture + auto-recall). The process is fully natural-language driven, requiring no command-line knowledge from the user.

A dedicated skill for performing manual data synchronization and knowledge recall with OpenViking. It allows users to explicitly trigger chat transcript syncing from OpenClaw sessions and perform targeted memory searches via command line, without disrupting normal conversation flow or occupying the standard context engine slot.

This skill facilitates the loading and application of relevant historical experience memories (OpenViking memories) before executing task actions. It guides the user through a rigorous process: querying memories, applying strict applicability and exclusion checks (gating), and prioritizing real-time facts over loaded guidance. Essential for complex, multi-intent conversational flows.

This operator skill provides comprehensive control over the OpenViking context engine, enabling agents to manage long-term memory, session archives, and external resources within OpenClaw. It facilitates semantic recall, context querying, resource import, and recall trace debugging by communicating with a remote OpenViking server. Use this plugin when your agent requires advanced, persistent context management.

Converts a research paper or PDF into an ARA-structured artifact, validates it, and ingests into OpenViking as a resource. Handles claims, evidence, figures, tables, and full document parsing from PDFs or URLs.

Retrieve and apply prior task Experience through OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, config changes, deployment, and failure recovery. Enhances reliability by advisory guidance while keeping the current request and environment authoritative. Scoped to the current user's Experience root, searches and reads canonical URIs, and applies relevant steps conservatively.

Search and read documents, repositories, URLs, and notes stored in OpenViking. Guides tool choice among find, grep, glob, and list, and drilling from directory summaries to exact files for efficient reference retrieval.