Mode Switch
Switch between plan and bypass modes. Use when changing Claude's execution mode.
109 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
offline-ai-toolkit
Build offline-capable AI systems with local models, embedded knowledge bases, and no internet dependency. Use when: building AI tools for offline use, creating self-contained knowledge systems, deploying AI in air-gapped environments.
109 repo starsObserved in 1 repos
Agent Building
oh-my-claudecode
Orchestrate multi-agent Claude Code teams — assign roles, coordinate parallel tasks, share context between agents, and manage team workflows. Use when: running multiple Claude Code agents simultaneously, building team-based AI development workflows, coordinating complex multi-agent coding projects.
109 repo starsObserved in 1 repos
Agent Building
onyx-ai
Deploy and configure Onyx, a self-hosted AI chat platform with RAG and 25+ data connectors. Use when: setting up private ChatGPT alternative, connecting AI to company documents, building enterprise AI assistant with Confluence/Slack/Drive access.
109 repo starsObserved in 1 repos
Agent Building
open-swe
Build asynchronous coding agents using LangChain's Open SWE framework — agents that plan, code, test, and iterate on software engineering tasks. Use when: building coding bots, automating issue resolution, creating SWE agents that work on repos asynchronously.
109 repo starsObserved in 1 repos
Agent Building
openviking
Manage AI agent context (memory, resources, skills) using OpenViking's file system paradigm. Use when: building agents with persistent context, managing agent memories across sessions, implementing hierarchical context delivery for complex agent systems.
109 repo starsObserved in 1 repos
Agent Building
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent workflow, or describe a use case that maps to an Orloj topology (pipeline, hierarchical, swarm-loop). Even if they just say something like "I want agents that do X then Y then Z" — that's a pipeline, and this skill should activate. Covers generating all Orloj resource types: Agent, AgentSystem, Task, ModelEndpoint, Secret, Tool, McpServer, Memory, AgentPolicy, AgentRole, ToolPermission, TaskSchedule, and TaskWebhook manifests.
109 repo starsObserved in 1 repos
Agent Building
payload-results-yaml
State management for agentic payload triage actions — you must use this skill whenever reading or writing the payload results YAML file
109 repo starsObserved in 1 repos
Agent Building
prose-architect
Architect PROSE-compliant agent primitives for AI-native development. Use when (1) Building AI-native apps from requirements ("I want an app that...") (2) Making legacy projects AI-native (3) Designing agent workflows (4) Auditing existing primitives for reliability issues. PROSE = Progressive Disclosure, Reduced Scope, Orchestrated Composition, Safety Boundaries, Explicit Hierarchy
109 repo starsObserved in 1 repos
Agent Building
pumasi
Codex-native parallel build orchestration. Use when the user explicitly wants to delegate a greenfield or large multi-module implementation into parallel Codex worker sessions, while the host agent stays in the PM/architect role. Best for 3 or more independent modules with clear gates and interfaces. Korean triggers — "품앗이로 만들어줘", "품앗이 켜줘", "병렬로 외주". English triggers — "pumasi", "parallel codex workers", "delegate to codex".
109 repo starsObserved in 1 repos
Agent Building