
from claude-skill-registry361
Guidelines for creating and running Claude Code CLI agents: agent JSON format, storage conventions, and execution commands.
This skill documents how to author, store, and run Claude Code CLI agents. It provides concrete instructions for formatting agent definitions as JSON, recommended storage locations (.claude/agents/agents.json and per-agent .md files), and the exact claude CLI commands to run agents in single-shot or interactive modes. The skill also prescribes migration rules when converting from other formats and a required completion report template.
Use this skill when a user asks how to create or execute custom Claude Code agents via the CLI, when they request the correct JSON structure for --agents, or when they need guidance migrating agent definitions from other formats (OpenCode, etc.). It's aimed at users working with Claude CLI and customizing agent deployments.
Primarily designed for Claude Code CLI usage; applicable to environments that accept JSON-based agent definitions and CLI-driven agent execution.
A documentation-only skill for creating and running Claude CLI agents using the --agents JSON format and --agent flag. Written primarily in Korean, which limits accessibility for global users. No scripts or executable code to test — purely instructional content covering agent definition format, storage conventions, and execution commands. Includes migration guidance from OpenCode format.
Clean from a security perspective — no executable code. The Korean-language content is a notable accessibility concern for a directory skill. The migration section (OpenCode to Claude format) is a nice touch but niche.
Uloop: Execute Dynamic Code
Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing
Bookmarklet Creation
Generates browser-executable JavaScript bookmarklets with strict formatting (IIFE wrapper, block comments) and provides ready-to-install links or installer inst
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Bexio API (Swiss CRM & Invoicing)
Integrate and manage Bexio contacts, quotes, invoices, orders and products via the Bexio API. Useful for CRM and Swiss business document workflows.
Content Research Writer
A writing-partner skill that helps research, outline, draft, cite, and iteratively improve articles, tutorials, and thought pieces.
Agent Hierarchy Diagram
Generate visual hierarchy diagrams (ASCII, Mermaid, GraphML) that show agent roles, levels, and delegation for documentation and onboarding.
Review Pull Request
Automated, structured PR reviewer: gathers metadata, diffs, CI results, dependency changes and provides a concise verdict with testing and documentation recomme
Agent Ops — Testing Workflow
Guidance for designing, running, and analyzing test suites for agents: test isolation, execution patterns, and coverage-based enforcement.
libagent
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a
Raindrop.io API
Manage Raindrop.io bookmarks, collections, tags and highlights via the Raindrop REST API with helper scripts and examples.