From sundial-org-awesome-openclaw-skills-4
Discovers and lazy-loads Claude Code agents using search_agents and get_agent Python scripts, cutting context usage by 95%. Use for agent queries, specialized tasks, or complex workflows.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin sundial-org-awesome-openclaw-skills-4This skill uses the workspace's default tool permissions.
Lazy-loading system for Claude Code agents. Eliminates the "~16k tokens" warning by loading agents on-demand.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Lazy-loading system for Claude Code agents. Eliminates the "~16k tokens" warning by loading agents on-demand.
NEVER assume agents are pre-loaded. Always use this registry to discover and load agents.
User Request → search_agents(intent) → select best match → get_agent(name) → execute with agent
| Command | When to Use | Example |
|---|---|---|
list_agents.py | User asks "what agents do I have" or needs overview | python scripts/list_agents.py |
search_agents.py | Find agents matching user intent (ALWAYS do this first) | python scripts/search_agents.py "code review security" |
search_agents_paged.py | Paged search for large registries (300+ agents) | python scripts/search_agents_paged.py "query" --page 1 --page-size 10 |
get_agent.py | Load a specific agent's full instructions | python scripts/get_agent.py code-reviewer |
python scripts/search_agents.py "<keywords>"python scripts/get_agent.py <agent-name>User: "Can you review my authentication code for security issues?"
# Step 1: Search for relevant agents
python scripts/search_agents.py "code review security authentication"
# Output:
# Found 2 matching agents:
# 1. security-auditor (score: 0.89) - Analyzes code for security vulnerabilities
# 2. code-reviewer (score: 0.71) - General code review and best practices
# Step 2: Load the best match
python scripts/get_agent.py security-auditor
# Step 3: Follow loaded agent instructions for the task
Quick Install (Recommended):
# NPX with add-skill (recommended)
npx add-skill MaTriXy/Agent-Registry
# OR npm directly
npm install -g @claude-code/agent-registry
Traditional Install:
# User-level installation
./install.sh
# OR project-level installation
./install.sh --project
What install.sh does:
~/.claude/skills/agent-registry/questionary Python package (for interactive UI)pip3 not availableNote: All installation methods support Python-based migration and CLI tools
Run the interactive migration script:
cd ~/.claude/skills/agent-registry
python scripts/init_registry.py
Interactive selection modes:
With questionary (recommended): Checkbox UI with category grouping, token indicators, and paging
Without questionary (fallback): Text-based number input
1,3,5)all to migrate everythingWhat init_registry.py does:
~/.claude/agents/ and .claude/agents/ for agent filesregistry.json)The installer automatically installs questionary. If installation fails or pip3 is unavailable, the migration script falls back to text-based input mode.
Manual installation:
pip3 install questionary
~/.claude/skills/agent-registry/.claude/skills/agent-registry/ (optional override)Agents not migrated remain in their original locations and load normally (contributing to token overhead).