claude-agent-sdk-agent-creation
Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
25,184 results
Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns.
This skill should be used when the user asks to "use the Harness MCP", "connect Harness to Jira", "manage Harness pipelines/repos/PRs from AI", or "sync Jira…
Work with self-hosted Nabu knowledge spaces through native remote MCP first, including owner-agent connection links, bearer authentication, shared-space…
Use when implementing features or fixes - test-driven development with RED-GREEN-REFACTOR cycle and full code coverage requirement
Review and record one pending human checkpoint in a research Workspace; use when a HUMAN Unit is blocked on an `Approve C*` decision, and never treat silence…
Saturate loop kind taxonomy: six typed loop kinds, per-kind specs, turn results, terminal states. OMH v18 skill→kind mapping.
Used when maintaining and releasing the rock-marketplace plugin repository. When the user wants to add a skill, delete a skill, update skill content, modify the plugin's metadata (plugin.json/registry.json/marketplace.json), adjust the README, give the plugin…
Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.
Standardized tool set definitions for Claude Code agents ensuring consistent tool access across similar agent types
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires…
Optimize agent skills for discoverability on ClawdHub/MoltHub. Use when improving search ranking, writing descriptions for semantic search, understanding how…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Run Claude Code as a headless worker — delegate, monitor, or resume Claude runs and named subagents, including background agents and a choice between CLI and…
Thinking partner for a half-formed idea: explore the problem, compare approaches, and decide whether it needs an intent at all. Use when the user says…
Use when Antigravity MCP is available locally and you want to query workspaces, check quota, run lightweight Antigravity asks, or generate images through the…
Keep a multi-agent panel across harnesses, or read-only consultants, available in the current chat, consulting them when independent input is worth the cost…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
Self-improving AI memory system that persists learnings across sessions in CLAUDE.md. Use when capturing corrections, remembering user preferences, or…
Delegate a task to another AI agent in a separate cmux pane or workspace. Supports Claude Code, Codex, Gemini CLI, and custom agents. Handles agent launch,…
Get a second opinion on code or specifications from a different AI agent via cmux. Default reviewer: Codex (or Claude Code if parent is Codex). Supports custom…
Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding…
Wallet MCP — gives your AI assistant access to a Coinbase Wallet Account via the Wallet MCP server (wallet-mcp.coinbase.com). Wallet, portfolio, sending,…
Fine-tune small open-weight LLMs locally with Unsloth + QLoRA for text tasks (classification, extraction, translation). Use when input is raw text (not tabular…
Creates and improves Claude Code Skills (SKILL.md files). Covers frontmatter, descriptions, progressive disclosure, bundled resources, and content…