Agent skill · software engineering · samhvw8
claude-extensibility
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation.
Why this skill is useful
Adds executable YAML templates and CLI commands for creating and managing agents and skills, which are not commonly found in public documentation.
What it needs
Requires claude installed locally. About 5k tokens when loaded. Last updated 2025-12-09. 10 stars on the source repository.
What this skill does
Claude Code Extensibility CRUD operations for agents, skills, and output styles following Anthropic best practices. Related Skills IMPORTANT: When creating or editing prompts, use prompt-enhancer skill to improve quality. Core Principles Simplicity: Direct tool calls, avoid complex abstractions Focus: Single, clear responsibility per extension Conciseness: Target <500 lines, use progressive disclosure Efficiency: Optimize for token usage and response time Extension Types Type Invocation Purpose Location ------ ------------ --------- ---------- Agents Task tool Specialized sub-processes .claude/agents/ Skills Model-invoked (autonomous) Domain knowledge .claude/skills/{name}/ Output Styles /output-style command Modify main agent behavior .claude/output-styles/ Agent Development Reference: references/agent-development.md - Full YAML structure, model/tool selection, system prompt patterns, optimization techniques. Quick Start: Agent YAML Fields Field Required Description ------- ---------- ------------- name Yes Lowercase, hyphens (e.g., code-reviewer) description Yes Single line with \n for newlines, include examples tools No Comma-separated; inherits all if omitted model No haiku, sonnet, opus, inherit (default: sonnet) permissionMode No default, acceptEdits, bypassPermissions, plan, ignore skills No Comma-separated skill names to auto-load Model Selection Model Use When Target Time ------- ---------- ------------- haiku Fast tasks, exploration, search < 3s sonnet Balanced, most use cases < 10s opus Complex reasoning, architecture < 30s inherit Match main conversation model varies Built-in Subagents Agent Model Tools Purpose ------- ------- ------- --------- general-purpose Sonnet All Complex research, multi-step operations plan Sonnet Read, Glob, Grep, Bash Research in plan mode Explore Haiku Read-only Fast codebase search (quick/medium/very thorough) Agent Locations Location Scope Priority ---------- ------- ---------- .claude/agents/ Project Highest ~/.claude/agent …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills samhvw8/claude-extensibility