Claude Skills by sefaertunc

Agent Routing Guide — when to spawn each installed agent

CLI-specific conventions: npm registry interaction, filesystem operations, JSON handling, settings merge, and configuration patterns for worclaude

How Claude writes rules for itself, when to update CLAUDE.md, keeping it lean and effective

Core behavioral principles: when to ask, when to push back, when to simplify, how to make surgical changes

Context budget awareness, when to compact, when to clear, subagent offloading

Multi-agent orchestration patterns: when to use coordinator mode, worker prompts, parallel execution

Terminal UI patterns: display.js visual system, Chalk styling, Ora spinners, Inquirer prompts, and CLI output conventions for worclaude

Branch naming, commit message format, PR workflow, worktree conventions, versioning policy

Five-layer memory architecture: where each fact lives, how layers interact, when to promote learnings

How to structure implementation plans as files, progressive implementation, plan review process

Architectural patterns, naming conventions, file organization, and error handling for the worclaude CLI project

Effective prompting patterns for working with Claude, demanding quality, writing specs

Session ending protocol, HANDOFF document format, seamless continuation between sessions

OWASP-based security checklist any agent can reference when reviewing or writing code

When to use subagents, how many, context hygiene, worktree isolation patterns

Test philosophy, coverage strategy, test-first patterns, what to test and what not to

Domain-specific verification beyond tests, closing the feedback loop for web, API, CLI, data