yu-iskw/coding-agent-skills Skills

Executes tasks using the Claude Code CLI (`claude`). Automatically determines the safest permission mode (plan, acceptEdits, or bypassPermissions) based on the task type.

Executes tasks using the Codex CLI (`codex`). Automatically determines the least privilege required (Read-Only, Editor, or Autonomous) based on the user's request and handles security approvals.

Executes tasks using the Cursor Agent CLI (`cursor-agent`). Provides structured modes for planning, Q&A, and full automation with safety guardrails.

Executes tasks using the Gemini CLI (`gemini`). Automatically determines the safest approval mode (plan, auto_edit, or yolo) based on the task type.

Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.

Run make format and make lint, then fix linter violations. Use when formatting code or fixing trunk/lint issues.

Decomposes complex or large-scale requirements into discrete, mutually exclusive sub-tasks that can be executed in parallel by multiple agents. Use when a task is described as an "epic", spans multiple architectural layers, or would benefit from concurrent development to reduce time-to-completion.

Synchronizes the list of Agent Skills in the root README.md with the actual skills present in the codebase.