“coding”

ALWAYS activate for programming-language work and code-adjacent project work: implementation, refactoring, debugging, code review, tests, CI fixes…

The user's coding and docs conventions and taste.

Apply Appie coding standards for minimal, readable, maintainable code changes, testing, reviews, and implementation quality.

Behavioral guidelines to reduce common LLM coding mistakes.

Provides cross-language coding conventions.

Use when changing source code or its tests, such as fixing a bug, adding or changing behavior, refactoring, improving performance, or prototyping a design…

Implement, refactor, and fix code with minimal testable changes and deterministic verification.

Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.

Canonical Arkira coding guidance for planning, implementation, and review of a bounded repository outcome.

Use when implementing or changing code to resolve an incident.

Best practices for writing and modifying code

List, read, create and edit UTF-8 text files in a host-selected workspace.

Coding conventions for writing scripts inside the sandbox.

Software development, code review, debugging, architecture, and technical implementation

Reference the upstream Micronaut project-template maintainer skill for Java implementation, API evolution, and committer-grade verification work.

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell.

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives…

AI-powered development for GTM — vibe coding workflows using v0, Cursor, Claude Code, Lovable, Bolt.new, Replit Agent, and Tempo Labs for rapidly building…

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox…

Coaching-oriented coding tutoring for capability growth through attempt-first implementation, concept explanation, guided debugging, code review, deliberate…

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.