RohiRIK

Generate a production-ready TypeScript CLI for autonomous agents (JSON contract, non-interactive, semantic exits). USE WHEN create an agent CLI, tool for LLM/automation, or wrap an API for agents. NOT FOR human-first interactive CLIs (use CreateCLI-Human),…

Generate a production-ready TypeScript CLI for human operators (TTY UX, prose help, optional JSON). USE WHEN create a CLI for people, interactive command-line tool, or wrap an API for humans. NOT FOR agent-first CLIs (use CreateCLI-Agent), agent skills (use…

Phased playbook to build or port a native SwiftUI macOS menu bar app. USE WHEN starting or porting a macOS menu bar plugin. NOT FOR one view's styling (use MacUX).

Delegate a coding, refactor, PR-review, or image task to the Antigravity CLI (agy) as an autonomous worker. USE WHEN delegating such a task to agy/Antigravity, or running the agy CLI.

Bounded multi-pass loop: improve mode (one change per pass, Verify + Reflect, inline or wake-driven) or analysis mode (--lenses, read-only). USE WHEN iterate, refine, keep improving, or explore deeper.

Delegate a coding, refactor, or PR-review task to the OpenCode CLI as an autonomous worker. USE WHEN delegating such a task to OpenCode, or running the opencode CLI.

Decompose a spec into a dependency DAG, build units in parallel via delegation, review each in a separate context. USE WHEN orchestrating multi-unit or parallel work, or landing a spec.

Delegate a coding, refactor, or PR-review task to the Pi (pi.dev) CLI as an autonomous worker. USE WHEN delegating such a task to Pi, or running the pi CLI.

Reference for retrieved patterns and lessons from past sessions; use when prior fixes, gotchas, decisions, or earlier sessions may apply, or when asked what we learned before.

USE WHEN separating trusted instructions from untrusted content or tool output.

USE WHEN hardening command execution, path handling, or installer boundaries.

USE WHEN handling credentials, env vars, logs, tests, or docs safely.

Reference for LTM memory commands, context hooks, and DB schema; use when the user mentions learning, recalling, forgetting, relating, or capturing memory, or when a session starts or the project changes.

Mines LTM memories from past git commits. Use when onboarding a repo into LTM, backfilling history after enabling gitLearn, or harvesting patterns after a sprint.

The LTM memory-tool contract — names, ritual, categories, phase map. USE WHEN recalling, learning, relating, or restoring memory.

Start, stop, or check the LTM graph visualization server; use when the user asks to open, launch, stop, kill, or check graph-server status.

Enforce universal coding standards and best practices.

Optimize content for SEO, engagement, and conversion across multiple platforms. Analyzes content structure, readability, keyword density, and provides actionable recommendations for blog posts, landing pages, social media, and marketing materials.

Standards, patterns, and workflows for modern frontend development (React, Next.js, Performance). USE WHEN designing components, optimizing UI, or implementing state management.

Resume structure, achievement bullet formulas, ATS optimization, and job-targeted tailoring for software engineers. Use when reviewing resumes, crafting achievement bullets, extracting keywords from job descriptions, or tailoring content for specific roles.

Use when something is wrong with a cod workspace from the HOST - the container will not start, the system looks stuck, or you need to read state, logs and results without going inside. Runbook only; safe to read, destructive steps are marked.

Use when changing, extending, or debugging the cod CLI - onboarding, the shared container, cron scheduling, security controls, or what happens on a crash. Explains how the system actually works and why each boundary is where it is. NOT a runtime tool: this is…

This skill should be used when the user asks to "create a new dev-team agent", "scaffold a subagent", "port a Gemini/Cursor/Cline agent", "canonicalize an agent", or "validate the agents folder". Owns the full lifecycle — generate, research, validate, and…