nixos-config

Hand off the current task to a fresh background agent running in its own workmux worktree, passing a self-contained prompt synthesized from this conversation's context. Use when the user wants to outsource, delegate, or "hand off" implementation work to a separate agent session (e.g. "handoff this fix", "outsource it to a ccd agent", "spin up an agent to do X").

Delegate a code review to pi (`pi /skill:review`) running in a tmux window, then dispatch subagents to fix each finding and check it off the review file. Use when the user wants an automated review-and-fix loop over their current changes.

Teach a topic using the Feynman technique — explain simply, have the user re-explain, identify gaps, re-teach, and loop until they can explain it on their own. Use when the user wants to deeply understand a topic, test their understanding, or mentions "Feynman".

Build a focused 20-hour learning plan for a topic, structured as 10 two-hour sessions following the Pareto principle (20% that drives 80% of results). Use when the user wants to learn a topic fast, build a study plan, or create a structured curriculum.

Create or update a GitHub pull request for the current branch, committing pending changes first. Use when the user wants to open a PR, update an existing PR, or ship a branch for review.

Ask questions about specific GitHub code repositories using DeepWiki. Use when the user asks about a repo's code, architecture, configuration, modules, APIs, examples, or behavior and provides a GitHub repository in owner/repo form or as a GitHub URL.

Create hand-drawn Excalidraw diagrams from JSON using excalidraw-cli. Use when the user wants diagrams, flowcharts, architecture diagrams, visual explanations, or shareable Excalidraw URLs.

Review a pull request, branch diff, or local changes with a proven step-by-step workflow focused on architecture and design fit, refactor opportunities, potential bugs, and missing test coverage. Use when asked to review code, review a PR, look for bugs, suggest refactors, or assess test gaps.

Automate browser interactions for UI testing and debugging — navigate pages, fill forms, take screenshots, upload files, verify elements. Use when the user wants to test or interact with a web app from the CLI.

Execute tasks from a tasks.yaml by orchestrating code-writer agents. Use when the user has a tasks.yaml ready to run or says "run the tasks", "execute tasks.yaml".

Domain-Driven Design + Ports & Adapters (Hexagonal Architecture) implementation guide. Use when the user wants to model a domain, design bounded contexts, implement hexagonal architecture, or review code for DDD compliance.

Diagnose bugs, errors, and unexpected behavior — then suggest a fix. Use when the user describes something broken (errors, crashes, wrong output, "why is X happening"). Produces a structured prose diagnosis; never writes code.

Exa AI search API via CLI. Use when the user wants to search the web, find code examples, extract page content, or get AI answers with sources.

Plan a feature by delegating to the prd-planner subagent to produce a product requirements doc. Use when the user wants to plan, scope, or write a PRD for a new feature.

Rebase the current branch onto a target branch and walk through conflict resolution. Use when the user wants to rebase, sync with main, or resolve rebase conflicts.

Delegate investigation of a topic to a single subagent and report back. Use when the user asks to research, investigate, explore, or deep-dive on any topic.

Break down a PRD into actionable tasks with dependencies, written to tasks.yaml. Use when the user wants to convert a PRD or feature description into trackable tasks.

Manage tmux sessions, windows, and panes non-interactively — list state, read pane output, send keys, create/kill sessions, inspect long-running terminal work. Use when the user mentions tmux or asks about something running in another terminal.

Review and address all open PR comments — fetch, triage, implement changes, resolve, and summarize.