plugins/core/skills/tasklist-conventions/SKILL.md
This skill should be used when working with built-in TaskList tools (TaskCreate, TaskUpdate, TaskList, TaskGet) to track execution progress within and across Claude Code sessions.
npx skillsauth add rbozydar/rbw-claude-code tasklist-conventionsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
TaskList is a built-in Claude Code feature for tracking task execution. Tasks are stored in ~/.claude/tasks/[session-uuid]/ and can be shared across sessions using the import-tasks skill.
Use TaskList when:
Consider file-todos instead when:
Use both when:
| Tool | Purpose |
|------|---------|
| TaskCreate | Create a new task with subject, description, activeForm |
| TaskUpdate | Update status, add dependencies, modify tasks |
| TaskList | View all tasks with status and blockers |
| TaskGet | Get full details of a specific task |
Required: subject (imperative form), description (detailed scope)
Recommended: activeForm (present continuous for spinner display)
Set via TaskUpdate: status (pending/in_progress/completed), addBlockedBy, addBlocks
Use imperative form (like git commits): "Implement user authentication", "Add validation for email field", "Write integration tests"
Use present continuous: Subject "Run database migrations" → ActiveForm "Running database migrations"
pending → in_progress → completed
TaskCreate: "Implement User model" → #1
TaskCreate: "Add authentication service" → #2
TaskUpdate: #2 addBlockedBy [#1]
Create tasks that are completable in a focused session (1-4 hours), specific enough to know when done, independent or with clear dependencies, and verifiable.
while TaskList shows pending tasks:
TaskList # Check available work
TaskUpdate: #X status=in_progress # Claim next unblocked task
# ... implementation ...
TaskUpdate: #X status=completed # Mark complete
---
title: Add user authentication
task_list_id: a69ce44f-1559-4052-89e2-66605323adca
---
Use the import-tasks skill to import tasks from another session's TaskList.
Multiple agents can work on the same TaskList by importing it and claiming individual tasks.
| System | Storage | Purpose | Persistence |
|--------|---------|---------|-------------|
| TaskList (this) | ~/.claude/tasks/ | Execution tracking | Session-scoped |
| file-todos | todos/ in repo | Detailed documentation | Git-committed |
| TodoWrite tool | In-memory | Temporary tracking | None |
Recommended: File-todos for detailed findings, TaskList for execution tracking. Link them via description references.
development
This skill should be loaded when writing, reviewing, or refactoring Python code to apply strict coding standards directly in the current context without spawning a subagent. It provides comprehensive Python development standards covering SOLID principles, asyncio patterns, type hints, testing, and production-quality code.
tools
This skill should be used when invoking the Gemini CLI for code review, plan review, or any prompt-based task. It provides correct invocation patterns emphasizing stdin piping and @ syntax over shell variable gymnastics.
development
Use this skill when writing, reviewing, or debugging Quickshell configurations (QML files for desktop shell UI on Wayland/Hyprland). Triggers on: QML files with Quickshell imports, shell.qml entry points, PanelWindow or FloatingWindow usage, Quickshell service integration (PipeWire, MPRIS, notifications, Hyprland IPC), Wayland layer-shell or session-lock code, custom bar/panel/widget/dock/OSD/lockscreen/launcher development, or any question about building a desktop shell with Quickshell on Hyprland.
development
This skill should be used when thorough, multi-perspective research with citations is needed. It performs comprehensive research using a diffusion research loop with domain specialization, supporting general web research and specialized domains (geopolitical with GDELT). Auto-detects domain from query or accepts an explicit --domain flag.