This skill should be used when the user mentions "dots", "dot", "tasks", "task", "todo", "issue", "track", "plan", "breakdown", or asks about task management. Provides guidance for using the dots CLI task tracker.
/plugin marketplace add alexeldeib/clode/plugin install clode@clodeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Manages tasks using dots - a fast, minimal CLI task tracker that stores tasks as plain markdown files with YAML frontmatter in .dots/. Zero dependencies, git-friendly, perfect for AI agent workflows.
| Command | Purpose | Example |
|---|---|---|
dot init | Initialize .dots/ directory | dot init |
dot add "title" | Create new task | dot add "Fix login bug" |
dot ls | List open/active tasks | dot ls |
dot on <id> | Mark task as active | dot on a1b2c3d |
dot off <id> | Complete and archive task | dot off a1b2c3d |
dot ready | Show unblocked tasks | dot ready |
dot tree | Show task hierarchy | dot tree |
dot show <id> | Display task details | dot show a1b2c3d |
dot find "query" | Search tasks | dot find "auth" |
dot rm <id> | Delete task permanently | dot rm a1b2c3d |
# Basic task
dot add "Fix the login bug"
# With priority (0=critical, 1=high, 2=normal, 3=low, 4=backlog)
dot add "Critical security fix" -p 0
# With description
dot add "Refactor auth" -d "Move JWT validation to middleware"
# As child of parent task
dot add "Write unit tests" -P parent-task-id
# Blocked by another task (dependency)
dot add "Deploy to prod" -a blocking-task-id
# Quick add (shorthand)
dot "Quick task title"
open -> active -> done (archived)
.dots/archive/IDs use format: {prefix}-{slug}-{hex} (e.g., dots-fix-user-auth-a3f2b1c8)
Commands accept short prefixes:
dot on a3f2b1 # Matches dots-fix-user-auth-a3f2b1c8
dot show a3f # Error if ambiguous
# Create parent task
dot add "Implement user authentication" -p 1
# Output: dots-impl-user-auth-a1b2c3d4
# Add subtasks
dot add "Design database schema" -P a1b2c3d4
dot add "Create API endpoints" -P a1b2c3d4 -a schema-task-id
dot add "Build login UI" -P a1b2c3d4 -a api-task-id
dot add "Write integration tests" -P a1b2c3d4 -a ui-task-id
# View hierarchy
dot tree
# Start of day: see what's ready
dot ready
# Pick a task and start working
dot on a1b2c3d
# Check active tasks
dot ls --status active
# Complete task with reason
dot off a1b2c3d -r "Fixed in commit abc123"
# Add dependency after creation
dot update <task-id> -a <blocking-task-id>
# View task to see what's blocking it
dot show <task-id>
dots has built-in hooks for seamless Claude Code integration.
Add to ~/.claude/settings.json:
{
"hooks": {
"SessionStart": [
{
"hooks": [{"type": "command", "command": "dot hook session"}]
}
],
"PostToolUse": [
{
"matcher": "TodoWrite",
"hooks": [{"type": "command", "command": "dot hook sync"}]
}
]
}
}
.dots/todo-mapping.jsonTasks stored as markdown with YAML frontmatter:
.dots/
task-id.md # Root task
parent-id/ # Parent with children
parent-id.md # Parent task
child-id.md # Child task
archive/ # Completed tasks
config # Project prefix
todo-mapping.json # TodoWrite sync state
---
title: Fix the bug
status: open
priority: 2
issue-type: task
created-at: 2024-12-24T10:30:00Z
blocks:
- other-task-id
---
Description as markdown body here.
dot slugify to add readable slugs to existing IDsdot ls --status donedot purge to permanently delete all archived tasks.dots/ to track project historyThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.