This skill should be used when the user asks to "work with beads tasks", "create a beads ticket", "update beads status", "read task comments", "manage dependencies", "sync beads", "use bd commands", or needs guidance on beads task management workflows. Provides comprehensive beads CLI usage and workflow patterns.
/plugin marketplace add ivankristianto/k2-dev/plugin install k2-dev@k2-dev-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Beads is a git-backed issue tracker for multi-session work with dependencies and persistent memory. All tasks stored in .beads/ directory as markdown files, committed to git, surviving conversation compaction.
Key Capabilities: Task creation/management, status transitions, comments, dependencies, git worktree integration, synchronization.
Reference: See k2-dev-reference.md#beads-cli-commands for complete command syntax.
.beads/ as markdownbd show beads-123 # Task details
bd comments beads-123 # All comments for context
bd dep list beads-123 # Check dependencies
Parse output for:
# Epic
bd create "User Authentication System" -d "Epic description" -p P1
# Stories under epic
bd create "JWT Token Implementation" -d "Story" -p P1 --parent=beads-{epic}
# Subtasks
bd create "Auth middleware" -d "Subtask" -p P2 --parent=beads-{story}
# Dependencies (B blocks on A - A must complete before B)
bd dep add beads-{B} --blocks-on=beads-{A}
bd comments beads-123 add "Implementation Plan:
1. Create middleware in src/auth/
2. Use existing JWT library
3. Follow patterns in AGENTS.md
4. Add tests in tests/auth/"
Proper workflow:
# Technical Lead assigns to Engineer
bd update beads-123 --status in_progress --assignee engineer
# After implementation
bd update beads-123 --status closed
# If blocked
bd update beads-123 --status blocked
bd comments beads-123 add "Blocked by: beads-120 needs merge first"
When review identifies issues beyond 2 iterations:
# Critical issues
bd create "Fix authentication bypass vulnerability" \
-d "Critical security issue from PR #456 review. Details: [...]" \
-p P0
# Link to original
bd comments beads-789 add "Follow-up ticket created: beads-790 (P0)"
bd comments beads-790 add "Follow-up from: beads-789"
Good:
Implement JWT authentication middleware
Acceptance Criteria:
- Validates JWT tokens on protected routes
- Returns 401 for invalid/expired tokens
- Follows patterns in src/auth/oauth.ts
- Test coverage >80%
Related: beads-120 (API refactor)
Bad:
Add auth stuff
Use comments for:
Set dependencies to:
Always sync after:
bd sync
Epic (1-2 weeks): bd create "User Management System" -d "Complete user CRUD with roles" -p P1
Story (2-5 days): bd create "User Profile Editing" -d "Users can edit profile" -p P1 --parent=beads-{epic}
Subtask (0.5-2 days): bd create "Profile API endpoint" -d "Create PUT /api/users/:id" -p P2 --parent=beads-{story}
Link with dependencies to show hierarchy.
Task Not Found:
bd sync # Sync first
bd list # List all
bd search "keyword" # Search
Status Not Updating:
Dependency Cycles:
# Check before adding to avoid cycles
bd dep list beads-123
bd dep list beads-456
bd worktree create beads-123 # Creates ../beads-123/, branch feature/beads-123
bd worktree list # List worktrees
bd worktree remove beads-123 # Remove worktree
Reference: See git-worktree-workflow skill for detailed patterns.
Technical Lead:
Engineer:
Planner:
Reviewer:
Tester:
Reference: See k2-dev-reference.md for complete command syntax, priority levels, and task granularity guidelines.
This 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.