Proactive workflow for projects using beads issue tracker. ACTIVATE AUTOMATICALLY when session starts in directory with .beads/. Use when: starting work session, selecting tasks, completing tasks, creating subtasks. Triggers: "какие задачи", "что делать", "готово", "done", "следующая задача", "создай задачу", "tasks", "next task", "pick task", "обнови задачи", "refresh", "sync".
/plugin marketplace add timequity/vibe-coder/plugin install vibe-coder@vibe-coderThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/issue-template.mdreferences/session-lifecycle.mdreferences/task-operations.mdProactive task management for projects using beads issue tracker.
When starting a session in a project directory:
ls -d .beads 2>/dev/null
If .beads/ does not exist — this skill is not applicable.
YOU MUST ALWAYS CHECK AND OFFER TO CREATE CLAUDE.md:
# Check if CLAUDE.md exists and has Beads Workflow section
if [ -f CLAUDE.md ]; then
grep -q "## Beads Workflow" CLAUDE.md && echo "configured" || echo "needs_section"
else
echo "no_claude_md"
fi
If "no_claude_md" or "needs_section":
CLAUDE.md content to add:
# CLAUDE.md
## Beads Workflow
При старте сессии используй скилл `beads-workflow` для:
1. Показать текущую задачу (in_progress) или выбрать из ready
2. Отслеживать прогресс через TodoWrite
3. При завершении — закрыть задачу через bd close
## Project Info
<!-- Add project-specific instructions here -->
bd list --status in_progress --json
bd ready --json
If task in_progress exists:
"Продолжаем работу над [id] [title]" Show task details with
bd show <id>
If no in_progress: Use AskUserQuestion with ready tasks as options (max 4, sorted by priority).
bd update <id> --status in_progress
bd show <id>
Use TodoWrite to break down the task into subtasks.
bd create "Subtask title" -t task -p 1
bd dep add <new-id> <parent-id> --type parent-child
When user says "готово", "done", "сделал", "закрой задачу":
Confirm which task (if ambiguous)
Ask for brief reason via AskUserQuestion:
Close and sync:
bd close <id> --reason "<reason>"
bd sync
Offer next task from ready list
When user says "создай задачу", "новая задача", "create task":
Task description must include:
skill:<name># With skill recommendation
bd create "Implement user auth API" -t task -p 1 -l "skill:backend-rust"
# Without skill (general task)
bd create "Write documentation" -t task -p 2
Priority: 0=critical, 1=high, 2=medium, 3=low
For subtasks, link to parent:
bd dep add <child-id> <parent-id> --type parent-child
Every issue must be readable without external context. A future session (or different developer) should understand the task completely from the description alone.
Use the template from references/issue-template.md:
## Summary
[What and why — 1-2 sentences]
## Files to Modify
- `path/to/file.ts:123` — what changes
## Implementation Steps
1. Specific step with details
2. Next step
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Tests pass
Before creating, ask yourself:
# Edit main description
bd edit <id> --description
# Add technical design notes
bd edit <id> --design
# Add gotchas and warnings
bd edit <id> --notes
Run before committing:
python3 skills/beads-validation/scripts/validate_beads.py --check-quality
See references/issue-template.md for full template and examples.
When user says "обнови задачи", "refresh", "sync":
bd sync
bd ready --json
Show what changed:
If current in_progress task was modified, warn user.
Before showing ready list for next task selection, ALWAYS sync first:
bd sync
bd ready --json
This ensures task list is current before user picks.
If task is still in_progress when session ends:
bd sync to save stateThis 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 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 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.