Agent skill
backlog-workflow
Expert knowledge for working with Backlog.md task management. Use when managing tasks, organizing epics, handling dependencies, or tracking project progress. Automatically applies Backlog.md best practices.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/backlog-workflow
SKILL.md
Backlog.md Workflow Skill
Expert guidance for managing projects with Backlog.md - a markdown-native task manager with MCP support.
Core Concepts
Tasks
- Stored as markdown files in
backlog/tasks/ - Named pattern:
task-<id> - <title>.md - Support: status, priority, labels, assignees, acceptance criteria, notes, plans, dependencies
Epics (Parent-Child)
- Parent tasks group related work
- Create subtasks with
-p <parent-id> - Track epic progress via subtask completion
Dependencies
- Tasks can depend on other tasks
- Prevents starting blocked work
- Creates execution sequences
- Validated for circular references
Statuses
- "To Do": Not started
- "In Progress": Currently being worked on
- "Done": Completed
Command Reference
Task Operations
backlog task create "Title" [options]
backlog task edit <id> [options]
backlog task <id> # View task
backlog task list [filters] # List tasks
backlog task archive <id> # Archive completed task
Common Options
--desc, -d Description
--status, -s Task status
--priority high/medium/low
--labels, -l Comma-separated labels
--assignee, -a @username
--ac Acceptance criteria (repeatable)
--dep Dependencies (task-1,task-2)
--plan Implementation plan
--notes Implementation notes
--append-notes Add to existing notes
-p Parent task ID (for subtasks)
Board & Search
backlog board # Interactive Kanban board
backlog board export # Export to markdown
backlog search "query" # Fuzzy search tasks
backlog overview # Project statistics
Acceptance Criteria
--ac "Criterion" # Add criterion
--check-ac 1 # Mark #1 complete
--uncheck-ac 2 # Mark #2 incomplete
--remove-ac 3 # Remove criterion
Workflow Patterns
Starting New Work
- Search for existing tasks:
backlog search "<keywords>" - If exists, update status to "In Progress"
- If new, create task with full context
- Set dependencies if applicable
During Work
- Add implementation notes as you learn
- Check acceptance criteria as completed
- Update status appropriately
- Create subtasks for discovered work
Completing Work
- Verify all acceptance criteria are checked
- Add final implementation notes
- Move to "Done" status
- Archive if no longer needed
Epic Planning
- Create parent task with epic overview
- Break into 5-10 focused subtasks
- Establish dependencies between subtasks
- Track progress via subtask completion
Multi-line Input (Bash/Zsh)
Use ANSI-C quoting for newlines:
backlog task edit <id> --notes $'Line 1\nLine 2\n\nParagraph 2'
MCP Integration
When MCP is available, use backlog tools directly:
backlog.task_create- Create tasksbacklog.task_update- Update tasksbacklog.task_list- List tasksbacklog.acceptance_criteria_check- Check criteriabacklog.implementation_notes_append- Add notesbacklog.dependencies_add- Add dependencies
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?