Review, proofread, and refine filed Beads epics and issues
/plugin marketplace add ReinaMacCredy/my-workflow/plugin install reinamaccredy-my-workflow@ReinaMacCredy/my-workflowThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You are tasked with thoroughly reviewing, proofreading, and polishing the filed Beads epics and issues to ensure workers have a smooth implementation experience.
First, get the current state:
bd list --json
bd ready --json
If specific IDs were provided ($ARGUMENTS), focus on those. Otherwise, review all issues.
For EACH issue, verify:
Watch for and correct:
Use bd update to fix issues:
bd update <id> --title "Improved title" --json
bd update <id> --priority <new-priority> --json
bd update <id> --description "New description" --json
bd update <id> --acceptance "Acceptance criteria" --json
Manage dependencies separately with bd dep:
bd dep add <issue-id> <dependency-id> --json # Add dependency
bd dep remove <issue-id> <dependency-id> --json # Remove dependency
bd dep tree <issue-id> --json # View dependency tree
bd dep cycles --json # Check for circular deps
For major rewrites, close and recreate:
bd close <id> --reason "Replaced by <new-id>" --json
bd create "Better title" -t <type> -p <priority> --deps <dep-id> --json
After refinements, validate:
bd list --json # View all issues
bd list --status open --json # View only open issues
bd ready --json # View unblocked issues ready for work
bd dep cycles --json # Check for circular dependencies
bd dep tree <epic-id> --json # View dependency tree for an epic
Check:
Before completing, ensure:
For closed/completed issues, verify workflow integration:
bd show <id> --json | jq -r '.notes // "" | scan("THREAD: [^\n]+")'
When all issues in an epic are closed with thread URLs:
Check epic status:
bd show <epic-id> --json
# Verify all child issues have THREAD: in notes
Prompt user: "All issues complete with thread URLs. Run doc-sync to update AGENTS.md? (y/n)"
If yes: Trigger doc-sync workflow with epic ID
When epic is complete (all issues closed):
Prompt: "Epic complete. Archive to conductor/archive/? (y/n)"
If yes:
mv conductor/tracks/<id>/ conductor/archive/<id>/
Update epic notes:
bd update <epic-id> --notes "ARCHIVED: conductor/archive/<id>/"
Provide a review report:
You may iterate on refinements up to 5 times if asked. Track iterations:
After 5 iterations, respond: "I don't think we can do much better than this. The issues are thoroughly reviewed, well-documented, and ready for workers to implement."
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 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.