File detailed Beads epics and issues from a plan
/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.
Convert a plan into Beads epics and issues using sequential subagents to keep the main context clean.
Why Sequential? The
bdCLI does not have file locking or atomic ID generation. Parallelbd createcalls cause race conditions (ID collisions, data corruption). Each epic must complete before the next begins.
Review the plan context: $ARGUMENTS
If no plan provided, check:
docs/plans/ directoryconductor/tracks/ for spec.md and plan.md filesIdentify for each epic:
| Field | Description |
|---|---|
| Epic title | Clear workstream name |
| Child tasks | Individual issues under this epic |
| Intra-epic deps | Dependencies within the epic |
| Cross-epic hints | Tasks that depend on other epics (by name, not ID) |
| Priority | 0-4 scale |
Dispatch one subagent per epic. Wait for each to complete before starting the next to avoid ID collisions.
File Epic: "<EPIC_TITLE>"
## Your Task
Create one epic and all its child issues in Beads.
## Epic Context
<PASTE_EPIC_SECTION_FROM_PLAN>
## Steps
1. Create the epic:
```bash
bd create "Epic: <title>" -t epic -p <priority> --json
For each task, create an issue with parent dependency:
bd create "<task title>" -t <type> -p <priority> --deps bd-<epic-id> --json
Include in each issue:
Link intra-epic dependencies:
bd dep add bd-<child> bd-<blocker> --type blocks --json
Return ONLY this JSON (no other text):
{
"epicId": "bd-XXX",
"epicTitle": "<title>",
"issues": [
{"id": "bd-XXX", "title": "...", "deps": ["bd-XXX"]}
],
"crossEpicDeps": [
{"issueId": "bd-XXX", "needsLinkTo": "<epic or task name>"}
]
}
### Dispatch Example
Task(description: "File Epic: Authentication", prompt: <above template>) // Wait for result...
Task(description: "File Epic: Database Layer", prompt: <above template>) // Wait for result...
Task(description: "File Epic: API Endpoints", prompt: <above template>) // Wait for result...
**Execute sequentially** — each subagent must return before dispatching the next.
## Phase 3: Collect & Link Cross-Epic Dependencies
When subagents return:
1. Parse JSON results from each subagent
2. Build ID lookup table:
"Authentication" → bd-101 "Database Layer" → bd-102 "Setup user table" → bd-105
3. Resolve cross-epic dependencies:
```bash
bd dep add bd-<from> bd-<to> --type blocks --json
Run verification:
bd list --json
bd ready --json
Check:
Present to user:
## Filed Beads Summary
**Epics created:** 3
**Issues created:** 12
| Epic | Issues | Ready |
|------|--------|-------|
| Authentication | 4 | 2 |
| Database Layer | 5 | 1 |
| API Endpoints | 3 | 0 (blocked) |
**Start with:** bd-105 (Setup user table), bd-108 (Init auth config)
**Cross-epic deps linked:** 2
| Priority | Use For |
|---|---|
| 0 | Critical path blockers, security |
| 1 | Core functionality, high value |
| 2 | Standard work (default) |
| 3 | Nice-to-haves, polish |
| 4 | Backlog, future |
bd CLI lacks file locking; serial execution prevents ID collisionsbd create output stays in subagent contextsAfter filing, save handoff state and output for next session:
bd update <epic-id> --notes "HANDOFF_READY: true. PLAN: <plan-path>"
Where <plan-path> is the source plan (e.g., conductor/plans/2024-12-20-feature-design.md or conductor/tracks/<id>/plan.md)
## HANDOFF
**Command:** `Start epic <epic-id>`
**Epic:** <epic-id> - <epic-title>
**Plan:** <plan-path>
**Ready issues:** <count>
**First task:** <first-issue-id> - <title>
Copy the command above to start a new session.
This enables the execution-workflow to detect handoffs and load epic context automatically.
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.