From lemur-os
Use when facing 2+ tasks that can run without shared state, sequential dependency, or overlapping file writes. Trigger when you are about to send subagents and notice they touch disjoint files with no order dependency.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lemur-os:dispatching-parallel-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When tasks are truly independent, dispatch them in a single message with multiple `Task` tool blocks. Parallel dispatch is fast but unsafe when independence isn't real — overlapping writes corrupt state, sequential dependencies produce wrong outputs.
When tasks are truly independent, dispatch them in a single message with multiple Task tool blocks. Parallel dispatch is fast but unsafe when independence isn't real — overlapping writes corrupt state, sequential dependencies produce wrong outputs.
All four conditions must hold:
Parallel dispatches go in a single assistant message with multiple Task tool calls. Splitting across messages is sequential, not parallel.
After all subagents return, aggregate verdicts using the table below before emitting your own verdict.
| Situation | Why wrong | Do this instead |
|---|---|---|
Tasks 2 and 3 both edit theme.ts | Last write wins → silent loss | Sequence |
| Task B uses Task A's output file | Race: B may read before A writes | Sequence |
| Both write to vault under same slug | Librarian serialises via per-slug lock | Either sequence, or accept hidden queueing |
| One task is a migration / env mutation | Side effects sequence-sensitive | Sequence |
For each task, list:
- Files written
- Files read (only)
- Vault slug touched (if any)
If any "Files written" overlaps across tasks → SEQUENTIAL
If any task's "Files read" appears in another's "Files written" → SEQUENTIAL
If 2+ tasks touch the same vault slug → ACCEPT serialisation or sequence
Else → PARALLEL OK
| Any subagent returned | Parent emits |
|---|---|
BLOCKED | BLOCKED |
REQUEST_CHANGES | REQUEST_CHANGES |
DONE_WITH_CONCERNS | DONE_WITH_CONCERNS |
All DONE | DONE |
| Thought | Reality |
|---|---|
| "Last write wins, it's fine" | Last write wins is the bug, not the design. |
| "They probably won't collide" | Probably ≠ provably. List the write sets. |
| "Parallel is always faster" | Parallel-to-a-locked-resource is sequential with extra overhead. |
| "Splitting across messages is still parallel" | No — a new assistant turn means the prior batch already completed. |
Emit the aggregated keyword from the table above.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub demurthelemur/lemuros --plugin lemur-os