parallel-clone-orchestrator

name	parallel-clone-orchestrator
description	Retired skill tombstone. Do not invoke — use native planning plus llm-compat lanes for advisory work instead. Use when encountering a reference to /pco, /clone, or parallel-clone-orchestrator and need to redirect to the current replacement: native planning + llm-compat lanes.
version	1.0.1
status	retired
retired_on	2026-06-07T00:00:00.000Z
replacement	native planning + _SYSTEM/Scripts/llm-compat.sh / ai llm <lane>
enterprise_ready	false
non_destructive_default	true
triggers	[]
requires	["enterprise-control-plane","audit-events","rollback-policy"]
scope	harness
invocation	workflow

Parallel Clone Orchestrator Skill (Retired)

Retirement Notice

Retired on 2026-06-07 by owner directive. Do not route work through clone orchestration, /pco, /clone, or this skill. Complex decomposition now stays in the native planning session; advisory model calls go through the LLM compatibility lane only. DeepSeek specifically uses ai llm deepseek ..., _SYSTEM/Scripts/llm-compat.sh, or llm-lane.mjs deepseek.

When to use

Do not use this skill. Historical material below is retained only to explain what was retired:

• domain_manifest
• task_breakdown
• clone_budget
• agent_roles
• source_artifacts
• output_contract

Also use it when the active task matches this operating principle:

Split complex work into specialized sub-agents with bounded budgets, clear output contracts, evidence requirements, and a merge protocol that reconciles contradictions before action.

When not to use

Do not use this skill when:

• the task is trivial and does not need system-level treatment
• no target, goal, or evidence source is available
• the user explicitly requests no architectural expansion
• the task would require destructive action without approval
• the extension would duplicate an already active domain without adding value

Retired Trigger Phrases

These phrases used to activate the skill. They are no longer active triggers. Use native planning plus explicit llm-compat advisory lanes instead.

Required inputs

input:
  goal: string
  artifact_type: domain_manifest | task_breakdown | clone_budget | agent_roles | source_artifacts | output_contract
  target: string
  constraints:
    enterprise_mode: 
     
     
     
  
       
     []