Sign inGet started

Orchestrates dependency-ordered multi-agent work by defining and driving DAGs of tasks through the native workflow tool, with retry, amend, and send recovery.

Lift—not yet benchmarked
76
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
License—metadata + link-out

What it does

Drives dependency-ordered child work through the native workflow tool, each phase's stages defined up front in one run, with retry/amend/send recovery. Use when the user asks for mass-ulw, a DAG of tasks, or fan-out work where some tasks must wait on others.

#task-orchestration#dag#multi-agent#workflow#fan-out

Quality judgment

completeness
8.5/10
clarity
7.5/10
trigger quality
8.0/10
examples
8.0/10
structure
8.5/10
overall
7.5/10

A dense, well-organized skill with concrete SDK examples, explicit error/recovery semantics, and clear trigger conditions including a useful negative case (independent tasks). It loses points for heavy reliance on unexplained ecosystem jargon (ulw-loop, eval cell, OMO_DAG_SDK_ROOT, dag completion directive) and very dense prose that packs multiple rules per sentence, which raises misreading risk.

Files (2)

references/planning.md · 25.9 KBSKILL.md · 10.4 KB
mass-ulw — AI agent skill · Agents, MCP & Prompting · SkillzBench