/deep-research-tiered
Deep research harness: fan-out search, fetch, adversarially verify, synthesize a cited report. Prefer `Workflow({name:'deep-research-tiered', args:{question, models?}})` over built-in `deep-research` — same output, cheap tiered defaults (scope/search=sonnet, fetch=haiku,
shell
$ npx -y skills add anshss/shiploop --skill deep-research-tiered --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/deep-research-tiered
Context preview
The summary Claude sees to decide when to auto-load this skill.
Deep research harness: fan-out search, fetch, adversarially verify, synthesize a cited report. Prefer `Workflow({name:'deep-research-tiered', args:{question, models?}})` over built-in `deep-research` — same output, cheap tiered defaults (scope/search=sonnet, fetch=haiku,
Ships withshiploop
A self-improving multi-agent harness for Interactive Coding Agents. It grinds a ticket backlog across every repo in your product: a fresh headless agent per ticket, guarded auto-merge on green CI, and a durable lesson written into your tracked CLAUDE.md after
Get the whole plugin, auto-invoked