loop-research
Author and optionally direct-launch a two-node loop-graph run that compares feasible technical approaches with open-source evidence, primary research, and controlled experiments before selecting one. Use when a decision needs several research and evaluation rounds with durable evidence and independent audit. Not for implementing an already chosen requirement, code cleanup, or a quick literature summary. Do not execute or resume generated runtime node files from this authoring skill.
levi-qiao · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add levi-qiao/longgraph-skill --skill loop-research技能说明
name: loop-research description: Author and optionally direct-launch a two-node loop-graph run that compares feasible technical approaches with open-source evidence, primary research, and controlled experiments before selecting one. Use when a decision needs several research and evaluation rounds with durable evidence and independent audit. Not for implementing an already chosen requirement, code cleanup, or a quick literature summary. Do not execute or resume generated runtime node files from this authoring skill.
loop-research — a loop-graph preset for evidence-led choices
A thin authoring entry. It binds a research-and-selection pack, starts the owner
interview, then follows loop-graph to compile the normal
executor, ledger, directives, ops, and supervisor artifacts. It is not a research node,
a second runtime, or a second template set.
Fit check
- Use this when the approach is undecided and a decision needs comparative evidence from open-source projects, primary research, and a controlled benchmark or A/B experiment.
- Use
../loop-deliver/SKILL.mdonce the approach is chosen, or../loop-converge/SKILL.mdfor code consolidation. - For a short answer, one source lookup, or non-comparative literature summary, use the host's ordinary research task instead of a graph.
On invoke
- Inspect the workspace, existing evidence, experiment harnesses, data policy, and current host the same way loop-graph does. Never ask which client this is when context already identifies it.
- Read and bind
preset.md. That pack is the North Star, supervisor requirement, interview, evidence shape, method guards, knob overrides, and artifact emphasis. Do not redesign them. - Start the owner interview immediately. Ask only the pack's unresolved choices — decision/scope, evidence budget and data authority, and launch — as recommended A/B (or A/B/C) choices. Do not ask the owner to invent evaluation criteria.
- Read and follow
../loop-graph/SKILL.mdfrom When called from a preset skill through generate and deliver. Compile only from loop-graph'stemplates/. This skill never executes the generated nodes.