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.md once the approach is chosen,
or ../loop-converge/SKILL.md for 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.md from When called
from a preset skill through generate and deliver. Compile only from
loop-graph's templates/. This skill never executes the
generated nodes.
1---2name: loop-research3description: 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.4---56# loop-research — a loop-graph preset for evidence-led choices78A thin authoring entry. It binds a research-and-selection pack, starts the owner9interview, then follows [`loop-graph`](../loop-graph/SKILL.md) to compile the normal10executor, ledger, directives, ops, and supervisor artifacts. It is not a research node,11a second runtime, or a second template set.1213## Fit check1415- Use this when the approach is undecided and a decision needs comparative evidence from16 open-source projects, primary research, and a controlled benchmark or A/B experiment.17- Use [`../loop-deliver/SKILL.md`](../loop-deliver/SKILL.md) once the approach is chosen,18 or [`../loop-converge/SKILL.md`](../loop-converge/SKILL.md) for code consolidation.19- For a short answer, one source lookup, or non-comparative literature summary, use the20 host's ordinary research task instead of a graph.2122## On invoke23241. Inspect the workspace, existing evidence, experiment harnesses, data policy, and25 current host the same way loop-graph does. Never ask which client this is when context26 already identifies it.272. Read and bind [`preset.md`](preset.md). That pack is the North Star, supervisor28 requirement, interview, evidence shape, method guards, knob overrides, and artifact29 emphasis. Do not redesign them.303. Start the owner interview immediately. Ask only the pack's unresolved choices —31 decision/scope, evidence budget and data authority, and launch — as recommended A/B32 (or A/B/C) choices. Do not ask the owner to invent evaluation criteria.334. Read and follow [`../loop-graph/SKILL.md`](../loop-graph/SKILL.md) from **When called34 from a preset skill** through generate and deliver. Compile only from35 loop-graph's [`templates/`](../loop-graph/templates/). This skill never executes the36 generated nodes.
levi-qiao