levi-qiao/longgraph-skill / skills/loop-research
loop-research
VerifiedUse only when the user explicitly invokes /loop-research or names this skill. Authors a loop-research run. Do not use unless named. Do not execute or resume generated runtime node files.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.4 KB |
| README.zh-CN.md | markdown | 1.3 KB |
| SKILL.md | skill md | 2.0 KB |
| preset.md | markdown | 6.6 KB |
README.md
View on GitHub# loop-research
**A thin `/loop-research` entry for selecting a technical approach with comparative evidence.**
English · [简体中文](README.zh-CN.md)
`/loop-research` binds a research-and-selection pack, then uses
[loop-graph](../loop-graph/SKILL.md) to compile the shared executor, supervisor, ledger,
directives, and ops files. It adds no research runtime, node, or template set.
## When to use it
Use it when the approach is not chosen and the decision needs open-source evidence,
primary research, and a fair benchmark or controlled A/B evaluation. The outcome is
evidence-backed under declared criteria; if the evidence is not comparable or decisive,
it reports that rather than inventing a winner. Use `/loop-deliver` after selection.
## How to run it
1. Invoke `/loop-research` (Claude Code plugin: `longgraph:loop-research`).
2. Answer only unresolved choices: decision boundary, evidence/data/budget authority, and
launch — or accept the recommended option.
3. **A** creates the two nodes on Codex or Claude Code. **B** prints copy-ready prompts
for another host.
Authoring never executes generated runtime nodes.
## Files
| Path | What it is |
| --- | --- |
| [`SKILL.md`](SKILL.md) | Fit check, pack binding, and the focused interview |
| [`preset.md`](preset.md) | Evidence funnel, selection guards, knobs, and artifact emphasis |
Runtime templates live only under [`../loop-graph/templates/`](../loop-graph/templates/).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |