Individual skill

light-design

Turn a research idea into an executable study or experiment plan, especially after light-idea. Use for 实验设计、研究设计、实验规划、对照与消融、样本量论证、先导实验、预分析计划 and experiment handoff. Connect claims to discriminating tests, verified resources, analysis, budgets and decision rules. Idea discovery, analysis of collected data and running full experiments belong to adjacent workflows.

light-design/SKILL.md

Read pinned source

Source commit 6597430ad09d8f7c3518ec4cb08829be2b417e18

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 901
Repository last updated: Nov 8, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

academic-writing Repository topic
ai-agent Repository topic
claude-code Repository topic
codex Repository topic
llm-skills Repository topic
paper-writing Repository topic
research-tools Repository topic
scientific-workflow Repository topic
agent-skills Repository topic
ai-skills Repository topic
design Derived category
data Derived category
research Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.gitignoreasset · 37 bytes
SKILL.mdcore · 13,182 bytes
SKILL.mdcore · 13,182 bytes
SKILL.mdcore · 13,182 bytes
agents/openai.yamlasset · 366 bytes
evaluations/2026-11-06-upgrade.mddoc · 4,062 bytes
evaluations/scenarios.mddoc · 5,697 bytes
evaluations/validation-report.mddoc · 2,835 bytes
references/artifact-contract.mddoc · 7,925 bytes
references/design-choice.mddoc · 4,331 bytes
references/domain-guides.mddoc · 6,007 bytes
references/execution-and-decisions.mddoc · 4,368 bytes
references/measurement-and-analysis.mddoc · 4,203 bytes
references/pipeline.mddoc · 3,557 bytes
references/project-layout.mddoc · 6,054 bytes
references/repository-audit.jsonasset · 6,595 bytes
references/revision-and-handoff.mddoc · 4,238 bytes
references/sources.mddoc · 16,503 bytes
scripts/design_bridge.pyruns · 25,573 bytes
templates/design.example.jsonasset · 479 bytes
templates/plan.mddoc · 2,654 bytes
tests/test_design_bridge.pyruns · 13,986 bytes
tests/test_source_handoff.pyruns · 7,445 bytes

Read excerpt


# Light Design

## 项目目录与续作

需要落盘或继续已有项目时，先读 [项目目录约定](references/project-layout.md)，按其中的本阶段位置、版本与关联规则保存；用户指定路径和旧项目优先。包内资源相对本 skill，研究产物相对真实项目，二者不要混用。只做局部讨论时无需初始化目录。

把一个值得研究的想法落成**别人拿到就知道如何开展、如何记录、如何判断结果的研究方案**。默认中文交流，保留原始论文标题、变量名与必要术语。核心交付是可回答问题的设计，不是把实验数量堆满，也不是提前写出理想结果。

宿主负责科学推理、原文核对和设计取舍；附带脚本只冻结上游输入、检查记录关系，不调用模型、不联网、不启动实验。快速讨论直接在聊天中完成；只有需要项目交付时才建立文件。

续作先读实际设计版本和已采用范围；有 Memory 时恢复有关决定、设计取舍及失效前提并核对来源，有 Workflow 时查看当前任务与交接。用户已明确局部修改就直接处理有关内容，不初始化无关阶段。记忆不能代替原设计或批准执行。

## 接收任务与选择深度