Individual skill

light-analysis

Analyze existing research experiment results, especially after light-experiment. Use for 实验结果分析、方法比较、误差与不确定性、阴性结果、消融与机制解释、稳健性分析 and deciding whether to return to execution, light-design or light-idea. Produce traceable findings and a bounded next research step. Designing a study from scratch, running new scientific experiments and manuscript-only polishing belong elsewhere.

light-analysis/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: Yes
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): 892
Repository last updated: Nov 7, 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
research Derived category
design 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 · 23 bytes
SKILL.mdcore · 14,186 bytes
agents/openai.yamlasset · 367 bytes
evaluations/2026-11-06-upgrade.mddoc · 5,528 bytes
evaluations/fixtures/task-seed-comparison/protocol.mddoc · 1,593 bytes
evaluations/fixtures/task-seed-comparison/scores.csvasset · 359 bytes
evaluations/forward-test.mddoc · 3,149 bytes
evaluations/forward-test/observed/analysis-plan.jsonasset · 4,571 bytes
evaluations/forward-test/observed/analysis-report.mddoc · 11,949 bytes
evaluations/forward-test/observed/analysis.jsonasset · 10,873 bytes
evaluations/forward-test/observed/artifacts/NUMBERS.jsonasset · 739 bytes
evaluations/forward-test/observed/artifacts/TASKS.jsonasset · 740 bytes
evaluations/forward-test/observed/code/analyze.pyruns · 10,291 bytes
evaluations/forward-test/observed/context.jsonasset · 904 bytes
evaluations/forward-test/observed/derived/results.jsonasset · 8,517 bytes
evaluations/forward-test/observed/derived/task-summary.csvasset · 595 bytes
evaluations/forward-test/observed/handoff.jsonasset · 10,967 bytes
evaluations/forward-test/observed/inputs/protocol.mddoc · 1,593 bytes
evaluations/forward-test/observed/inputs/scores.csvasset · 359 bytes
evaluations/forward-test/observed/plan-lock.jsonasset · 331 bytes
evaluations/forward-test/observed/receipt.jsonasset · 236 bytes
evaluations/forward-test/observed/verification.jsonasset · 372 bytes
evaluations/forward-test/review.jsonasset · 4,971 bytes
evaluations/integration-results.jsonasset · 742 bytes
evaluations/scenarios.mddoc · 5,277 bytes
evaluations/validation-report.mddoc · 3,784 bytes
references/analysis-methods.mddoc · 8,177 bytes
references/artifact-contract.mddoc · 13,034 bytes
references/domain-guides.mddoc · 5,995 bytes
references/pipeline-loop.mddoc · 8,222 bytes
references/project-layout.mddoc · 6,117 bytes
references/repository-audit.jsonasset · 15,200 bytes
references/search-log.jsonasset · 4,829 bytes
references/sources.mddoc · 15,689 bytes
scripts/analysis_bridge.pyruns · 36,790 bytes
scripts/paired_effect.pyruns · 5,667 bytes
templates/analysis-plan.example.jsonasset · 359 bytes
templates/analysis-report.mddoc · 2,291 bytes
templates/analysis.example.jsonasset · 534 bytes
tests/test_analysis.pyruns · 14,466 bytes
tests/test_evidence_integrity.pyruns · 12,267 bytes
tests/test_native_intake.pyruns · 6,151 bytes
tests/test_pipeline_integration.pyruns · 6,781 bytes

Read excerpt


# Light Analysis

## 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。

持续项目先从已有 Memory/current.md 恢复问题、已采用规格、前轮否定的解释与待办，再核对 Analysis 和实际实验来源；旧摘要不充当重新核验。有关 Workflow 任务只在现有授权范围内续作。一个项目以一篇核心论文或一项软著及关联成果为单位，分析不是自动拆出多篇论文的入口。

把实际实验产物变成**有边界的研究结论，以及有证据、有停止条件的下一步**。本技能在 v2.0.0 及更早版本中名为 `light-anaysis`，现更正为 `light-analysis`；旧项目记录里的旧名指同一技能。默认中文，覆盖 ML、算法与系统、数值计算、仿真和一般定量研究；理论与定性材料按对应证据方式解释，不强套统计检验。

宿主负责真正读取、编写并运行分析代码、解释证据和研究取舍；辅助脚本只冻结输入、记录关系、检查一致性，或计算明确适用的一种配对效应。导入成功、进程成功和统计显著都不等于科学主张成立。方法资料库不是用户课题本身的实验证据。

## 选择入口