academic-research

academic-research is a skill for Claude Code from GGbond-bo/MemOmics-Agent. It costs 21 tokens per session (3,714 once invoked), scanned A, original, MIT.

A research-planning tool for designing experiments, reviewing scientific literature, and turning a biological question into a testable study plan. It covers hypotheses, expected observations, methods, evidence, and analysis choices.

In plain words
What is it for?
Use it to design experiments, plan research projects, or prepare a literature-based study proposal with hypotheses, methods, and predicted results.
Why use it?
It helps organize a research idea into explicit claims, controls, methods, and supporting sources instead of leaving the plan as a loose outline.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit Use it to design experiments, plan research projects, or prepare a literature-based study proposal with hypotheses, methods, and predicted results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ggbond-bo/memomics-agent/academic-research
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add GGbond-bo/MemOmics-Agent --skill academic-research
Clone the repo
git clone --depth 1 https://github.com/GGbond-bo/MemOmics-Agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for academic-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/academic-research/github.svg)](https://agentmods.dev/skills/ggbond-bo/memomics-agent/academic-research)
Your own site
<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/academic-research"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/academic-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for academic-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/academic-research"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/academic-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.03714
Opus 5 $0.00010 $0.01857
Sonnet 5 $0.00004 $0.00743
Haiku 4.5 $0.00002 $0.00371

Measured 9d ago against content hash 815ce6e790e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

academic-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hermes_home/skills/bioinformatics/academic-research/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

学术研究设计

综合学术研究技能:实验方案设计、文献检索、研究规划

适用场景: 实验方案设计, 研究规划, 文献综述

难度: advanced

触发提示: "帮我设计实验方案"

别名: 实验方案, 研究设计, experiment design, 研究方案

When to Use

适用于: 实验方案设计, 研究规划, 文献综述

执行模板 — CNS 级研究方案生成

当用户请求生成研究方案时,必须按以下 10 段模板输出。禁止省略任何一个段落。

## 研究方案: {species} {tissue} {direction}

### 1. 核心假说 (Core Hypothesis)
- **生物学问题**: 用 1-2 句话描述要回答的生物学问题
- **已发表工作缺口 (Gap)**: 对比 [KB] 中的文献,说明现有知识缺少什么
- **零假说 (H₀)**: 无效应/无差异的陈述
- **备择假说 (H₁)**: 本研究要验证的主张
- **预测链**: 如果 H₁ 成立 → 预期观察 A → 预期观察 B → 预期观察 C
  - 预测 A: {用数据X的方法Y检验}
  - 预测 B: ...
  - 预测 C: ...

### 2. 创新性声明 (Novelty Statement)
- **本研究 vs 已发表工作**: 与 [KB: 论文名] 相比,本研究的独特之处在于:
  - (1) 新数据/新物种/新组织
  - (2) 新方法/新组合
  - (3) 新假说/新角度
- **潜在领域贡献**: 如果假说成立,将改变 __ 的认知

### 3. 文献依据 (Literature Foundation)
| 文献(作者+年份,PMID/DOI) | 关键方法 | 与本方案关系 | 来源 |
|--------------------------|----------|-------------|------|
| ... | Seurat v4.0.2, SCTransform | 方法参考+可复现性 | [KB] |
| ... | ... | ... | [PMID:xxx] |

### 4. 分析方法与论证 (Methods & Rationale)
每个方法必须回答: **为什么选这个方法?它验证假说的哪一部分?**
1. **数据预处理**: [KB] Seurat v4.0.2 → SCTransform
   - 理由: SCTransform 优于 LogNormalize 因为 [具体理由,如 UMI count 异方差性]
   - 验证: 预测 A (细胞类型鉴定)
2. **批次校正**: [KB] Harmony v1.0
   - 理由: 优于 Seurat CCA 因为 [datasets 大小不均/跨物种]
   - 验证: 预测 A (确保 cell type 而非 batch 驱动聚类)
3. ...
每个方法的理由必须有实质性内容,不能只说"常用"/"标准"

### 5. 统计方案 (Statistical Plan)

> **针对多因素干预研究**(如衰老×疾病×运动),统计设计须特别注意:
> - **交互效应检验**:DESeq2/limma 公式 `~ group + time + group:time`,检验 FDR < 0.05 的交互 DEGs
> - **两轮策略**:第一轮做组内配对对比(pre vs post),第二轮比较效应量的组间差异(meta-analytic thinking)
> - **小型样本**(每组 n≤3):降维为"一阶效应对比 + 效应量比较"而非 full factorial;使用 MCMC 建模
> - **协变量控制**:将额外临床指标(BMI, HbA1c, VO2max)纳入线性模型

- **统计功效**: 基于预期效应量 ___ (Cohen's d/log2FC),显著性 α=0.05,需≥___ 样本
- **多重检验校正**: BH (FDR < 0.05) 或 Bonferroni (当检验数<10时)
- **效应量度量**: log2FC ≥ 0.5(scRNA-seq)/ ≥ 1.0(bulk RNA-seq), Cohen's d ≥ 0.8
- **阴性对照**: (如: shuffled labels, permuted genotypes, shuffled cell type labels)
- **阳性对照**: (如: 已知衰老标记基因 SenMayo/CellAge, 已知运动应答基因 PPARGC1A/ESRRG)
- **批次效应评估**: kBET, LISI score

### 6. Figure 策略 (Figure Strategy)

> **多因素干预研究特别指导**:参考 `references/multi-factor-study-design.md` 的 Phase 1-4 框架
> - Phase 1 → Figure 1(基线图谱)
> - Phase 2 → Figure 2(干预效果)
> - Phase 3 → Figure 3(机制深挖)
> - Phase 4 → Figure 4+(整合与模型)
> - 每个 Phase 的 Figure 结构见参考文件中的具体模板

**每张Figure对应假说的一个预测,必须写明预期结果:**
- **Figure 1**: [验证预测A] {标题}
  - 内容: UMAP/标记基因表达
  - 预期结果: 明确cluster分离,已知marker在对应cluster高表达
  - 如预期不符合: [备选] 调整分辨率,手动注释
- **Figure 2**: [验证预测B] {标题}
  - 内容: 差异表达 + 通路富集
  - 预期结果: DEGs富集于衰老通路,SenMayo基因集上调
  - 如预期不符合: [备选] GSEA替代ORA,降低FDR阈值
- **Figure 3**: [验证预测C] {标题}
  - 内容: ...
参见 `references/cns-figure-trinity.md` 获取详细模板和真实案例。

## ⚠️ 知识库引用规则
- **正交验证**: (如 IF 染色验证蛋白水平、RNA-FISH 验证空间定位、qPCR 验证关键基因)
- **公共数据验证**: (如 Tabula Muris Senis, GTEx, Human Cell Atlas)
- **阳性对照基因集**: SenMayo / CellAge / GO:0007568 (aging)
- **如果全部预测被证伪**: 报告 negative result,讨论原因(统计功效不足?假说错误?)

### 8. 备选方案与风险 (Contingency Plan)
| 风险 | 可能性 (高/中/低) | 缓解策略 |
|------|-------------------|----------|
| 细胞数/基因数不足 (QC过滤过严) | 中 | 降低 MT%阈值,用 EmptyDrops 替代 |
| 批次效应无法消除 | 低 | 切换 Seurat CCA+RPCA,分析每个 batch 单独验证 |
| 假说被完全证伪 | 低 | 转向 explorative analysis,报告 negative result |
| [KB] 方法不适合本研究 | 中 | 回退到 [PMID:xxx] 中的备选方法 |

### 9. 可复现性声明 (Reproducibility)
- **代码**: GitHub/Figshare (提交时附URL)
- **数据**: GEO accession / EGA / dbGaP (如有)
- **环境**: Docker/Singularity 容器 + conda env yaml → 提供 container URL
- **随机种子**: set.seed(42) / random_state=42

### 10. 可执行待办
调用 memomics_pipeline(action='todos', selected_modules=[...])

### 11. 交付格式
用户要求"生成完整方案"时,必须以 **可编辑文档(DOCX优先)** 交付,同时生成 PDF。
- 使用 python-docx 生成 Word 文档,路径: `results/research_proposal/{species}_{tissue}_{direction}_CNS方案_v{version}.docx`
- 使用 reportlab 生成 PDF 附件
- 脚本保留在 `results/research_proposal/generate_proposal.py`,可复现修改

## ⚠️ 用户偏好嵌入(2026-07-13 会话)

当用户(尤其是骨骼肌衰老方向)要求CNS级方案时,已纠正过的问题:
| 用户投诉 | 根因 | 必须做到 |
|---------|------|---------|
| "太泛了,深度不够" | 只有方法列表,无论文级phased结构 | Phase 1-5分层 + Figure三一结构 |
| "不分阶段" | 一次性讲所有内容 | 每Phase只答一个生物学问题 |
| "看看人家文章怎么探究的" | 缺论文技术对照表 | 必须有:参考论文 vs 本研究 Figure/方法对应表 |
| "太泛"(再次) | 预测无具体数值 | 必须写"Type II从49%→29%"这类精确数值+文献依据 |
| 无可执行性 | 只讲"做什么"不讲"顺序" | Phase级待办清单 + skill绑定 |

Read the full file on GitHub · 236 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 236 lines · 21 tokens per session scan A 815ce6e790e4

Subscribe to this mod's changes

academic-research is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 3,714 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens