research-project-planner
Transforms vague research ideas into actionable project routes, hypotheses, and evidence packages.
Install
mkdir -p .claude/skills/research-project-planner && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17298" && unzip -o skill.zip -d .claude/skills/research-project-planner && rm skill.zipInstalls to .claude/skills/research-project-planner
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
用于生物信息学或计算生物学项目启动前，将模糊研究方向转成可执行研究路线：澄清 central question、knowledge gap、hypothesis、evidence package、figure skeleton、技术路线、风险和 stop/pivot criteria。不用于已明确的代码执行、单篇论文阅读或单纯文本润色。Key capabilities
- →Clarify central research questions
- →Define knowledge gaps in a research area
- →Formulate testable hypotheses and expected claims
- →Design evidence packages for research projects
- →Outline technical routes for data analysis and tool selection
- →Generate Project Charter level artifacts
How it works
The skill transforms vague research directions into executable plans by systematically clarifying the central question, identifying knowledge gaps, formulating hypotheses, and outlining the technical and evidence-based approach.
Inputs & outputs
When to use research-project-planner
- →Launching computational biology projects
- →Defining hypothesis and evidence paths
- →Setting go/no-go criteria
About this skill
Research Project Planner
核心问题
如何把已具基本边界的研究方向变成可检验、可分阶段、可停止或转向的项目路线？
边界与归属
- 从科学问题与知识缺口开始，不从可用工具清单开始；用户拥有 central question、方法、figure logic、最终 claim 和 go/no-go 决策。
- 零散想法尚不能形成 bounded question 时，先用
research-question-brief；已有路线需要比较 continue/pivot/stop 或工具取舍时，用research-decision-review。 - 单个 claim 的分层验证选项交给
validation-strategy-planner；本 Skill 只在项目级定义需要何种验证证据及其阶段位置。 - 规划完成后写入当前 GUIDE 交给
project-guide-maintainer；明确代码、分析或绘图任务交给相应执行 Skill。 - 单篇论文阅读用
paper-reader，系统证据地图用literature-search-workflow。不把计划写成已执行结果。
工作流程
- 读取 research brief、项目规则、用户指定证据和必要的当前 GUIDE；不默认读取完整历史或大型 artifact 目录。
- 明确 central question、已知背景、knowledge gap、范围和预期贡献；若关键边界缺失，只问最多三个会改变路线的问题。
- 写 tentative hypothesis 与 expected claim，同时列出竞争解释和 claim 降级条件。
- 设计 evidence package：数据、对照、统计、外部或实验验证、可复现性和主要排除项；区分 exploration、confirmation、validation。
- 用
Known / Unknown / Question / Finding / Advance检查逻辑收敛，并让每张主图对应一个问题与证据门槛。 - 规划 minimum viable analysis、后续模块、依赖、里程碑、risk register 和 bounded implementation tasks；不执行这些任务。
- 对陌生领域先建立最小 field/method map：权威综述、成熟 baseline、可信实现、共识/争议、复现候选和适用限制。
- 为关键节点定义可观测的 continue、pivot 和 stop 条件，标明哪些需要用户决定。
- 输出完整但精简的 project brief，并给出可压缩进 GUIDE 的 seed；不要直接接管 GUIDE 生命周期。
输出契约
- Central question、known/background、knowledge gap、scope
- Tentative hypothesis、expected claim、alternative explanations
- Topic scorecard 与
Known / Unknown / Question / Finding / Advance - Evidence package 与 phase labels
- Figure skeleton（每图的问题、输入和证据门槛）
- Technical modules、minimum viable analysis、dependencies 和 milestones
- Risk register、alternatives、stop/pivot/go-no-go criteria
- Field/method map（仅陌生领域）与 next bounded tasks
- User decisions required 与
PROJECT_GUIDEseed
需要完整字段或可落盘 project brief 时读取 references/project-brief-template.md；只需路线摘要时不要加载模板。
When not to use it
- →When explicit code execution or table processing tasks are given
- →When the user only needs to read a single paper
- →When the user only requires text polishing, translation, or rewriting
Limitations
- →Does not perform active analysis or code execution
- →Does not read long project records by default
- →Focuses on planning rather than direct code implementation
How it compares
This skill provides a structured framework for planning bioinformatics projects from conception to execution, which is more complete than simply performing individual analyses or writing tasks.
Compared to similar skills
research-project-planner side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| research-project-planner (this skill) | 0 | 2mo | No flags | Intermediate |
| literature-review | 559 | 3mo | Review | Advanced |
| openalex-database | 48 | 8mo | Review | Intermediate |
| jupyter-notebook | 30 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by Taichuan3
View all by Taichuan3 →You might also like
literature-review
K-Dense-AI
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
openalex-database
davila7
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
jupyter-notebook
davila7
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
exploratory-data-analysis
K-Dense-AI
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
scientific-critical-thinking
davila7
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
model-compare
rawwerks
Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.