YCC-Lover/research-starter-skills / skills/rsk-research-design
rsk-research-design
Verified基于 Research-Starter-Kit 的 TPIC 框架帮助选题、比较候选问题、形成可检验的 Idea 与最小验证。用于研究决策、资源约束和创新点论证,不代替实验结果或论文写作。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
| agents/openai.yaml | config | 318 B |
| references/advanced-design.md | markdown | 1.4 KB |
| references/decision.md | markdown | 2.1 KB |
| references/design.md | markdown | 3.9 KB |
| references/source-manifest.json | config | 5.4 KB |
| references/sources.md | markdown | 2.9 KB |
references/decision.md
View on GitHub# 从候选问题到研究决策
本仓库独立补充。用户已确定题目时,只评估指定疑问,不擅自重新选题。
## 比较会改变决定的因素
用当前证据而非形容词比较:谁需要答案;最近邻已经回答什么;尚余的具体未知;何种结果能区分解释;数据、仪器、时间与合作依赖;最可能失败的环节。把未检索的新颖性、待借用的设备和预计结果列为待确认,不以“创新性高、可行性强”代替依据。
可裁剪为:候选问题 | 价值依据 | 最近邻及差异 | 决定性验证 | 现有资源 | 外部依赖 | 主要风险 | 下一步。先排除硬约束不满足的方案,再解释条件性优先级;不强迫每个因素数字打分,不虚构成本、成功率或导师偏好。
## 使最小验证有信息价值
写清主假设与至少一个合理替代解释、控制条件和观察单位。选择能改变当前决定的最小工作,而不是重复收集有利示例。继续、调整或停止的判据应来自目标与测量能力,不能看到结果后再选择阈值。
教学例子:A 方案需要尚未获准使用的仪器,B 方案可用现有材料区分两个解释。可以优先核查 B,同时把 A 的仪器可用性作为待确认条件;这不证明 B 更有创新性。失败也可能支持缩小范围,不能自动解释成研究没有价值。
## 交付决策而非替用户拍板
先给一句近期优先建议,再用少量有信息差的维度解释。将“这周能推进什么”与“值得长期投入什么”分开;资源尚未落实的方向可以保留为后备。最小验证要说明:它区分哪两种解释、观察哪项结果、结果分别会改变什么决定。与当前决定无关的测量留到后续,使用户能立即分配时间和材料。
给出建议、依据、能推翻建议的新信息与下一步。尚未检索时,只能提出候选方向及检索验证计划。用户需要论文开题材料时,把已完成前期工作和拟研究内容分开,由写作模块组织而不伪造预实验。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |