research-director

Strategic research leadership for designing high-impact research agendas, coordinating teams, and translating research into policy and institutional influence.

跳到安装查看文件

仓库: brycewang-stanford/Auto-Empirical-Research-Skills
最近来源活动: 2026年7月22日 09:27
检测到的 SKILL.md 语言: 英语
星标: 4,570
分支: 541

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 AI 助手安装

复制这段 Prompt，发给你正在使用的 AI 助手。

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/19-CuellarC05-vera-economic-intelligence/research/research-director.

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills --skill research-director

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

2 个文件

SKILL.md

来源说明 · 只读预览

name: research-director
description: Strategic research leadership for designing high-impact research agendas, coordinating teams, and translating research into policy and institutional influence.
owner: Vera / Research
tags: ["research","strategy","leadership","publication"]
triggers: ["research strategy","design research agenda","research director"]
inputs: [{"name":"research_goal","type":"string","required":false}]
outputs: [{"name":"research_program_plan","type":"document"},{"name":"publication_pipeline","type":"document"}]
examples: [{"prompt":"Design a 3-year research program on childcare affordability focused on policy impact.\n","expected":"Stream-level objectives, paper slate, student roles, data sources, and dissemination plan.\n"}]
guardrails: Prioritize data availability and policy relevance; flag projects requiring significant new data collection.

Purpose Act as a Research Director supporting agenda design, identify high-value questions, structure publication pipelines, coordinate student teams, and translate research into policy. Workflow 1. Identify high-value research questions (originality, data availability, feasibility, policy importance) 2. Design research streams rather than isolated papers 3. Build publication pipelines (academic → policy → public-facing outputs) 4. Integrate student research to scale capacity and training 5. Structure projects with clear Research Question, Data, Identification Strategy, and Expected Contribution 6. Plan institutional activities to build long-term impact (indices, dashboards, partnerships) Success Conditions - Research ideas become clear projects - Projects fit a coherent agenda and publication pipeline - Outputs enable publications, policy engagement, or institutional growth

在 GitHub 查看

返回搜索返回安装

auto-empirical-research-skills

Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows, or an end-to-end run from raw data all the way to a finished Word (.docx) manuscript, without reading the entire repository at once.

2026-10-05

humanizer-academic

Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature.

2026-09-30

statspai-skill

Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 / Table 2 / event-study figure / robustness gauntlet — OR in epidemiology / public health style (target-trial emulation, IPTW + g-formula + TMLE triplet, Mendelian randomization, KM/AFT survival, E-value sensitivity, STROBE/TRIPOD reporting) — OR in ML causal inference style (DML, S/T/X/R/DR meta-learners, causal forest, Dragonnet/TARNet/CEVAE, BCF, CATE distribution, policy learning, conformal causal, fairness audit, causal discovery) — OR in distributional / gap-decomposition style (Oaxaca–Blinder `sp.oaxaca`, Kitagawa `sp.kitagawa_decompose`, DiNardo–Fortin–Lemieux `sp.dfl_decompose`, Gelbach `sp.gelbach`, Fairlie `sp.fairlie`, RIF / FFL `sp.rif_decomposition`, all reachable through the `sp.decompose` dispatcher). Also covers exporting mu

2026-09-30

查看这个仓库的全部 Skills

research-director

来源信息

安装方式

用 AI 助手安装

检查来源文件

同仓库更多 Skills

用 AI 助手安装

同仓库更多 Skills