Auto-Empirical Research Skills Router

Name: Auto-Empirical Research Skills Router
Author: brycewang-stanford

Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill…

Install this skill Read the source first Free Written by brycewang-stanford

Context cost: 970.8k tokensestimated from the bundle; more than a 200k window holds
Bundle: 122 of 4215 fileshanded out here; the rest is at its source
Licence: CC-BY-SA-4.0the author’s own terms
Last change: —no release on file
Servers it uses: Noneruns standalone

What it does

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.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

data scienceresearch

Filed under

AI & Agents

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md13.4 kB · preview

--- name: auto-empirical-research-skills license: CC-BY-SA-4.0 ---

7# Auto-Empirical Research Skills Router

9Use this root skill when the full AERS repository has been installed as a single skill folder. Treat it as a router and catalog, not as a request to load every vendored SKILL.md.

11The catalog holds **1,107 skills across 77 vendored collections**. Never read them all — route to one, then load only that skill's SKILL.md.

13## Workflow

151. Classify the user's empirical-research task by **stage**, then load the single best-matching skill:

16 - Full pipeline or orchestration: start with skills/69-Paper-WorkFlow/ or the skills/00* flagship analysis skills — skills/00-Full-empirical-analysis-skill_StatsPAI/ (StatsPAI), skills/00.1-Full-empirical-analysis-skill_Python/ (Python), skills/00.2-Full-empirical-analysis-skill_Stata/ (Stata), skills/00.3-Full-empirical-analysis-skill_R/ (R). Note the StatsPAI flagship has no dot in its prefix, so a skills/00.* glob misses it.

17 - Causal inference and econometrics: pick by method from the table below, or search catalog/skills.json / docs/TAXONOMY.md.

18 - AER or top economics journal work: start with skills/50-brycewang-aer-skills/.

19 - Replication, citation, or peer review: use docs/SKILL_CATALOG.md and docs/GOLDEN_WORKFLOWS.md to choose a focused skill.

20 - Academic de-AIGC (English or Chinese) or academic rewriting: start with skills/48-de-AIGC-skills/ or nearby writing skills in the catalog.

212. Read only the selected child skill's SKILL.md, then follow its progressive-disclosure instructions for references/, scripts/, assets/, or templates.

223. If no child skill clearly matches, run the ranked catalog search first — it takes English or Chinese task text:

24 ```bash

25 python3 scripts/find-skill.py "staggered difference-in-differences event study"

This is a preview of SKILL.md. Download or install the skill to get the whole thing.

In the file

SKILL.md1,564 words

Files122

LicenceCC-BY-SA-4.0

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈160

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

970,590

on trigger

The instruction body and 121 supporting files, read only when the skill fires.

4.9×

a 200k window

It does not fit in the window: loaded whole, it would need more room than the model has.

050k100k150k200k context window

970.8k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for

Writes filesnot declared

Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

870 other skills in AI & Agents

What is in the bundle

The download carries 122 of the 4215 files in its source folder; the list here names 122 files, 4173.1 kB on disk. Mostly text — the instructions the model reads — with 14 scripts in it that your client would run only if the instructions tell it to. The other 4,093 are not in the download — the first 100 are listed after these, with why.

SKILL.md13.4 kB
.pre-commit-config.yaml2.5 kB
CHANGELOG.md41.0 kB
CODE_OF_CONDUCT.md1.1 kB
CONTRIBUTING.md5.7 kB
INSTALL.md11.2 kB
LICENSE0.6 kB
README-en.md76.0 kB
README-ja.md84.8 kB
README-ko.md78.7 kB
README-zh-CN.md5.8 kB
README-zh-TW.md71.8 kB
README.md40.3 kB
SECURITY-SCAN-REPORT.md22.9 kB
SECURITY.md2.6 kB
index.html6.7 kB
pyproject.toml2.1 kB
requirements.txt1.8 kB
.claude-plugin/marketplace.json5.3 kB
.github/dependabot.yml1.0 kB
.github/pull_request_template.md1.0 kB
aers_score/README.md3.6 kB
aers_score/__init__.py1.4 kB
aers_score/__main__.py0.2 kB
aers_score/cli.py17.9 kB
aers_score/exam.py13.8 kB
agents/README.md5.5 kB
agents/aider.yaml3.7 kB
agents/anthropic.yaml4.6 kB
agents/codebuddy.yaml3.3 kB
agents/cursor.yaml5.0 kB
agents/openai.yaml0.2 kB
benchmark/README.md11.6 kB
benchmark/check_benchmark.py39.1 kB
benchmark/reference_pipeline.py23.0 kB
catalog/curation.json7.2 kB
catalog/provenance.json46.7 kB
catalog/security-scan.json19.4 kB
catalog/skill-audit.json381.1 kB
catalog/skills-enriched.json1025.1 kB
catalog/skills.json902.2 kB
demo-StatsPAI-skill/README.md7.0 kB
demo-StatsPAI-skill/card_returns_to_schooling_pipeline.py29.0 kB
demo-notebooks/README.md3.4 kB
demo-notebooks/_lalonde_data.csv27.5 kB
demo-notebooks/manuscript_docx_demo.py10.4 kB
demo-notebooks/statsPAI_pipeline_5.2.py37.1 kB
demo-notebooks/statsPAI_pipeline_v2.py32.4 kB
docs/01-选题与研究设计.md8.7 kB
docs/02-文献检索与综述.md11.5 kB
docs/03-论文阅读与拆解.md6.7 kB
docs/04-数据获取与清洗.md9.1 kB
docs/05-统计分析与因果推断.md14.7 kB
docs/06-论文写作.md7.8 kB
docs/07-论文修改与润色.md15.2 kB
docs/08-引用管理与排版.md7.5 kB
docs/09-论文复现与可复现研究.md8.4 kB
docs/10-审稿回复与学术答辩.md6.3 kB
docs/AGENT_COORDINATION.md2.2 kB
docs/BENCHMARK_SCOREBOARD.md4.6 kB
docs/CHOOSING_A_SKILL.md5.5 kB
docs/COMPETITIVE_LANDSCAPE.md5.7 kB
docs/CONTENT_ZH.md72.5 kB
docs/ECOSYSTEM.md9.6 kB
docs/EVALS.md11.7 kB
docs/EXTERNAL_SCOREBOARD.md2.2 kB
docs/FAQ.md4.5 kB
docs/GETTING_STARTED.md5.9 kB
docs/GOLDEN_WORKFLOWS.md6.7 kB
docs/INSTALL.md3.9 kB
docs/INTEROP.md9.1 kB
docs/LICENSE_AUDIT.md17.0 kB
docs/LINK_TRIAGE.md0.8 kB
docs/LONG_SKILL_SPLIT_PLAN.md4.1 kB
docs/LONG_SKILL_STATUS.md9.5 kB
docs/MAINTAINER_PLAYBOOK.md2.0 kB
docs/OUT_OF_SCOPE.md25.6 kB
docs/PLAN-2026-07.md7.8 kB
docs/PLAN-2026-08.md5.1 kB
docs/PLAN-2026-09.md8.1 kB
docs/PLAN-2026-10.md5.2 kB
docs/PYPI_PACKAGING_DRAFT.md6.4 kB
docs/QUALITY_ASSESSMENT_2026-07.md7.8 kB
docs/QUALITY_GATE.md5.3 kB
docs/QUICKSTART_REPORT.md2.3 kB
docs/README.md3.1 kB
docs/RELEASE.md1.2 kB
docs/RELEASE_NOTES.md2.0 kB
docs/RIGOR_COVERAGE.md8.0 kB
docs/ROADMAP.md5.9 kB
docs/SCOREBOARD.md6.9 kB
docs/SCOREBOARD_RULES.md5.9 kB
docs/SKILL_AUDIT.md12.3 kB
docs/SKILL_CATALOG.md328.8 kB
docs/SKILL_FRONTMATTER_SPEC.md4.8 kB
docs/SKILL_HYGIENE.md13.7 kB
docs/SKILL_QUALITY.md0.7 kB
docs/SKILL_SUBMISSION_GUIDE.md2.0 kB
docs/SUBMODULE_ASSESSMENT.md6.7 kB
docs/TAXONOMY.md30.2 kB
docs/TRUST.md7.2 kB
docs/WORKFLOW_MAP.md5.7 kB
docs/agent-worklog-bench.md4.8 kB
docs/search.html9.2 kB
docs/tools-search.html9.8 kB
ecosystem/ecosystem.json10.1 kB
eval-harness/README.md9.3 kB
eval-harness/run_evals.py36.1 kB
evals/flagship-evals.json11.2 kB
evals/routing-cases.json23.1 kB
images/aers-causal-models-poster-philosophy.md2.4 kB
images/skill-s1-Python生态-chart02.svg5.0 kB
images/skill-s1-工具对比-chart01.svg6.0 kB
images/skill-s2-方法图谱-chart01.svg5.5 kB
images/skill-s3-AI工具-chart01.svg8.8 kB
images/skill-s4-数据流程-chart01.svg6.8 kB
images/skill-s6-路线图-chart01.svg4.1 kB
images/star-history-dark.svg20.7 kB
images/star-history.svg20.7 kB
plugins/build_plugins.py7.4 kB
scripts/build-benchmark-scoreboard.py13.8 kB
scripts/build-catalog-enrich.py28.5 kB

Not in the download

The first 100 are named here, those the skill reads first. Too deep is past six folders and not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

demo-StatsPAI-skill/figures/fig1_education_by_proximity.pngread · not carried
demo-StatsPAI-skill/figures/fig2a_first_stage_binscatter.pngread · not carried
demo-StatsPAI-skill/figures/fig2b_mincer.pngread · not carried
demo-StatsPAI-skill/figures/fig3_coefplot_main.pngread · not carried
demo-StatsPAI-skill/figures/fig4a_cate_hist.pngread · not carried
demo-StatsPAI-skill/figures/fig4b_cate_by_group.pngread · not carried
demo-StatsPAI-skill/figures/fig5_spec_curve.pngread · not carried
demo-StatsPAI-skill/figures/fig5b_robustness_forest.pngread · not carried
demo-StatsPAI-skill/figures/fig6_sensitivity_dashboard.pngread · not carried
demo-StatsPAI-skill/replication/paper.docxread · not carried
demo-StatsPAI-skill/tables/table1_summary.docxread · not carried
demo-StatsPAI-skill/tables/table1_summary.xlsxread · not carried
demo-StatsPAI-skill/tables/table2_main_ols.docxread · not carried
demo-StatsPAI-skill/tables/table2_main_ols.xlsxread · not carried
demo-StatsPAI-skill/tables/table2b_iv_triplet.docxread · not carried
demo-StatsPAI-skill/tables/table2b_iv_triplet.xlsxread · not carried
demo-StatsPAI-skill/tables/table2c_design_horserace.docxread · not carried
demo-StatsPAI-skill/tables/table2c_design_horserace.xlsxread · not carried
demo-StatsPAI-skill/tables/table2d_multi_outcome.docxread · not carried
demo-StatsPAI-skill/tables/table2d_multi_outcome.xlsxread · not carried
demo-StatsPAI-skill/tables/table3_heterogeneity.docxread · not carried
demo-StatsPAI-skill/tables/table3_heterogeneity.xlsxread · not carried
demo-StatsPAI-skill/tables/table3b_interactions.docxread · not carried
demo-StatsPAI-skill/tables/table3b_interactions.xlsxread · not carried
demo-StatsPAI-skill/tables/tableA1_robustness.docxread · not carried
demo-StatsPAI-skill/tables/tableA1_robustness.xlsxread · not carried
demo-notebooks/_manuscript_docx_demo/04_results/fig3_coefplot.pngread · not carried
demo-notebooks/_manuscript_docx_demo/09_submission/main.docxread · not carried
demo-notebooks/_python_pipeline_outputs/figures/fig2c2_overlap.pngread · not carried
demo-notebooks/_python_pipeline_outputs/figures/fig2c_love_plot.pngread · not carried
demo-notebooks/_python_pipeline_outputs/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_python_pipeline_outputs/figures/fig5_spec_curve.pngread · not carried
demo-notebooks/_r_pipeline_outputs/figures/fig2c2_overlap.pngread · not carried
demo-notebooks/_r_pipeline_outputs/figures/fig2c_love_plot.pngread · not carried
demo-notebooks/_r_pipeline_outputs/figures/fig5_spec_curve.pngread · not carried
demo-notebooks/_r_pipeline_outputs_5.2/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_r_pipeline_outputs_5.2/tables/table2_main.docxread · not carried
demo-notebooks/_r_pipeline_outputs_5.2/tables/table2_main.xlsxread · not carried
demo-notebooks/_stata_lalonde_outputs/figures/fig2c2_overlap.pngread · not carried
demo-notebooks/_stata_lalonde_outputs/figures/fig5_spec_curve.pngread · not carried
demo-notebooks/_stata_lalonde_outputs/tables/tableA1_robustness.docxread · not carried
demo-notebooks/_stata_lalonde_outputs/tables/tableA1_robustness.xlsxread · not carried
demo-notebooks/_stata_lalonde_outputs_v5.2/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_stata_lalonde_outputs_v5.2/tables/table2_main.docxread · not carried
demo-notebooks/_stata_lalonde_outputs_v5.2/tables/table2_main.xlsxread · not carried
demo-notebooks/_stata_lalonde_outputs_v5.2/tables/tableA1_robustness.docxread · not carried
demo-notebooks/_stata_lalonde_outputs_v5.2/tables/tableA1_robustness.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig1_distributions.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig2c2_overlap.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig2c_love_plot.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig5_robustness_forest.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig5b_spec_curve.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs/figures/fig8_final_result.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/figures/fig5_robustness_forest.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/replication/paper.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table1_summary.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table1_summary.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table2_main.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table2_main.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table3_heterogeneity.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/table3_heterogeneity.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/tableA1_robustness.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_5.2/tables/tableA1_robustness.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig1_distributions.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig2c2_overlap.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig2c_love_plot.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig3_coefplot.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig4_cate.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig4b_cate_by_group.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig5_robustness_forest.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/figures/fig5b_spec_curve.pngread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/replication.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/replication.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table1_summary.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table1_summary.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table2_main.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table2_main.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table2b_design_race.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table2b_design_race.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table3_heterogeneity.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/table3_heterogeneity.xlsxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/tableA1_robustness.docxread · not carried
demo-notebooks/_statspai_pipeline_outputs_v2/tables/tableA1_robustness.xlsxread · not carried
skills/32-dylantmoore-stata-skill/plugins/stata-c-plugins/skills/stata-c-plugins/SKILL.mdread · too deep
skills/32-dylantmoore-stata-skill/plugins/stata-skill-contributor/skills/stata-skill-contributor/SKILL.mdread · too deep
skills/32-dylantmoore-stata-skill/plugins/stata/skills/stata/SKILL.mdread · too deep
skills/33-Galaxy-Dawn-claude-scholar/skills/ml-paper-writing/references/knowledge/README.mdread · too deep
skills/33-Galaxy-Dawn-claude-scholar/skills/ml-paper-writing/templates/aaai2026/README.mdread · too deep
skills/33-Galaxy-Dawn-claude-scholar/skills/ml-paper-writing/templates/acl/README.mdread · too deep
skills/33-Galaxy-Dawn-claude-scholar/skills/ml-paper-writing/templates/colm2025/README.mdread · too deep
skills/33-Galaxy-Dawn-claude-scholar/skills/ml-paper-writing/templates/neurips2025/main.texread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/algorithm-visualizer-guide/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/bokeh-visualization-guide/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/chart-image-generator/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/color-accessibility-guide/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/d3-visualization-guide/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/echarts-visualization-guide/SKILL.mdread · too deep
skills/43-wentorai-research-plugins/skills/analysis/dataviz/geospatial-viz-guide/SKILL.mdread · too deep

What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 14 scripts beside the text, so the download is 122 files — not the whole of its source: at least 4,093 files are left out, and the skill reads 100 of them. The first 100 are listed under the files, with why. The CC-BY-SA-4.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Auto-Empirical Research Skills Router · 970.8k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
  curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/auto-empirical-research-skills-router/bundle.tar.gz &&
  tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/auto-empirical-research-skills-router" ] &&
  { [ ! -e .claude/skills/auto-empirical-research-skills-router ] || { mv .claude/skills/auto-empirical-research-skills-router "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
  mv "$t/auto-empirical-research-skills-router" .claude/skills/ && echo "Installed .claude/skills/auto-empirical-research-skills-router"

On Windows, or any OS with Node 20+

npx mcprush@latest skill add brycewang-stanford/auto-empirical-research-skills-router

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/auto-empirical-research-skills-router/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/auto-empirical-research-skills-router/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/auto-empirical-research-skills-router" ] && { [ ! -e ~/.claude/skills/auto-empirical-research-skills-router ] || { mv ~/.claude/skills/auto-empirical-research-skills-router "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/auto-empirical-research-skills-router" ~/.claude/skills/ && echo "Installed ~/.claude/skills/auto-empirical-research-skills-router" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/auto-empirical-research-skills-router/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as auto-empirical-research-skills in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, auto-empirical-research-skills-router. Not in this download: at least 4,093 files of its source, 100 of them read by its SKILL.md or scripts (the list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/

Claude DesktopCustomize › Skills

ChatGPTSkills › Create › Upload

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok Build.grok/skills/

Microsoft CopilotSkills › Upload a skill

PerplexityComputer › Skills › Upload a skill

DeepSeek Harness.dsh/skills/

Zed.agents/skills/

Devin Desktop.devin/skills/

Windsurf (legacy).windsurf/skills/

OpenAI Agents SDKInstructions or sandbox Skills

HTTP / APIa request parameter

This release

Versionnot versioned

Publishedno release date on file

PriceFree

Referencebrycewang-stanford/auto-empirical-research-skills-router

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

brycewang-stanford

Publishes on mcprush.

0 servers listed3591 skills listednot claimed

Profile

Publisher

Servers0

Claim this skill