# brycewang-stanford/auto-empirical-research-skills architecture

> Architecture diagram of the GitHub repository brycewang-stanford/auto-empirical-research-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-12). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/brycewang-stanford/auto-empirical-research-skills
- Repository: https://github.com/brycewang-stanford/auto-empirical-research-skills

## Overview

AERS is a catalog of agent-facing empirical-research skills, presented as a human-interruptible workflow from research idea to submission. The README documents the end-to-end stages; source excerpts also show a numeric benchmark scorer, a rubric-based skill evaluation harness, and a specification-search tool for auditing p-hacking. Workflow links below reflect the README’s documented sequence; implementation-level links are limited to relationships visible in the supplied excerpts or source index.

Main entry points: [`skills/73-brycewang-p-hacking-skills/scripts/phack/search.py`](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/search.py) (Specification search), [`skills/33-Galaxy-Dawn-claude-scholar`](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/33-Galaxy-Dawn-claude-scholar) (Topic refinement), [`skills/68-research-productivity-skills`](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/68-research-productivity-skills) (Literature review), [`skills/67-econfin-workflow-toolkit`](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/67-econfin-workflow-toolkit) (Data acquisition)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Research workflow"]
  node_ideation["Topic refinement"]
  node_literature["Literature review"]
  node_data["Data acquisition"]
  node_identification["Identification strategy"]
  node_estimation["Estimation modeling"]
  node_robustness["Robustness audit"]
  node_presentation["Tables and figures"]
  node_writing["Writing and review"]
  node_provenance["AI-text reduction"]
  node_submission["Journal submission"]
end

subgraph group_skills["Skill capabilities"]
  node_skill_catalog["Agent skill catalog"]
end

subgraph group_assurance["Evaluation and rigor"]
  node_eval_runner["Rubric evaluation<br/>[run_evals.py]"]
  node_rubric_checks["Automated checks<br/>[checks.py]"]
  node_score_cli["Benchmark scorer<br/>[cli.py]"]
  node_exam["Exam discovery and grading<br/>[exam.py]"]
end

subgraph group_analysis["Analysis tools"]
  node_search["Specification search<br/>[search.py]"]
  node_grid["Analysis design grid<br/>[grid.py]"]
  node_procedures["Search procedures<br/>[procedures.py]"]
end

node_researcher(("Researcher or agent"))

node_researcher -->|"requests work"| node_skill_catalog
node_skill_catalog -->|"offers skills"| node_ideation
node_ideation -->|"refines into review"| node_literature
node_literature -->|"informs data search"| node_data
node_data -->|"supports design"| node_identification
node_identification -->|"guides estimation"| node_estimation
node_estimation -->|"feeds audit"| node_robustness
node_robustness -->|"informs reporting"| node_presentation
node_presentation -->|"supports writing"| node_writing
node_writing -->|"continues through"| node_provenance
node_provenance -->|"prepares submission"| node_submission
node_eval_runner -->|"runs checks"| node_rubric_checks
node_score_cli -->|"loads exam"| node_exam
node_search -->|"uses grid"| node_grid
node_search -.->|"runs procedure"| node_procedures

click node_ideation "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/33-Galaxy-Dawn-claude-scholar"
click node_literature "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/68-research-productivity-skills"
click node_data "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/67-econfin-workflow-toolkit"
click node_identification "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/50-brycewang-aer-skills/templates/python"
click node_estimation "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/demo-notebooks/statsPAI_pipeline_5.2.py"
click node_robustness "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/73-brycewang-p-hacking-skills/scripts/phack"
click node_presentation "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/50-brycewang-aer-skills/templates/python"
click node_writing "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/35-bahayonghang-academic-writing-skills"
click node_provenance "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/48-de-AIGC-skills/scripts/provenance_scrub.py"
click node_submission "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/67-econfin-workflow-toolkit/paper-submission"
click node_skill_catalog "https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills"
click node_eval_runner "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/eval-harness/run_evals.py"
click node_rubric_checks "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/eval-harness/lib/checks.py"
click node_score_cli "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/aers_score/cli.py"
click node_exam "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/aers_score/exam.py"
click node_search "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/search.py"
click node_grid "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/grid.py"
click node_procedures "https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/procedures.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_ideation,node_literature,node_data,node_identification,node_estimation,node_robustness,node_presentation,node_writing,node_provenance,node_submission toneBlue
class node_skill_catalog toneAmber
class node_eval_runner,node_rubric_checks,node_score_cli,node_exam toneMint
class node_search,node_grid,node_procedures toneRose
class node_researcher toneIndigo
```

## Components

### Research workflow

- [Topic refinement](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/33-Galaxy-Dawn-claude-scholar): `skills/33-Galaxy-Dawn-claude-scholar`
- [Literature review](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/68-research-productivity-skills): `skills/68-research-productivity-skills`
- [Data acquisition](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/67-econfin-workflow-toolkit): `skills/67-econfin-workflow-toolkit`
- [Identification strategy](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/50-brycewang-aer-skills/templates/python): `skills/50-brycewang-aer-skills/templates/python`
- [Estimation modeling](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/demo-notebooks/statsPAI_pipeline_5.2.py): `demo-notebooks/statsPAI_pipeline_5.2.py`
- [Robustness audit](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/73-brycewang-p-hacking-skills/scripts/phack): `skills/73-brycewang-p-hacking-skills/scripts/phack`
- [Tables and figures](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/50-brycewang-aer-skills/templates/python): `skills/50-brycewang-aer-skills/templates/python`
- [Writing and review](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/35-bahayonghang-academic-writing-skills): `skills/35-bahayonghang-academic-writing-skills`
- [AI-text reduction](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/48-de-AIGC-skills/scripts/provenance_scrub.py): `skills/48-de-AIGC-skills/scripts/provenance_scrub.py`
- [Journal submission](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills/67-econfin-workflow-toolkit/paper-submission): `skills/67-econfin-workflow-toolkit/paper-submission`

### Skill capabilities

- [Agent skill catalog](https://github.com/brycewang-stanford/auto-empirical-research-skills/tree/main/skills): `skills`

### Evaluation and rigor

- [Rubric evaluation](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/eval-harness/run_evals.py): `eval-harness/run_evals.py`
- [Automated checks](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/eval-harness/lib/checks.py): `eval-harness/lib/checks.py`
- [Benchmark scorer](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/aers_score/cli.py): `aers_score/cli.py`
- [Exam discovery and grading](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/aers_score/exam.py): `aers_score/exam.py`

### Analysis tools

- [Specification search](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/search.py): `skills/73-brycewang-p-hacking-skills/scripts/phack/search.py`
- [Analysis design grid](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/grid.py): `skills/73-brycewang-p-hacking-skills/scripts/phack/grid.py`
- [Search procedures](https://github.com/brycewang-stanford/auto-empirical-research-skills/blob/main/skills/73-brycewang-p-hacking-skills/scripts/phack/procedures.py): `skills/73-brycewang-p-hacking-skills/scripts/phack/procedures.py`

### Other components

- **Researcher or agent**

## Connections

- Researcher or agent → Agent skill catalog: requests work (evidence: `README.md`)
- Agent skill catalog → Topic refinement: offers skills (evidence: `README.md`)
- Topic refinement → Literature review: refines into review (evidence: `README.md`)
- Literature review → Data acquisition: informs data search (evidence: `README.md`)
- Data acquisition → Identification strategy: supports design (evidence: `README.md`)
- Identification strategy → Estimation modeling: guides estimation (evidence: `README.md`)
- Estimation modeling → Robustness audit: feeds audit (evidence: `README.md`)
- Robustness audit → Tables and figures: informs reporting (evidence: `README.md`)
- Tables and figures → Writing and review: supports writing (evidence: `README.md`)
- Writing and review → AI-text reduction: continues through (evidence: `README.md`)
- AI-text reduction → Journal submission: prepares submission (evidence: `README.md`)
- Rubric evaluation → Automated checks: runs checks (evidence: `eval-harness/run_evals.py`)
- Benchmark scorer → Exam discovery and grading: loads exam (evidence: `aers_score/cli.py`)
- Specification search → Analysis design grid: uses grid (evidence: `skills/73-brycewang-p-hacking-skills/scripts/phack/search.py`)
- Specification search → Search procedures: runs procedure (evidence: `skills/73-brycewang-p-hacking-skills/scripts/phack/procedures.py`)