External pipelines · RISE project catalogue
Auto-Empirical Research Skills (AERS)
A Claude-plugin-structured mega-catalog of agent skills for empirical social-science research: 74 collections / 1,094 vendored skills — 7 first-party Stanford REAP × CoPaper.AI collections (including the StatsPAI causal engine and the Paper-WorkFlow meta-orchestrator) plus 67 curated, security-audited community collections — spanning topic refinement, literature review, data acquisition, identification strategy, estimation (Python/Stata/R), robustness audit, publication tables, writing, review simulation, AI-trace removal, and journal submission. The headline "23,000+ skills" refers to an accompanying awesome-list map of 119 ecosystem repos; the vendored, cataloged content is 1,094 skills.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Bryce Wang
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
The largest empirical-social-science skills distribution in the catalog, and unusually serious about verification for a skills list: a numeric benchmark of 17 tasks whose gold values are recomputed from real data each run (encoding classic traps such as the LaLonde naive-ATT sign flip and Card IV recovery), a behavioral eval harness (37 scenarios / 183 rubric items), per-skill provenance and license audits in catalog JSON, and a root SKILL.md router so 1,094 skills are dispatched without flooding context. Vendors several standalone entries of this catalog (clo-author, academic-research-skills) as collections.
- Focus
- end-to-end
- Inputs
- research-topic, user-dataset, paper-draft
- Outputs
- paper-draft, analysis-code, publication-tables, figures, replication-audit-report
- Architecture
- tool-use, artifact-versioning
- Maintained by
- Bryce Wang (Stanford REAP / CoPaper.AI)
- Started
- 2026
Description
Data model- Discipline
- Social sciences
- Method family
- not specified
- Design
- not specified
- Research stage
- Research questionLiterature discoveryLiterature synthesisData acquisitionResearch designData analysisCode generationReplicationDraftingRevision and editingReviewDissemination
- Contributors
- Bryce Wang
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:auto-empirical-research-skills · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.