Open-source repos
Auto-Empirical Research Skills (AERS)
Connect empirical identification, analysis planning and replication delivery
This page provides source information and editorial guidance. Recommendations and trust labels do not mean every skill here was tested. Results for individual skills are on the skill data pages. See skill data · Listing policy
Overview
SkillFlux selected preregistration, identification and replication from the MIT-licensed AER-skills subcollection within AERS. These skills connect research questions to estimands, analysis plans, diagnostics and replication packages. The selection also preserves robustness, StatsPAI and tables/figures support skills with required templates, shared scripts, references and examples.
SkillFlux sample check
On 2026-10-31, SkillFlux pinned this source at commit 8dd077b, drew a seeded sample of 20 from the 1250 entries it contains, and ran static health check 1.0.0 on each. 50% had no failing check, said when to use the skill and carried a license.
- 20/20sampled entries had a SKILL.md we could check
- 0/20fail at least one check
- 10/20do not say when to use the skill
- 0/20have no license we could find
- 2/20bundle scripts the agent may run
- 0/20include scripts that call the network
- 0/20include destructive shell commands
- 2/20exceed the 5,000-token body guideline
See the 20 sampled entries
The sample reads files only; it does not run any skill and does not describe entries outside the sample. Flags describe what a skill contains; they are not verdicts. Raw data · Method
What the skills help you do
Inputs, methods and outputs described in the collected source version.
Map the design to an identification strategy
aer-identification organizes DiD, IV, RDD, synthetic control and other branches around assignment, thresholds, policy timing or exogenous variation, with estimands, diagnostics and inference recorded.
Read the source instructions ↗Turn experimental decisions into an analysis plan
aer-preregistration provides a PAP outline covering hypotheses, primary outcomes, estimating equations, inclusion rules, power and multiplicity, supporting later comparison of the plan with deviations.
Read the source instructions ↗Plan checks around the main result
aer-robustness separates sensitivity to specifications, samples, outcome definitions and inference from heterogeneity, mechanism and placebo checks, making each check’s question explicit.
Read the source instructions ↗Connect manuscript results to replication files
aer-replication organizes provenance records, environment instructions, a master script and exhibit mappings so tables and figures can be traced to generating scripts and output files.
Read the source instructions ↗A typical workflow
State the question and data conditions
Describe assignment, available data, time structure and the target effect. Record identifying assumptions before choosing a method branch.
Record the plan and execution environment
Prepare an analysis plan for applicable experimental or prospective work and check statistical software, package versions and available external tools.
Run the analysis and retain diagnostics
Use the prepared environment for estimation and relevant checks, retaining results, exhibits, assumption changes and deviations from the plan.
Check replication from a clean environment
Rebuild outputs with the master script, check exhibit mappings and data provenance, and document runtime requirements, restricted-data access and unresolved issues.
Best for
- Empirical-economics researchers who need to specify identifying assumptions, estimators and diagnostic reports for an existing question.
- Teams preparing an experimental analysis plan or organizing data provenance, scripts and manuscript exhibits into a reproducible deliverable.
Use cases
- Planning & long tasks
- Coding & development
- Content & writing
SkillFlux notes
Main selections are aer-preregistration, aer-identification and aer-replication, supported by aer-robustness, aer-statspai and aer-tables-figures. This analysis of pinned instructions does not claim validated estimates or completed research registration.
Installation and use
Open the original repository and read its README, the selected skill instructions and any linked scripts. Check installation paths, host requirements, dependencies and licenses, then follow the project documentation to verify a small task in a workspace you can restore.
Read the original Auto-Empirical Research Skills (AERS) source
Limitations
- MIT applies to the selected AER-skills subcollection, while other sources in AERS have different terms. StatsPAI MCP, statistical software, data access and registration services are separate from the collected files.
- Templates and method branches are starting points to assess against the data and identifying assumptions. Completing a checklist cannot guarantee causal validity or journal acceptance; registration and submission requirements must be checked with the relevant platform and journal.
Alternatives
- Scientific Agent Skills
Compare the selected K-Dense brainstorming and critical-thinking skills when the task is still research ideation or evidence appraisal, before a specific empirical design.
- OthmanAdi/planning-with-files
Compare planning-with-files when the need is persistent research plans, findings and progress rather than statistical-method guidance.
Source links
- github.com/brycewang-stanford/Auto-Empirical-Research-Skills
- github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/9fa87d86e34d6c9a1c7cdb0db755c83c780537a0/README.md
- github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/9fa87d86e34d6c9a1c7cdb0db755c83c780537a0/LICENSE
- github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/9fa87d86e34d6c9a1c7cdb0db755c83c780537a0/docs/LICENSE_AUDIT.md