Social Science Research

Plugin social-science-research in Felpix-Studios/social-science-research-codex. Commands read from the repo's manifest — 1 month ago.

Skills (14)

• data-analysis

  End-to-end empirical data analysis workflow for R or Python projects.

• data-finder

  Find and assess datasets for a research question.

• deep-audit

  Repository-wide consistency audit for skills, hooks, rules, and docs.

• lit-review

  Systematic literature review workflow using parallel librarian agents.

• new-project

  Structured interview and project-spec workflow for new research ideas.

• proofread

  Proofreading workflow for academic manuscripts and papers.

• quality-gate

  Verify that paper claims match analysis outputs before submission.

• research-setup

  Configure field, institution, datasets, journals, and project metadata.

• review-paper

  Substantive referee-style review for academic manuscripts.

• review-r

  Review existing R analysis code for quality and reproducibility.

• revise-paper

  Apply revisions from a review report to a manuscript.

• session-log

  Create or update a session log to capture decisions, changes, and progress.

• validate-bib

  Check bibliography completeness against citations in project files.

• write-paper

  Draft an academic paper from analysis outputs and project materials.

Subagents (9)

• adversarial-reviewer

  Hostile-referee stress test for papers. Not balanced critique — actively tries to kill the paper by finding fatal flaws, over-claims, unaddressed confounders, and identification weaknesses. Use before submission to pressure-test the argument against the strongest possible attack.

• domain-reviewer

  Substantive domain review for papers and analyses. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, logical consistency, and design-specific diagnostic reporting. Use after content is drafted or before presenting or submitting.

• explorer-critic

  Dataset assessor for the data-finder skill. Applies a 5-point critique to each dataset proposed by the Explorer agent — measurement validity, sample selection, external validity, identification compatibility, and known issues. Adjusts feasibility grades and flags deal-breakers.

• explorer

  Dataset finder for the data-finder skill. Searches across public microdata, administrative data, survey panels, international sources, and novel alternatives. Returns a graded list of candidate datasets for a given research question. Dispatched in parallel pairs by data-finder.

• fresh-eyes-reviewer

  First-time reader perspective on a paper. Reads cold with no prior context — not the spec, not the lit review, not the analysis scripts — and reports what lands, what confuses, and what a reader walks away believing. Use to catch clarity problems authors cannot see because they know too much.

• librarian

  Parallel literature search agent. Searches one assigned angle — journals, working paper repositories, or citation chains — and returns a verified list of relevant papers with BibTeX. Dispatched in parallel by the lit-review skill.

• proofreader

  Expert proofreading agent for academic writing — manuscripts and papers. Reviews for grammar, typos, layout issues, and consistency. Use proactively after creating or modifying any academic content.

• r-reviewer

  R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.

• verifier

  Analysis verification agent. Checks that scripts run cleanly, output files exist and are non-empty, and bibliography is consistent with the manuscript. Use before presenting results to collaborators or submitting work.

Similar plugins