Skill Claude CodeCodex
Run a cross-model adversarial pre-submission audit from Codex. Use when a user explicitly requests the heavier paper-review-lite-codex workflow, independent Codex and Claude review passes, or cross-model verification of a manuscript. Apply the paper-review-lite protocol, cross-check findings against the manuscript…
Skill Claude CodeCodex
Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.
Skill Claude CodeCodex
Typeset a working paper or journal submission in house-style LaTeX from Markdown, Word, TeX, ODT, RTF, or HTML. Use to convert drafts, build PDFs, or prepare journal-specific spacing, limits, anonymization, disclosures, and citations.
Skill Claude CodeCodex
Clean post-OCR research text. Use for correction, quality assurance, multilingual handling, uncertainty preservation, and provenance-aware cleanup.
Skill Claude CodeCodex
Write pre-analysis plans and preregistrations. Use for PAP structure, registry requirements, estimands, analysis strategy, exclusions, and deviation planning.
Skill Claude CodeCodex
Operate a live Qualtrics survey via the v3 APIs without breaking fielding. Publish gating, quotas, flow routing, embedded data, panel-vendor redirects, and read-back verification.
Skill Claude CodeCodex
Scaffold or audit a social-science replication package at a target directory. Generates folder structure, README, master.R, figure/table crosswalk, codebook template, LICENSE placeholder, .gitignore, and pre-release checklist. Adapted from Yusaku Horiuchi's replication-package-guide with FAIR-principle integration…
Skill Claude CodeCodex
Scaffold or audit an entire research project repository organized around its source library. Use when starting, structuring, organizing, or reviewing a research repo. Build sources/{og,md,unprocessed}, references.bib, a PDF-to-Markdown converter, a repo-local process-source skill, AGENTS.md, .gitignore, .venv, and the…
Skill Claude CodeCodex
Plan a research project as a durable decision map, resolving one design decision per session until the destination is a defensible, pre-registerable design. Not for executing analyses or writing the paper. Use at the start of a project, when a design has more open decisions than one conversation holds, or when…
Skill Claude CodeCodex
Spawn full peer Codex or Claude sessions in their own panes and git worktrees — real sessions, not subagents — briefed by the lead and merged back. Not for bounded consults a subagent covers. Use when work must outlive or run beside this session, needs its own worktree, or must stay user-steerable.
Skill Claude CodeCodex
Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity. Emits an appendix-ready quality report.
Skill Claude CodeCodex
Design survey instruments. Use for question wording, scales, flow, pretesting, respondent burden, and social-desirability mitigation.
Skill Claude CodeCodex
Pre-fielding audit of a live survey over the platform API, with an optional browser walk. Consent-before-anything gates, publish state, force-response completeness, quotas, vendor redirects, anti-bot instrumentation, language-arm symmetry.
Skill Claude CodeCodex
Design and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.
Skill Claude CodeCodex
Design and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics, and reporting model-coded data.
Skill Claude CodeCodex
Design and diagnose structural topic models. Use for STM specification, topic-count selection, coherence-exclusivity tradeoffs, validation, and interpretation.
Skill Claude CodeCodex
Compare OCR systems before a bulk run: candidate set, stratified ground truth, CER/WER, normalization, per-language and per-stratum accuracy.
Skill Claude CodeCodex
Design VLM-based OCR pipelines. Use for model selection, prompting, architecture, multilingual documents, structured output, and evaluation planning.
Plugin Claude Code
Open Science Skills (oss). 43 Claude Code skills for experimental social science and computational text analysis (including fable-orchestrate and opus-orchestrate, general multi-model orchestration workflows led by Fable 5 or by Opus 5; advisor, a single independent-second-reviewer consult in which the calling session.
Command
Consult Fable 5 as an independent second reviewer, always at max reasoning effort regardless of what this session runs at. Your session is the main seat — Opus 5, or Sonnet 5 for cheaper sustained work — and Fable holds the advisor seat. Use before committing to an interpretation or a substantial piece of…
Command
Audit citation integrity for the task below. Check in-text/reference parity, DOI and URL status, author-year consistency, stale working papers, suspicious or unresolved sources, citation style, and whether key citations actually support the claims they are attached to.
Command
Apply conjoint data cleaning expertise to the task below. Cover the relevant aspects of Qualtrics column conventions, wide-to-long reshaping, choice variable mapping, attribute translation, pilot data detection, reference category selection, and validation based on what is needed.
Command
Apply conjoint experiment design expertise to the task below. Cover the relevant aspects of attribute architecture, statistical power, AMCE/AMIE estimation, design variants, and quality checks based on what is needed.
Command
Run a conjoint diagnostics review of the task or study described below. Evaluate design integrity, estimation choices, measurement error, external validity, and interpretation against the diagnostic checklist.