scdenney/open-science-skills
38 skills
$npx skills add scdenney/open-science-skillsSkillInstalls
46-orchestrateOrchestrate complex work as the Codex lead on the GPT-5.6 family. Default — a gpt-5.6-sol lead at xhigh effort owns decomposition, integration, and verification; it routes bounded work down to gpt-5.6advisorConsult this library's independent GPT-5.6 advisor before committing to a substantive interpretation, approach, or final result. Always gpt-5.6-sol at xhigh (Extra high) effort — the flagship 5.6 tiercitation-checkAudit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.conjoint-cleaningClean and reshape Qualtrics conjoint exports to analysis-ready long format.conjoint-designDesign conjoint experiments covering attributes, power, and AMCE/AMIE estimation. Use for conjoint design choices, attribute tables, estimands, and power planning.conjoint-diagnosticsDiagnose conjoint design integrity, estimation choices, and validity.cross-national-designDesign cross-national survey experiments covering power, equivalence, and localization. Use for multi-country sampling, measurement comparability, and instrument adaptation.divergeBefore implementing, generate 3-5 conceptually distinct approaches labeled by creativity dimension (Novel, Surprising, Diverse, Conventional), then hold for selection. Brainstorm-then-select to resistdiverge-codexDelegate creative divergence to a fresh Codex subagent before implementation. Use when the user explicitly asks Codex to delegate brainstorming, obtain an independent Codex context, or keep implementafable-orchestrateRun a multi-model orchestration workflow led by Fable 5, the strongest model on the team. The Fable lead does the hard reasoning and the judgment calls itself; it delegates mechanical work (boilerplatfact-checkFact-check manuscript claims against cited sources in a per-source Markdown knowledge base. Use to audit claim support, overclaiming, direction, scope, and misattribution after source intake is complefair-checkAudit manuscript and replication package against FAIR open-science principles.figure-table-auditAudit figures, tables, captions, cross-references, and statistical notes.figuresDesign and format publication-quality figures. Use for chart choice, color, scales, legends, captions, accessibility, and reproducible figure workflows.hypothesis-buildingBuild falsifiable causal hypotheses. Use for DAGs, FPCI, equivalence testing, mechanism specification, and deriving testable predictions from theory.journal-reviewDraft a senior peer-review report on a social-science manuscript.list-experimentDesign and diagnose list experiments (item count technique).literature-reviewBuild or audit a literature review. Use for evidence maps, gap analysis, contribution checks, source verification, and synthesis planning.llm-calibration-logprobsAnalyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.methods-reportingCheck methods reporting against CONSORT, JARS, DA-RT standards.model-committeeRun a deliberative two-model committee between GPT-5.6 "Sol" and Claude Opus 4.8. Use when the user needs one consequential decision from multiple defensible options and wants the two model families tmodel-committee-fableRun a deliberative two-model committee between GPT-5.6 "Sol" and Claude Opus 4.8, chaired by Fable 5. Same two deliberating members as model-committee; the difference is the chair — Fable 5 aggregatesmodel-committee-solRun a deliberative two-model committee between GPT-5.6 "Terra" and Claude Opus 4.8, chaired by GPT-5.6 "Sol." Same two deliberating members as model-committee; the difference is the chair — Sol aggregmodel-council-votingLLM council/panel voting: multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error diagnostics.narrative-buildingDraft or audit scientific introductions. Use for argument logic, framing, contribution structure, and coherence across multiple studies or experiments.paper-review-liteRun a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.paper-review-lite-codexRun 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-mopaper-texTypeset 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, anonymizpost-ocr-cleanupClean post-OCR research text. Use for correction, quality assurance, multilingual handling, uncertainty preservation, and provenance-aware cleanup.pre-registration-writingWrite pre-analysis plans and preregistrations. Use for PAP structure, registry requirements, estimands, analysis strategy, exclusions, and deviation planning.replication-packageScaffold 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, research-repoScaffold 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}survey-designDesign survey instruments. Use for question wording, scales, flow, pretesting, respondent burden, and social-desirability mitigation.tablesDesign and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.text-classificationDesign and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics, and reporting model-coded data.topic-modelingDesign and diagnose structural topic models. Use for STM specification, topic-count selection, coherence-exclusivity tradeoffs, validation, and interpretation.vlm-ocr-evaluationCompare OCR systems before a bulk run: candidate set, stratified ground truth, CER/WER, normalization, per-language and per-stratum accuracy.vlm-ocr-pipelineDesign VLM-based OCR pipelines. Use for model selection, prompting, architecture, multilingual documents, structured output, and evaluation planning.