메뉴
이 저장소의 skills
SkillsMP는 scdenney/open-science-skills에서 84개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
scdenney/open-science-skills수집된 skill 84개 중 40개를 표시합니다.
Drafts or audits the introduction and framing of a scientific paper — the motivating real-world "why", the evidence audit, the funnel from theory to a falsifiable if-then with a named estimand, bridges between multiple experiments, and a contribution list…
원문 언어: 영어
Designs and formats publication-quality figures for social-science manuscripts — chart type, scales, color, legend order, self-contained captions, and script-based reproducibility. Use when the user is making, revising, or critiquing a figure for a paper — a…
원문 언어: 영어
Builds or audits a literature review — evidence map, closest prior work, source clusters, gap verdict, and a synthesis plan that feeds the introduction. Use when the user asks whether a contribution is novel, who else has studied a question, what the…
원문 언어: 영어
Typeset a working paper or journal submission in house-style LaTeX from any draft — Markdown, Word (.docx), TeX, ODT, RTF, or HTML. Convert with pandoc, wrap in an EB Garamond template, build the PDF with latexmk, and prepare for a specific journal (spacing,…
원문 언어: 영어
Designs and formats publication-quality tables for social-science manuscripts — column order, row grouping and panels, decimal precision, standard-error versus confidence-interval conventions, self-contained titles and notes, and code-generated output. Use…
원문 언어: 영어
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
원문 언어: 영어
LLM council/panel voting — multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error diagnostics.
원문 언어: 영어
LLM-based text classification. Codebook, validation, agreement statistics.
원문 언어: 영어
Compare OCR systems before committing to a bulk run. Covers the candidate set, stratified ground truth, CER/WER scoring, normalization decisions, and per-language and per-stratum accuracy. Use as the selection gate before vlm-ocr-pipeline, whenever the…
원문 언어: 영어
VLM-based OCR pipeline. Model selection, prompts, architecture, evaluation.
원문 언어: 영어
Delegate creative divergence to Codex (GPT-5.6 "Sol" at xhigh effort). Codex generates 3-5 conceptually distinct approaches before any implementation; Claude presents them for selection, then has Codex implement the chosen one. Cross-model…
원문 언어: 영어
Cross-model adversarial pre-submission audit. Claude and Codex independently apply the paper-review-lite specification, then each cross-checks the other's findings; surviving issues are annotated by confidence.
원문 언어: 영어
Design and diagnose list experiments (item count technique).
원문 언어: 영어
Fact-check a manuscript's claims against the cited sources themselves. Locate each source's knowledge-base Markdown file and verify the in-text claim is actually supported. Runs a pre-flight gate that refuses unless a per-source Markdown knowledge base exists…
원문 언어: 영어
Draft a senior peer-review report on a social-science manuscript.
원문 언어: 영어
Pre-submission audit. Argument, numerics, refs, writing, figures, replication.
원문 언어: 영어
Before implementing, generate 3-5 conceptually distinct approaches labeled by creativity dimension (Novel, Surprising, Diverse, Conventional), then hold for selection. Brainstorm-then-select to resist defaulting to the most obvious solution.
원문 언어: 영어
Plan a research project as a decision map that outlives any single session — a destination (a defensible, pre-registerable design) reached by resolving decision tickets of four kinds, one at a time. Adapted for research from Matt Pocock's wayfinder. The map…
원문 언어: 영어
Run the standalone presubmit CLI. Adversarial 30+ stage peer-review pipeline.
원문 언어: 영어
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…
원문 언어: 영어
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…
원문 언어: 영어
Design conjoint experiments. Attributes, power, AMCE/AMIE estimation.
원문 언어: 영어
Design cross-national survey experiments. Power, equivalence, localization.
원문 언어: 영어
Build falsifiable causal hypotheses. DAGs, FPCI, equivalence testing.
원문 언어: 영어
Clean post-OCR text. Correction, QA, multilingual handling, provenance.
원문 언어: 영어
Write pre-analysis plans. PAP structure, registry, analysis strategy.
원문 언어: 영어
Design survey instruments. Questions, scales, flow, social desirability.
원문 언어: 영어
Structural topic modeling. STM spec, topic count, coherence-exclusivity.
원문 언어: 영어
Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.
원문 언어: 영어
Clean and reshape Qualtrics conjoint exports to analysis-ready long format.
원문 언어: 영어
Audit manuscript and replication package against FAIR open-science principles.
원문 언어: 영어
Audit figures, tables, captions, cross-references, and statistical notes.
원문 언어: 영어
Design and format publication-quality figures. Use for chart choice, color, scales, legends, captions, accessibility, and reproducible figure workflows.
원문 언어: 영어
Build or audit a literature review. Use for evidence maps, gap analysis, contribution checks, source verification, and synthesis planning.
원문 언어: 영어
Write pre-analysis plans and preregistrations. Use for PAP structure, registry requirements, estimands, analysis strategy, exclusions, and deviation planning.
원문 언어: 영어
Design survey instruments. Use for question wording, scales, flow, pretesting, respondent burden, and social-desirability mitigation.
원문 언어: 영어
Design and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.
원문 언어: 영어
Design and diagnose structural topic models. Use for STM specification, topic-count selection, coherence-exclusivity tradeoffs, validation, and interpretation.
원문 언어: 영어
Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.
원문 언어: 영어
Clean and reshape Qualtrics conjoint exports to analysis-ready long format.
원문 언어: 영어