Menu
Skills in this repository
SkillsMP has collected 84 skills from scdenney/open-science-skills. Open a skill to review its source and details.
scdenney/open-science-skillsShowing 40 of 84 collected skills.
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…
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…
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…
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,…
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…
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
LLM council/panel voting — multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error diagnostics.
LLM-based text classification. Codebook, validation, agreement statistics.
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…
VLM-based OCR pipeline. Model selection, prompts, architecture, evaluation.
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…
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.
Design and diagnose list experiments (item count technique).
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…
Draft a senior peer-review report on a social-science manuscript.
Pre-submission audit. Argument, numerics, refs, writing, figures, replication.
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.
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…
Run the standalone presubmit CLI. Adversarial 30+ stage peer-review pipeline.
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…
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…
Design conjoint experiments. Attributes, power, AMCE/AMIE estimation.
Design cross-national survey experiments. Power, equivalence, localization.
Build falsifiable causal hypotheses. DAGs, FPCI, equivalence testing.
Clean post-OCR text. Correction, QA, multilingual handling, provenance.
Write pre-analysis plans. PAP structure, registry, analysis strategy.
Design survey instruments. Questions, scales, flow, social desirability.
Structural topic modeling. STM spec, topic count, coherence-exclusivity.
Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.
Clean and reshape Qualtrics conjoint exports to analysis-ready long format.
Audit manuscript and replication package against FAIR open-science principles.
Audit figures, tables, captions, cross-references, and statistical notes.
Design and format publication-quality figures. Use for chart choice, color, scales, legends, captions, accessibility, and reproducible figure workflows.
Build or audit a literature review. Use for evidence maps, gap analysis, contribution checks, source verification, and synthesis planning.
Write pre-analysis plans and preregistrations. Use for PAP structure, registry requirements, estimands, analysis strategy, exclusions, and deviation planning.
Design survey instruments. Use for question wording, scales, flow, pretesting, respondent burden, and social-desirability mitigation.
Design and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.
Design and diagnose structural topic models. Use for STM specification, topic-count selection, coherence-exclusivity tradeoffs, validation, and interpretation.
Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.
Clean and reshape Qualtrics conjoint exports to analysis-ready long format.