{"id":51223189,"url":"https://github.com/scdenney/open-science-skills","last_synced_at":"2026-07-07T12:02:15.239Z","repository":{"id":337642107,"uuid":"1139217934","full_name":"scdenney/open-science-skills","owner":"scdenney","description":"A library of Agentic Skills for Claude Code and LLM agents, codified from social science standards and methodological texts for doing experimental and other kinds of work.","archived":false,"fork":false,"pushed_at":"2026-06-26T10:03:55.000Z","size":5785,"stargazers_count":22,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-26T11:09:09.374Z","etag":null,"topics":["anthropic","claude-code","claude-code-skills","conjoint","experimental-research","fair","list-experiment","literature-review","manuscript-qa","methods-reporting","open-science","peer-review","pre-registration","social-science","survey-experiments","text-classification","topic-modeling"],"latest_commit_sha":null,"homepage":"","language":"Markdown","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/scdenney.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-21T17:14:13.000Z","updated_at":"2026-06-26T10:03:58.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/scdenney/open-science-skills","commit_stats":null,"previous_names":["scdenney/open-science-skills"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/scdenney/open-science-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scdenney%2Fopen-science-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scdenney%2Fopen-science-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scdenney%2Fopen-science-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scdenney%2Fopen-science-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/scdenney","download_url":"https://codeload.github.com/scdenney/open-science-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scdenney%2Fopen-science-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35226918,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-07T02:00:07.222Z","response_time":90,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anthropic","claude-code","claude-code-skills","conjoint","experimental-research","fair","list-experiment","literature-review","manuscript-qa","methods-reporting","open-science","peer-review","pre-registration","social-science","survey-experiments","text-classification","topic-modeling"],"created_at":"2026-06-28T09:00:31.118Z","updated_at":"2026-07-07T12:02:15.210Z","avatar_url":"https://github.com/scdenney.png","language":"Markdown","funding_links":[],"categories":["Source Catalog","Suites, Systems \u0026 Meta"],"sub_categories":["Discipline-Specific Packs"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/hero.jpg\" alt=\"Open Science Skills — vintage typewriter, globe, and books labeled Open Access, Collaboration, Transparency, Reproducibility, beneath a framed title sign.\" width=\"900\"\u003e\n\u003c/p\u003e\n\n# Open Science Skills\n\n[![Claude Code](https://img.shields.io/badge/Claude_Code-plugin-D97757?logo=anthropic\u0026logoColor=white)](https://code.claude.com/docs/en/skills)\n[![OpenAI Codex](https://img.shields.io/badge/OpenAI_Codex-library-111111?logo=openai\u0026logoColor=white)](codex/README.md)\n[![version](https://img.shields.io/badge/version-2.12.0-blue)](https://github.com/scdenney/open-science-skills/releases)\n[![license](https://img.shields.io/badge/license-CC%20BY--NC%204.0-lightgrey)](LICENSE)\n[![skills](https://img.shields.io/badge/skills-35-blue)](#skills)\n[![updated](https://img.shields.io/badge/updated-July%202026-green)](https://github.com/scdenney/open-science-skills/commits/main)\n[![sources](https://img.shields.io/badge/sources-150%2B-purple)](SOURCES.md)\n[![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen)](#contributing)\n\nReusable agent workflows for experimental social science, computational text analysis, manuscript QA, and transparent reporting. The same research methods are packaged natively for both Claude Code and OpenAI Codex.\n\n| Platform | Package | Invoke |\n|---|---|---|\n| [Claude Code](https://code.claude.com/docs/en/skills) | 35 skills in the [`oss` plugin](plugin/skills) | `/oss:skill-name` |\n| [OpenAI Codex](https://developers.openai.com/codex/skills) | 34 skills in the [`codex/` library](codex/README.md) | `$skill-name` |\n\nThe two libraries track each other closely. On the Codex side there is no `presubmit`.\n\nThis is the toolkit I use in my own research. It is built from a curated corpus of methodology texts and grows as I add new sources, ideas, and skills. Authoring and editing are mine, with help from Opus 4.8, Gemini 3.0, and ChatGPT 5.4.\n\nBoth libraries follow the official authoring guidance for [Claude Code](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices) and [Codex](https://developers.openai.com/codex/skills): procedural workflows over definitions, with trigger-rich descriptions and progressive disclosure. The methods stay aligned across platforms; only invocation and tooling adapt to each runtime.\n\n\u003e These skills support the research and writing process. They do not replace it. They follow APSA, JARS, DA-RT, TOP, and FAIR open-science expectations, and all guidance is grounded in 150+ published sources and documented workflow patterns. See [**SOURCES.md**](SOURCES.md) for the full bibliography.\n\n---\n\n## Contents\n\n[Skill Map](#skill-map) · [How Skills Work](#how-skills-work) · [Installation](#installation) · [Skills](#skills) · [Contributing](#contributing) · [License](#license)\n\n**Skills:** [Project Setup](#project-setup) · [Ideation](#ideation) · [Research Design](#research-design) · [Analysis](#analysis) · [Corpus Processing](#corpus-processing) · [Writing \u0026amp; Reporting](#writing--reporting) · [Figures \u0026amp; Tables](#figures--tables) · [Manuscript QA](#manuscript-qa) · [Review \u0026amp; Submission](#review--submission)\n\n---\n\n## Skill Map\n\n```mermaid\nflowchart LR\n    A[Research Design] --\u003e B[Analysis]\n    A --\u003e C[Writing and PAP]\n    B --\u003e D[Methods Reporting]\n    C --\u003e D\n    D --\u003e E[Manuscript QA and FAIR]\n    E --\u003e F[Review and Submission]\n\n    G[Ideation] --\u003e A\n    G --\u003e C\n\n    A -.-\u003e A1[conjoint / survey / list / cross-national]\n    B -.-\u003e B1[topic modeling / text classification / council voting / model committee / calibration / OCR + OCR eval]\n    C -.-\u003e C1[hypotheses / literature review / narrative / preregistration]\n    D -.-\u003e D1[figures / tables / methods reporting]\n    E -.-\u003e E1[FAIR / citations / fact-check / figure-table-audit / replication-package / archive checks]\n    F -.-\u003e F1[paper-tex / paper-review-lite / paper-review-lite-codex / presubmit / journal-review]\n    G -.-\u003e G1[diverge / diverge-codex / fable-orchestrate or 46-orchestrate]\n```\n\nUse the domain skills when designing or analyzing a study. Use the manuscript-QA skills when a draft exists and you need to check whether FAIR availability, citations, figures, tables, reporting, and replication materials can survive review.\n\n---\n\n## How Skills Work\n\nInvocation depends on the platform:\n\n| Platform | Implicit | Explicit | Source |\n|---|---|---|---|\n| Claude Code | Loads matching skills from prompt context | `/oss:skill-name` | [`plugin/skills/`](plugin/skills) |\n| Codex | Loads matching skills from their descriptions | `$skill-name` | [`codex/`](codex) |\n\nOrchestration and delegated-review variants require explicit invocation because they start subagents or external model calls.\n\n---\n\n## Installation\n\n### Claude Code\n\n#### Option 1 — Plugin (recommended, installs all skills + slash commands)\n\n**Permanent install** (user-wide, persists across all projects):\n\n```bash\n# Step 1: Register the marketplace (one-time)\nclaude plugin marketplace add scdenney/open-science-skills\n\n# Step 2: Install the plugin\nclaude plugin install oss@open-science-skills\n\n# Project-only install\nclaude plugin install oss@open-science-skills --scope project\n```\n\nThe plugin's slash-command prefix is `oss:` (short for **o**pen **s**cience **s**kills). The marketplace and GitHub repo are still named `open-science-skills`.\n\n**Session-only** (no install required, active for the current session):\n\n```bash\ngit clone https://github.com/scdenney/open-science-skills.git\ncd open-science-skills \u0026\u0026 claude --plugin-dir ./plugin\n```\n\nAll 35 skills auto-trigger based on your prompts. All 35 slash commands (`/oss:research-repo`, `/oss:conjoint-design`, `/oss:fair-check`, `/oss:figures`, `/oss:tables`, `/oss:paper-tex`, `/oss:figure-table-audit`, `/oss:replication-package`, and so on) are immediately available. The prefix can be omitted when no other installed plugin claims the same name.\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eOption 2 — Selective install\u003c/b\u003e (choose specific skills, auto-trigger only)\u003c/summary\u003e\n\nUse the interactive install script to pick only the skills you want:\n\n```bash\ngit clone https://github.com/scdenney/open-science-skills.git\ncd open-science-skills\nbash plugin/scripts/install.sh\n```\n\nThe script lists available skills and lets you choose interactively. Skills are installed to `./.claude/skills/` by default (current project only). Options:\n\n```bash\n# Install to user-wide skills directory (all projects)\nbash plugin/scripts/install.sh --target ~/.claude/skills\n\n# Install specific skills non-interactively\nbash plugin/scripts/install.sh --skill conjoint-design survey-design list-experiment\n\n# Install all skills\nbash plugin/scripts/install.sh --all --target ~/.claude/skills\n```\n\nRestart Claude Code after installing to load the new skills.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eOption 3 — Manual copy\u003c/b\u003e (single skill, auto-trigger only)\u003c/summary\u003e\n\n```bash\ngit clone https://github.com/scdenney/open-science-skills.git\n\n# Project-level (current project only) — copy the whole skill folder:\n# many skills ship reference/, assets/, or scripts/ files their SKILL.md points at\nmkdir -p your-project/.claude/skills\ncp -R open-science-skills/plugin/skills/conjoint-design \\\n   your-project/.claude/skills/\n\n# User-wide (all projects)\nmkdir -p ~/.claude/skills\ncp -R open-science-skills/plugin/skills/list-experiment ~/.claude/skills/\n```\n\n\u003e **Note:** Manual install gives you auto-trigger only. Slash commands (`/skill-name`) require the plugin.\n\n\u003c/details\u003e\n\n### Codex\n\nCodex discovers repository skills under `.agents/skills` and user-wide skills under `~/.agents/skills`. From the repository root, install all 34 native skills user-wide:\n\n```bash\nmkdir -p \"$HOME/.agents/skills\"\nfor skill in \"$PWD\"/codex/*/; do\n  ln -sfn \"${skill%/}\" \"$HOME/.agents/skills/$(basename \"$skill\")\"\ndone\n```\n\nFor selective and repository-scoped installation, plus the compact Codex catalog, see [`codex/README.md`](codex/README.md).\n\n---\n\n## Skills\n\nThe detailed catalog shows Claude Code commands by default. Platform-specific entries are labeled: **Codex** means a Codex-native skill, while **Claude Code → Codex** means a Claude Code skill that calls Codex. Unmarked research workflows also have counterparts in the [Codex catalog](codex/README.md), except for `presubmit`.\n\n### Project Setup\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/research-repo/SKILL.md\"\u003e\u003cstrong\u003eresearch-repo\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/research-repo\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eScaffold or audit a research project repository organized around its source library. For a new repo, build the \u003ccode\u003esources/{og,md,unprocessed}\u003c/code\u003e + \u003ccode\u003ereferences.bib\u003c/code\u003e spine (PDF to Markdown via \u003ca href=\"https://github.com/opendataloader-project/opendataloader-pdf\"\u003eOpenDataLoader PDF\u003c/a\u003e), a \u003ccode\u003eprocess-source\u003c/code\u003e intake command, \u003ccode\u003eCLAUDE.md\u003c/code\u003e/\u003ccode\u003eAGENTS.md\u003c/code\u003e, \u003ccode\u003e.gitignore\u003c/code\u003e, and the archetype-appropriate analysis/manuscript/review folders, then smoke-test the pipeline; for an existing repo, audit against the convention with detection recipes for orphan PDFs, bib drift, and naming. Pairs with \u003ccode\u003eprocess-source\u003c/code\u003e (per-PDF intake) and \u003ccode\u003ereplication-package\u003c/code\u003e (publication output).\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Workflow \u0026 Orchestration\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/fable-orchestrate/SKILL.md\"\u003e\u003cstrong\u003efable-orchestrate\u003c/strong\u003e\u003c/a\u003e\u003cbr\u003e\u003csub\u003eClaude Code\u003c/sub\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/fable-orchestrate\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eMulti-model orchestration with Fable 5 as tech lead. Routes reasoning-heavy work to a deep-reasoner subagent (Opus), mechanical work to a fast-worker subagent (Sonnet), and fresh-perspective or high-stakes work to Codex, a different-vendor GPT-5 peer. High-stakes tasks run Opus and Codex in parallel, then synthesize. Ships the two agent definitions and a \u003ccode\u003ecodex-peer.sh\u003c/code\u003e driver.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"codex/46-orchestrate/SKILL.md\"\u003e\u003cstrong\u003e46-orchestrate\u003c/strong\u003e\u003c/a\u003e\u003cbr\u003e\u003csub\u003eCodex\u003c/sub\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e$46-orchestrate\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eSol-led Codex orchestration for complex work. Routes bounded research, implementation, and verification to role-based subagents; uses blind parallel review for high-blast-radius work that is difficult to verify; and keeps planning, integration, and final accountability with the lead.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Ideation\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/diverge/SKILL.md\"\u003e\u003cstrong\u003ediverge\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/diverge\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eBrainstorm-then-select: before implementing, generate 3–5 conceptually distinct approaches labeled by creativity dimension ([Novel], [Surprising], [Diverse], [Conventional]) and hold for selection. Resists defaulting to the most obvious solution. After Creative Preference Optimization (Ismayilzada et al., 2025).\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/diverge-codex/SKILL.md\"\u003e\u003cstrong\u003ediverge-codex\u003c/strong\u003e\u003c/a\u003e\u003cbr\u003e\u003csub\u003eClaude Code → Codex\u003c/sub\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/diverge-codex\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eCross-model variant of \u003ccode\u003ediverge\u003c/code\u003e. Delegates the brainstorm to Codex (GPT-5.4) via \u003ccode\u003ecodex exec\u003c/code\u003e, presents its approaches for selection, then has Codex implement the chosen one. A second model family widens the space of approaches.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Research Design\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/conjoint-design/SKILL.md\"\u003e\u003cstrong\u003econjoint-design\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/conjoint-design\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eAttribute architecture, AMCE/AMIE estimation, power analysis (\u003ccode\u003ecjpowR\u003c/code\u003e), BART heterogeneity detection, design variants\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/conjoint-diagnostics/SKILL.md\"\u003e\u003cstrong\u003econjoint-diagnostics\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/conjoint-diagnostics\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eDiagnostic checklist: design, estimation, measurement error (IRR), external validity, interpretation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/conjoint-cleaning/SKILL.md\"\u003e\u003cstrong\u003econjoint-cleaning\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/conjoint-cleaning\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eQualtrics export to analysis-ready format: column conventions, reshaping, choice mapping, translation, pilot detection, validation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/survey-design/SKILL.md\"\u003e\u003cstrong\u003esurvey-design\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/survey-design\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eQuestion construction, scale design, survey flow, pretesting, respondent burden, social desirability mitigation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/cross-national-design/SKILL.md\"\u003e\u003cstrong\u003ecross-national-design\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/cross-national-design\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eCross-national survey experiments: per-country power, sensitivity bias auditing, instrument localization\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/list-experiment/SKILL.md\"\u003e\u003cstrong\u003elist-experiment\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/list-experiment\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eItem count technique: pre-design sensitivity assessment, control list design, NLSreg/MLreg estimation, assumption testing, placebo diagnostics\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Analysis\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/topic-modeling/SKILL.md\"\u003e\u003cstrong\u003etopic-modeling\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/topic-modeling\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eSTM with metadata covariates, topic count selection via coherence-exclusivity diagnostics, reporting\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/text-classification/SKILL.md\"\u003e\u003cstrong\u003etext-classification\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/text-classification\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eLLM-based classification: codebook design, learning regime selection, human-LLM hybrid workflows, validation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/model-council-voting/SKILL.md\"\u003e\u003cstrong\u003emodel-council-voting\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/model-council-voting\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003ePanel of models as independent coders: consensus rules, chance-corrected agreement (Cohen/Fleiss/Krippendorff), correlated-error diagnostics, validation beyond the panel\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/model-committee/SKILL.md\"\u003e\u003cstrong\u003emodel-committee\u003c/strong\u003e\u003c/a\u003e\u003cbr\u003e\u003csub\u003eClaude Code + Codex\u003c/sub\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/model-committee\u003c/code\u003e\u003cbr\u003e\u003ccode\u003e$model-committee\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eGPT-5.5 and Claude Opus 4.8 as a deliberative committee: use-case gate, blind proposals, cross-critique and revision, blinded cross-ranking, and a precommitted rule for one decision\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/llm-calibration-logprobs/SKILL.md\"\u003e\u003cstrong\u003ellm-calibration-logprobs\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/llm-calibration-logprobs\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eWithin-model confidence from token log-probabilities: aggregation, triage, calibration (ECE, Brier, reliability diagrams) against human ground truth\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Corpus Processing\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/vlm-ocr-pipeline/SKILL.md\"\u003e\u003cstrong\u003evlm-ocr-pipeline\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/vlm-ocr-pipeline\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eVLM-based OCR: model selection, image handling, prompt engineering, batch strategy, accuracy evaluation, reproducibility\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/post-ocr-cleanup/SKILL.md\"\u003e\u003cstrong\u003epost-ocr-cleanup\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/post-ocr-cleanup\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003ePost-OCR cleanup: LLM and rule-based correction, quality diagnostics, multilingual considerations, corpus-level QA, provenance\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/vlm-ocr-evaluation/SKILL.md\"\u003e\u003cstrong\u003evlm-ocr-evaluation\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/vlm-ocr-evaluation\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eCompare OCR systems before bulk runs: candidate set, stratified ground truth, CER/WER with declared normalization, per-language and per-stratum accuracy\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Writing \u0026 Reporting\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/hypothesis-building/SKILL.md\"\u003e\u003cstrong\u003ehypothesis-building\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/hypothesis-building\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eFalsifiability, counterfactuals, DAGs, FPCI, three-level hypothesis specification, equivalence testing, SESOI\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/literature-review/SKILL.md\"\u003e\u003cstrong\u003eliterature-review\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/literature-review\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eEvidence maps, closest-prior-work assessment, gap verdicts, literature clusters, synthesis plans\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/narrative-building/SKILL.md\"\u003e\u003cstrong\u003enarrative-building\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/narrative-building\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eIntroduction logic, literature reviews, the \"Why-to-If-Then\" funnel, cumulative framing, multi-experiment coherence\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/pre-registration-writing/SKILL.md\"\u003e\u003cstrong\u003epre-registration-writing\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/pre-registration-writing\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003ePAP structure, registry selection, analytical strategy specification, code pre-registration, deviation documentation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/methods-reporting/SKILL.md\"\u003e\u003cstrong\u003emethods-reporting\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/methods-reporting\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003e40-item reporting checklist: CONSORT standards, JARS preregistration elements, DA-RT transparency\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/paper-tex/SKILL.md\"\u003e\u003cstrong\u003epaper-tex\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/paper-tex\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eTypeset a working paper or journal submission in house-style LaTeX from any draft (Markdown, Word, TeX, ODT, HTML): pandoc conversion, EB Garamond template, \u003ccode\u003e\\figcap\u003c/code\u003e title+note captions, \u003ccode\u003e[H]\u003c/code\u003e floats, single-spaced title block with the introduction on its own page, and journal-specific prep (spacing, page limit, anonymization, disclosures). Bundles a tested convert-and-build driver.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Figures \u0026 Tables\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/figures/SKILL.md\"\u003e\u003cstrong\u003efigures\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/figures\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eDesign publication-quality figures: chart choice from comparison, scales, color, legend ordering matched to visual order, self-contained captions, reproducibility\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/tables/SKILL.md\"\u003e\u003cstrong\u003etables\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/tables\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eDesign publication-quality tables: column order matching the argument, row grouping, precision and uncertainty conventions, self-contained titles and notes, code-generated workflows\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Manuscript QA\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/fair-check/SKILL.md\"\u003e\u003cstrong\u003efair-check\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/fair-check\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eFAIR audit for completed manuscripts: data/code/material availability, repository metadata, persistent identifiers, licenses, access restrictions, reuse conditions\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/citation-check/SKILL.md\"\u003e\u003cstrong\u003ecitation-check\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/citation-check\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eIn-text/reference parity, DOI and source-status checks, fabrication/existence verification (Crossref/OpenAlex), stale working papers, citation-style and support audits\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/fact-check/SKILL.md\"\u003e\u003cstrong\u003efact-check\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/fact-check\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eVerify each in-text claim is actually supported by its cited source. Runs \u003ccode\u003ecitation-check\u003c/code\u003e first, then locates each source's knowledge-base Markdown (\u003ccode\u003esources/md/\u003c/code\u003e) and audits claim support, overclaiming, direction, scope, and misattribution. Pairs with \u003ccode\u003eprocess-source\u003c/code\u003e.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/figure-table-audit/SKILL.md\"\u003e\u003cstrong\u003efigure-table-audit\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/figure-table-audit\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eEnd-stage QA of the finished figure/table set: inventory, cross-references, text-to-table consistency, accessibility, SI and replication linkage. Pairs with \u003ccode\u003efigures\u003c/code\u003e and \u003ccode\u003etables\u003c/code\u003e (production-stage).\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/replication-package/SKILL.md\"\u003e\u003cstrong\u003ereplication-package\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/replication-package\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eScaffold or audit a replication package at a target directory. Generates folder structure, README, \u003ccode\u003emaster.R\u003c/code\u003e, figure/table crosswalk, codebook template, LICENSE placeholder, \u003ccode\u003e.gitignore\u003c/code\u003e, and a pre-release checklist. Platform-neutral (Harvard Dataverse, OSF, Zenodo, GitHub releases). Adapted from Yusaku Horiuchi's \u003ca href=\"https://github.com/yhoriuchi/replication-package-guide\"\u003ereplication-package-guide\u003c/a\u003e with FAIR-principle integration. Pair with \u003ccode\u003efair-check\u003c/code\u003e.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n### Review \u0026 Submission\n\n\u003ctable width=\"100%\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth width=\"18%\"\u003eSkill\u003c/th\u003e\n\u003cth width=\"16%\"\u003eInvoke\u003c/th\u003e\n\u003cth width=\"66%\"\u003eWhat it does\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/paper-review-lite/SKILL.md\"\u003e\u003cstrong\u003epaper-review-lite\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/paper-review-lite\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eCritical-Reviewer-style pre-submission audit. Parallel quote-grounded sub-agents, verification cross-check, CONSORT and pre-reg audit for experimental papers. Single-model, in-session counterpart to the standalone \u003ca href=\"https://github.com/scdenney/presubmit\"\u003e\u003ccode\u003epresubmit\u003c/code\u003e\u003c/a\u003e CLI.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/paper-review-lite-codex/SKILL.md\"\u003e\u003cstrong\u003epaper-review-lite-codex\u003c/strong\u003e\u003c/a\u003e\u003cbr\u003e\u003csub\u003eClaude Code → Codex\u003c/sub\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/paper-review-lite-codex\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eCross-model adversarial variant of \u003ccode\u003epaper-review-lite\u003c/code\u003e. Claude and Codex (GPT-5.4) independently apply the same review specification, then each cross-checks the other's findings; surviving issues are annotated by confidence (mutual, asymmetric-confirmed, single-model-adjudicated). Roughly 22 model calls. Use before submission for maximum pressure and a second model family's blind spots.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/presubmit/SKILL.md\"\u003e\u003cstrong\u003epresubmit\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/presubmit\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eActivator and setup wizard for the standalone \u003ca href=\"https://github.com/scdenney/presubmit\"\u003e\u003ccode\u003epresubmit\u003c/code\u003e\u003c/a\u003e Python CLI. Walks first-time users through install (venv + \u003ccode\u003epip install -e .\u003c/code\u003e), Anthropic API key setup, and output location, then runs the heavier 30+ stage adversarial pipeline (resumable, cost-tracked, optional \u003ccode\u003e--math\u003c/code\u003e and \u003ccode\u003e--code-dir\u003c/code\u003e add-ons). Heavier API-driven counterpart to \u003ccode\u003epaper-review-lite\u003c/code\u003e.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"plugin/skills/journal-review/SKILL.md\"\u003e\u003cstrong\u003ejournal-review\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ccode\u003e/journal-review\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003eDrafts a senior-peer referee report on \u003cstrong\u003esomeone else's\u003c/strong\u003e manuscript for a social-science journal. Five parallel finder sub-agents (Breaker, Butcher, Shredder, Void, Situator), a Blue Team filter, Chief Reviewer synthesis, and Tone Guard sanitization produce a 1,200–2,000-word report (Recommendation, Summary, Major Concerns, Additional Concerns, Suggestions for Revision). Different role from \u003ccode\u003epaper-review-lite\u003c/code\u003e and \u003ccode\u003epresubmit\u003c/code\u003e, which are calibrated for self-audit. This one acts as a third-party referee and is meant to support, not replace, your own assessment of a manuscript.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\n---\n\n## Contributing\n\nPRs welcome. To add a new skill:\n\n1. Create `plugin/skills/\u003cname\u003e/SKILL.md` following the [skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)\n2. Add `plugin/commands/\u003cname\u003e.md` (see existing examples — one paragraph activation prompt + `$ARGUMENTS`)\n3. Add the Codex-native package at `codex/\u003cname\u003e/` with `SKILL.md` and `agents/openai.yaml`, unless the workflow is intentionally platform-specific\n4. Add sources to `SOURCES.md` under a new or existing section\n5. Update the platform catalogs and badges\n6. Run `bash plugin/scripts/check.sh` and validate each changed Codex skill before opening a PR\n\n## License\n\nThis project is licensed under [Creative Commons Attribution-NonCommercial 4.0 International](LICENSE). The skills are intended for noncommercial scholarly and educational use.\n\nThe `citation-check`, `literature-review`, `figures`, `tables`, and `figure-table-audit` skills remix workflow ideas from [Cheng-I Wu's Academic Research Skills for Claude Code](https://github.com/Imbad0202/academic-research-skills), also licensed CC BY-NC 4.0. The instructions here are rewritten for this repository's open-science and experimental-social-science scope.\n\nThe `replication-package` skill adapts the structural conventions in [Yusaku Horiuchi's replication-package-guide](https://github.com/yhoriuchi/replication-package-guide) (the source for single-entry-point, compact vs. build/analyze layouts, figure/table crosswalk, paper-consistency check, correction workflow, and pre-release checklist). FAIR-principle integration and Claude Code/Codex skill packaging are added on top; Harvard Dataverse and other platform-specific upload mechanics are not included. Cite Horiuchi's guide if you publish a package built with this skill.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscdenney%2Fopen-science-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fscdenney%2Fopen-science-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscdenney%2Fopen-science-skills/lists"}