research-setup
Configure field, institution, datasets, journals, and project metadata.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Configure field, institution, datasets, journals, and project metadata.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
End-to-end empirical data analysis workflow for R or Python projects.
Find and assess datasets for a research question.
Repository-wide consistency audit for skills, hooks, rules, and docs.
Systematic literature review workflow using parallel librarian agents.
Structured interview and project-spec workflow for new research ideas.
Proofreading workflow for academic manuscripts and papers.
| name | research-setup |
| description | Configure field, institution, datasets, journals, and project metadata. |
Walk the user through setup. Use request_user_input only for bounded single-choice prompts that fit Codex's 2-3 option UI in Plan mode; use conversational prompts otherwise. Collect all answers, then write config files in one pass.
This skill is the bootstrap entry point for project config. There is no session-start scaffold hook: other skills create quality_reports/, output/, scripts/, and manuscripts/ lazily when they need to write there.
Seed only the config files this skill owns. Do not copy templates into the user project and do not pre-create output scaffolds.
Seed references/domain-profile.md if absent. Create references/ if missing. Copy from the installed plugin when available:
plugins/social-science-research/references/domain-profile.mdreferences/domain-profile.md
If neither exists, create a minimal placeholder with sections for field, journals, datasets, key researchers, and institutional colors.Seed PROJECT_CONTEXT.md if absent. Write this placeholder:
# [YOUR PROJECT NAME]
**Author:** [YOUR NAME]
**Institution:** [YOUR INSTITUTION]
Read PROJECT_CONTEXT.md and references/domain-profile.md silently. If either file has real content (not placeholders), tell the user what's already configured and offer to confirm or update each section.
Ask both questions conversationally in one response. Do not use request_user_input here because the option sets exceed Codex's 2-3 choice limit:
Field: "What is your field or subfield?" Offer examples such as Political Science, Economics, Sociology, or Public Health, and let the user answer freely.
Institution: "What is your institution?" Offer examples such as Duke University, Harvard University, Stanford University, or UC Berkeley, and let the user answer freely.
Store field and institution for customizing later steps.
Ask conversationally:
Wait for the user's response before moving to Step 3.
Ask conversationally. Codex question UI does not support multi-select, so keep it lightweight and collect the answers in one response:
Top journals (multiSelect, header: "Top journals"): "Select your top journals (pick all that apply):" — Offer the 4 most prestigious journals for the user's selected field. Use your knowledge of the field's top venues.
Secondary journals (multiSelect, header: "Secondary"): "Select secondary or subfield journals:" — Offer 4 secondary/subfield journals appropriate to the user's field.
User can multi-select presets and add custom journals via Other.
Ask conversationally. Codex question UI does not support multi-select, so keep it lightweight and collect the answers in one response:
Common datasets (multiSelect, header: "Datasets"): "Which datasets do you commonly use?" — Offer the 4 most-used datasets for the user's field. Use your knowledge of field-standard data sources.
Additional sources (multiSelect, header: "More data"): "Any additional data sources?" — Offer 4 cross-disciplinary sources: World Bank Open Data, IPUMS, Bureau of Labor Statistics, Census Bureau.
Use request_user_input in Plan mode for this paired single-choice prompt when the choices fit Codex's 2-3 mutually exclusive option limit; otherwise ask both questions conversationally in one response:
Researchers (single select, header: "Researchers"): "Add key researchers for targeted literature searches?" — Options: "Skip for now" / "Add researchers".
Colors (single select, header: "Colors"): "Which color palette should R figures use?" — If the institution is well-known, offer up to 3 choices: "[Institution] brand colors (Recommended)" with the hex codes, "Custom colors", and "Skip for now". Otherwise offer: "Custom colors" / "Skip for now".
If the user chose "Add researchers", ask conversationally for names, institutions, and Google Scholar URLs. Do NOT guess researcher names.
If the user chose "Custom colors", ask conversationally for primary and secondary hex codes.
references/domain-profile.mdRead the existing file and update each section with the user's answers. Preserve the file's existing structure and comments. Only replace sections the user answered; leave unanswered sections unchanged. Add an "Institutional Colors" section at the end if one doesn't exist, with the user's hex codes (or defaults #012169 / #f2a900 if skipped).
IMPORTANT: Do NOT write to rules/r-code-conventions.md. Colors live in references/domain-profile.md only.
Use PROJECT_CONTEXT.md as the project metadata file for Codex installs.
Update the metadata file header placeholders:
[YOUR PROJECT NAME] → user's project title (or leave placeholder if skipped)[YOUR NAME] → user's name (or leave placeholder if skipped)[YOUR INSTITUTION] → user's institutionSetup complete:
- references/domain-profile.md — field, [N] journals, [N] datasets[, N researchers][, colors]
- project metadata file (`PROJECT_CONTEXT.md`) — project name and institution
- output directories will be created lazily by the skills that write to them
Update anytime: references/domain-profile.md
Next step: `new-project`
Note any skipped sections and where to add them later.