Yuan1z0825/nature-skills / skills/nature-social-science
nature-social-science
Verified社会科学及相邻学科学术写作与选题论证工作台,覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题阶段与论证自检。
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 2.9 KB |
| README_EN.md | markdown | 3.4 KB |
| SKILL.md | skill md | 11.5 KB |
| agents/openai.yaml | config | 308 B |
| manifest.yaml | config | 2.4 KB |
| references/01-foundations.md | markdown | 12.9 KB |
| references/02-workflow-steps1-3.md | markdown | 38.3 KB |
| references/03-workflow-steps4-5.md | markdown | 28.6 KB |
| references/04-workflow-steps6-8.md | markdown | 40.4 KB |
| references/05-prompt-library.md | markdown | 53.3 KB |
| references/06-worksheets.md | markdown | 12.7 KB |
| references/07-status-terminology.md | markdown | 11.3 KB |
| references/08-usage-handoff.md | markdown | 8.7 KB |
| references/09-academic-expression.md | markdown | 13.2 KB |
README_EN.md
View on GitHub# `nature-social-science` Skill
[中文说明](README.md)
`nature-social-science` is a workbench for social-science and adjacent humanities academic writing and topic argumentation, covering four elements: topic development, literature mapping, argument organization, and academic expression. Quantitative, qualitative, ethnographic, archival, documentary, corpus, and digital research are all in scope. The judging criteria are always the same: **Is the question clear? Does the evidence match? Are the claims honest? Can the researcher actually complete the project?**
## What To Use It For
- Turn "I want to study XX" interest into a bounded, searchable research space (Mode A).
- Narrow a broad topic or known relationship into a specific unresolved knowledge problem (Mode B).
- Audit an existing research question: evidence fit, overclaiming, and resilience against a "Reviewer 2" attack (Mode C).
- Map a field's literature landscape: distinguish "few studies" from genuinely unresolved knowledge problems while preserving contradictions, null results, and alternative explanations.
- Design evidence routes and set a claim ceiling — which conclusions the evidence can and cannot support.
- Assess PhD/thesis feasibility of candidate topics: hard-failure conditions, data access, ethics, and time fit.
- Audit argument paragraphs for overclaiming, verb-evidence mismatch, and concept conflation.
- Prepare supervisor communication materials and the argumentation sections of proposals.
## Typical Requests
- "I want to study social media's effect on teenagers — help me find a thesis topic."
- "Has anyone done this before? Is my topic novel?"
- "Help me anticipate how a reviewer would attack this research question."
- "Is this conclusion overclaimed? My data only supports correlation."
- "Help me sort out the argumentation section of my proposal."
## What You Need To Provide
- Your interest, broad topic, or tentative research question (any one as the starting point).
- Key literature you have read, existing data, or method preferences (if any).
- Your constraints: time, funding, data access, ethics boundaries, and target degree level.
## Outputs
- A one-page search space, a field landscape, and 3–7 unresolved-problem cards.
- 1–3 evidence routes and 6–12 candidate RQ cards.
- A novelty audit with Reviewer 2 attack records, a feasibility dossier, and a shortlist of up to three Topic Cards.
- Honest-wording revision suggestions for argument paragraphs plus a red-flags list.
## Boundaries
- The skill does not hand you a "correct topic" and does not guarantee novelty, admission, funding, publication, or thesis success.
- It does not treat any single method (quantitative, qualitative, causal inference, etc.) as the default answer to quality research.
- AI confidence is not evidence: unknowns are recorded as "unknown"; no fabricated citations, sources, or results.
- Steps that require human judgement (disciplinary weight, source access, sensitive participants, supervisor willingness) stop and hand off explicitly instead of deciding for you.
## Related Skills
- `nature-writing`: drafting and restructuring Nature-style natural-science manuscript sections.
- `nature-reviewer`: simulated pre-submission peer review.
- `nature-polishing`: language polishing and terminology-consistency checks for existing drafts.
- `academic-investigation`: scholar background and research-integrity investigation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |