Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/24-Imbad0202-academic-research-skills/deep-research

deep-research

Verified

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

FileKindSize
SKILL.mdskill md31.8 KB
agents/bibliography_agent.mdmarkdown3.6 KB
agents/devils_advocate_agent.mdmarkdown6.1 KB
agents/editor_in_chief_agent.mdmarkdown4.9 KB
agents/ethics_review_agent.mdmarkdown6.9 KB
agents/meta_analysis_agent.mdmarkdown14.6 KB
agents/monitoring_agent.mdmarkdown9.0 KB
agents/report_compiler_agent.mdmarkdown5.4 KB
agents/research_architect_agent.mdmarkdown6.9 KB
agents/research_question_agent.mdmarkdown6.9 KB
agents/risk_of_bias_agent.mdmarkdown9.4 KB
agents/socratic_mentor_agent.mdmarkdown21.2 KB
agents/source_verification_agent.mdmarkdown6.4 KB
agents/synthesis_agent.mdmarkdown6.0 KB
examples/exploratory_research.mdmarkdown6.9 KB
examples/fact_check_mode.mdmarkdown12.9 KB
examples/handoff_to_paper.mdmarkdown11.0 KB
examples/policy_analysis.mdmarkdown9.4 KB
examples/review_mode.mdmarkdown17.3 KB
examples/socratic_guided_research.mdmarkdown22.9 KB
examples/systematic_review.mdmarkdown7.7 KB
references/apa7_style_guide.mdmarkdown4.6 KB
references/equator_reporting_guidelines.mdmarkdown14.0 KB
references/ethics_checklist.mdmarkdown10.2 KB
references/failure_paths.mdmarkdown14.8 KB
references/interdisciplinary_bridges.mdmarkdown20.9 KB
references/irb_decision_tree.mdmarkdown11.5 KB
references/literature_monitoring_strategies.mdmarkdown9.6 KB
references/logical_fallacies.mdmarkdown10.4 KB
references/methodology_patterns.mdmarkdown17.0 KB
references/mode_selection_guide.mdmarkdown16.2 KB
references/preregistration_guide.mdmarkdown11.8 KB
references/socratic_questioning_framework.mdmarkdown11.4 KB
references/source_quality_hierarchy.mdmarkdown7.2 KB
references/systematic_review_toolkit.mdmarkdown18.7 KB
templates/evidence_assessment_template.mdmarkdown3.7 KB
templates/literature_matrix_template.mdmarkdown3.7 KB
templates/preregistration_template.mdmarkdown8.5 KB
templates/prisma_protocol_template.mdmarkdown8.8 KB
templates/prisma_report_template.mdmarkdown15.8 KB
templates/research_brief_template.mdmarkdown2.1 KB

references/ethics_checklist.md

View on GitHub
# Research Ethics Checklist — AI-Assisted Research

## Purpose
Comprehensive ethics checklist for AI-assisted academic research. Used by the ethics_review_agent.

## 1. AI Disclosure

### Mandatory Disclosure Elements
- [ ] AI tools used are named (e.g., "Claude," "GPT-4," "Gemini")
- [ ] Scope of AI involvement specified:
  - [ ] Literature search assistance
  - [ ] Source screening
  - [ ] Evidence synthesis
  - [ ] Draft writing
  - [ ] Editing/revision
  - [ ] Data analysis
  - [ ] Translation
- [ ] Human oversight described (who reviewed what, at which stages)
- [ ] AI limitations acknowledged (potential hallucination, knowledge cutoff, etc.)
- [ ] AI version/date noted (for reproducibility)

### Disclosure Statement Template
```
AI Disclosure: This research was conducted with assistance from [AI Tool Name]
(version/date). AI was used for [specific tasks]. All findings were verified
against cited sources by [human role]. The research team maintains full
responsibility for the accuracy and interpretation of all content.
```

### Where to Place Disclosure
- In the methodology section (detailed)
- In the abstract or author note (brief)
- In footnotes for specific AI-generated analyses

## 2. Attribution Integrity

### Citation Ethics
- [ ] Every factual claim has at least one supporting citation
- [ ] No fabricated or hallucinated references
  - Verification: Spot-check minimum 20% of references for existence
  - Cross-check DOIs, publication years, author names
- [ ] Paraphrasing is genuine (not just rearranging words)
- [ ] Direct quotes are exact and attributed
- [ ] Ideas are attributed to original authors, not intermediary sources
- [ ] Self-citation is proportionate (not excessive or exclusionary)

### AI-Specific Attribution Risks
| Risk | Description | Mitigation |
|------|-------------|-----------|
| Hallucinated references | AI generates plausible but non-existent citations | Verify every reference against database |
| Merged citations | AI combines details from multiple sources | Cross-check each citation element |
| Incorrect authors | AI assigns wrong authors to works | Verify author names against actual publications |
| Wrong year | AI uses incorrect publication year | Cross-check against database records |
| Ghost citations | References listed but never cited in text | Audit reference list against in-text citations |

## 3. Dual-Use Assessment

### Screening Questions
1. Could this research be used to harm individuals or communities?
2. Does it reveal vulnerabilities that could be exploited?
3. Could it be used to develop surveillance or control mechanisms?
4. Does it provide information that could be weaponized?
5. Could it be used to discriminate against specific groups?

### Risk Levels and Responses

| Level | Action Required |
|-------|----------------|
| None | No additional action |
| Low | Brief note in limitations |
| Moderate | Responsible Use statement in report |
| High | Prominent warning + limited distribution recommendation |
| Critical | Do not publish without institutional ethics review |

### Responsible Use Statement Template
```
Responsible Use: This research is intended for [stated purpose]. The authors
acknowledge that findings related to [sensitive area] could potentially be
applied in ways not intended by this research. Users of this research are
urged to consider the ethical implications of their applications and to
prioritize [specific ethical principle].
```

## 4. Fair Representation

### Balanced Treatment Checklist
- [ ] Multiple perspectives on contested issues are presented
- [ ] Minority/dissenting viewpoints are not dismissed without engagement
- [ ] Subjects and communities are described accurately
- [ ] Language is respectful and non-stigmatizing
- [ ] Cultural context is acknowledged where relevant
- [ ] Power dynamics are considered (who is studied vs. who studies)
- [ ] Geographic and cultural diversity in sources

### Sensitive Topics
- Indigenous knowledge: Respect OCAP principles (Ownership, Control, Access, Possession)
- Disability: Person-first language unless community prefers identity-first
- Gender/sexuality: Use inclusive, current terminology
- Race/ethnicity: Use preferred terminology of the communities discussed
- Socioeconomic status: Avoid deficit framing
- Mental health: Avoid stigmatizing language

### Representation Audit Questions
1. Whose voices are centered? Whose are missing?
2. Are communities described on their own terms?
3. Is there implicit bias in the framing?
4. Would the subjects/communities recognize themselves in this description?

## 5. Data Ethics

### Data Source Ethics
- [ ] All data sources are legal to use
- [ ] Public data: Confirm public domain or appropriate license
- [ ] Licensed data: Usage complies with license terms
- [ ] Scraped data: Complies with robots.txt and terms of service
- [ ] Personal data: GDPR/privacy law compliance (if applicable)
- [ ] Institutional data: Authorized access confirmed

### Privacy Protection
- [ ] No personally identifiable information (PII) without consent
- [ ] Aggregated data used where possible
- [ ] Small-N groups protected from identification
- [ ] Institutional identities protected when not public
- [ ] Data retention/deletion plan (if primary data collected)

### AI-Specific Data Concerns
- [ ] AI training data biases acknowledged
- [ ] AI knowledge cutoff date noted
- [ ] AI-generated data clearly labeled as such
- [ ] No circular citation (AI cites AI-generated content)

## 6. Conflict of Interest

### Types to Assess
- [ ] Financial: Funding source, consulting relationships
- [ ] Institutional: Author evaluating own institution
- [ ] Intellectual: Author defending own prior work
- [ ] Personal: Relationships with subjects/stakeholders
- [ ] Political: Government-funded research on government policy
- [ ] Commercial: Industry connections or product interests
- [ ] AI-specific: AI tool company influence on research design

### Disclosure Requirement
Any identified conflict must be disclosed in the report, with an assessment of whether it could have influenced the findings.

## 7. Reproducibility Ethics

### Documentation Requirements
- [ ] Search strategies documented (databases, terms, dates)
- [ ] Inclusion/exclusion criteria documented
- [ ] Analytical methods described in replicable detail
- [ ] AI prompts/instructions documented (if relevant)
- [ ] Data processing steps documented
- [ ] Code/scripts shared (if applicable)

### Reproducibility Statement Template
```
Reproducibility: The search strategy, inclusion criteria, and analytical
methods used in this research are documented in [section/appendix]. The
AI-assisted components used [specific prompts/parameters]. Researchers
wishing to replicate or extend this work should note [relevant limitations
or conditions].
```

## 8. Human Subjects Ethics

### 8.1 Human Subjects Determination

- [ ] Does the research collect, use, or analyze human-related data?
- [ ] If yes, is the data personally identifiable?
- [ ] If the data is publicly available and de-identified, has exempt review status been confirmed with the IRB?

### 8.2 IRB Review Levels

| Review Level | Applicable Conditions | Review Timeline |
|-------------|----------------------|-----------------|
| **Exempt Review** | Public data, de-identified data, anonymous surveys (no sensitive topics) | 1-2 weeks |
| **Expedited Review** | Minimal risk, non-vulnerable populations, general surveys/interviews | 2-4 weeks |
| **Full Board Review** | Greater than minimal risk, vulnerable populations, sensitive topics, deception | 4-8 weeks |

- [ ] Applicable IRB review level has been determined
- [ ] IRB review timeline has been incorporated into the research project schedule
- [ ] Researcher has completed research ethics training (CITI or equivalent course)

### 8.3 Informed Consent

- [ ] Informed consent form includes research title, purpose, procedures, risks, and benefits
- [ ] Clearly states voluntary nature of participation (may withdraw at any time, no penalties)
- [ ] Provides researcher and IRB contact information
- [ ] Special situations addressed:
  - [ ] Online survey: Electronic consent (clicking "I agree")
  - [ ] Audio/video recording: Separate checkbox item
  - [ ] Minors: Legal guardian consent + subject assent
  - [ ] Indigenous research: Community consent + individual informed consent

### 8.4 Data De-identification

- [ ] Remove direct identifiers (names, student IDs, national ID numbers)
- [ ] Assess indirect identifier risks (department + year + gender combinations)
- [ ] Small sample re-identification risk assessment (small departments may allow re-identification of individuals)
- [ ] Remove identifiable details from qualitative quotations
- [ ] Encrypt data storage with access controls
- [ ] Establish data retention and destruction timeline

### 8.5 Vulnerable Population Protection

| Population | Additional Protective Measures |
|-----------|-------------------------------|
| **Minors** | Legal guardian consent + age-appropriate assent form |
| **Persons with disabilities** | Assess consent capacity, provide accessible consent procedures |
| **Students (researcher is a teacher)** | Avoid power dynamics affecting voluntariness, use third-party recruitment |
| **Indigenous peoples** | Community consultation and consent, respect OCAP principles |
| **Economically disadvantaged** | Compensation must not constitute undue inducement |
| **Incarcerated persons** | Additional IRB review, ensure non-coercive participation |

- [ ] Vulnerable populations involved in the research have been identified
- [ ] Corresponding additional protective measures have been planned
- [ ] IRB review level accounts for vulnerable population considerations

> For detailed IRB decision tree and Taiwan-specific process: see `references/irb_decision_tree.md`

---

## Quick Audit Checklist (Final Gate)

Before delivery, confirm ALL items:

- [ ] AI disclosure present and accurate
- [ ] All references spot-checked (minimum 20%)
- [ ] No fabricated citations detected
- [ ] Dual-use assessment completed
- [ ] Fair representation reviewed
- [ ] Data sources legally and ethically used
- [ ] Conflicts of interest disclosed
- [ ] Reproducibility documentation provided
- [ ] Writing is inclusive and respectful
- [ ] Report benefits stated audience without causing foreseeable harm
- [ ] If the research involves human subjects, has IRB review been planned?
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall