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

templates/evidence_assessment_template.md

View on GitHub
# Evidence Assessment Template

## Purpose
Per-source quality assessment card. Used by the source_verification_agent to systematically evaluate each source entering the research pipeline.

## Assessment Card

```markdown
## Evidence Assessment Card

### Source Identification
- **Citation (APA 7.0)**: [full reference]
- **DOI/URL**: [link]
- **Type**: [journal article / book / report / web / conference paper / thesis / other]
- **Access Date**: [when verified]

---

### Quality Assessment

#### 1. Evidence Level
**Level**: [I / II / III / IV / V / VI / VII]
**Justification**: [why this level]

#### 2. Publication Venue
- **Journal/Publisher**: [name]
- **Indexed in**: [Scopus / WoS / PubMed / DOAJ / other / none]
- **Impact Factor/CiteScore**: [value or N/A]
- **COPE member**: [Yes / No / Unknown]
- **Predatory indicators**: [None / Flags: list]

**Venue Grade**: [Excellent / Good / Adequate / Questionable / Unacceptable]

#### 3. Author Credibility
- **Author(s)**: [names]
- **Affiliation(s)**: [institutions]
- **ORCID**: [if available]
- **Track record**: [publication history in field]
- **Expertise match**: [relevant to topic? Yes/Partial/No]

**Author Grade**: [Excellent / Good / Adequate / Unknown / Questionable]

#### 4. Methodological Quality
- **Design**: [description]
- **Sample**: [size, selection, representativeness]
- **Analysis**: [appropriate for design?]
- **Limitations acknowledged**: [Yes / Partially / No]
- **Replicable**: [Yes / Partially / No]

**Method Grade**: [Excellent / Good / Adequate / Weak / Flawed]

#### 5. Currency
- **Publication year**: [YYYY]
- **Data collection period**: [if stated]
- **Field velocity**: [Rapid / Moderate / Slow / Foundational]
- **Still current**: [Yes / Conditionally / No]

**Currency Grade**: [Current / Acceptable / Dated / Outdated / Foundational]

#### 6. Conflict of Interest
- **Declared COI**: [None / Listed: details]
- **Funding source**: [source or Not stated]
- **Potential undeclared COI**: [None detected / Possible: details]

**COI Grade**: [Clean / Minor / Moderate / Significant / Critical]

---

### Overall Assessment

| Dimension | Grade |
|-----------|-------|
| Evidence Level | [I-VII] |
| Venue | [Excellent-Unacceptable] |
| Author | [Excellent-Questionable] |
| Method | [Excellent-Flawed] |
| Currency | [Current-Outdated] |
| COI | [Clean-Critical] |
| **Overall** | **[A / B / C / D / F]** |

### Recommendation
- [ ] **Use as primary evidence** (Grade A-B)
- [ ] **Use as supporting evidence** (Grade B-C)
- [ ] **Use with explicit caveats** (Grade C-D)
- [ ] **Do not use** (Grade D-F) — Reason: [specific reason]

### Notes
[Any additional observations, caveats, or context]
```

## Batch Assessment Summary

```markdown
## Source Verification Summary

**Date**: [YYYY-MM-DD]
**Sources assessed**: [N]
**Assessor**: source_verification_agent

### Grade Distribution
| Grade | Count | % |
|-------|-------|---|
| A (Excellent) | X | X% |
| B (Good) | X | X% |
| C (Adequate) | X | X% |
| D (Weak) | X | X% |
| F (Unacceptable) | X | X% |

### Flagged Sources
| Source | Issue | Severity | Recommendation |
|--------|-------|----------|---------------|
| [ref] | [issue] | [High/Medium/Low] | [Include with caveat / Exclude] |

### Predatory Journal Alerts
[List any flagged journals]

### Overall Source Base Quality
**Assessment**: [Strong / Adequate / Mixed / Weak]
**Recommendation**: [Proceed / Supplement / Major revision of source base needed]
```

## Usage Notes
- Complete one card per source for full verification
- Batch summary should be produced after all cards are complete
- Minimum spot-check: 20% of sources get full card assessment
- All Grade D/F sources require documented justification
- Any predatory journal flag requires full verification
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