academic-researcher
Expert-level academic research and LaTeX paper writing with IEEE/APA citation support. Creates peer-reviewed research papers, literature reviews, and theses with proper scholarly standards.
What this skill does
## What I Do
I help you create expert-level academic research documents with:
- Peer-reviewed source discovery and verification
- Proper IMRaD structure and academic writing conventions
- IEEE (primary) and APA (secondary) citation formats
- LaTeX output for professional mathematical typesetting
- Quality assurance against scholarly standards
## Non-Negotiables (Research Integrity)
- **No fabricated citations**: never cite papers you did not locate and verify (title, authors, venue, year, DOI/URL).
- **Label source status precisely**: distinguish peer-reviewed articles from preprints (e.g., arXiv) and from non-academic web sources.
- **Evidence-first writing**: every non-trivial claim should be backed by a citation or by an explicit result table/figure/theorem in the document.
- **Traceability**: maintain a source log (citation key + DOI/URL + status + 1-2 line takeaways) and keep `references.bib` as the single source of truth.
## When to Use Me
Use this skill when you need to write:
- **Research papers** for conferences (IEEE, ACM) or journals
- **Literature reviews** and survey papers
- **Theses/dissertations** (master's or PhD)
- **Research proposals** and grant applications
- **Technical reports** with academic rigor
## Workflow Overview
```
Phase 1: Requirements → Phase 2: Planning → Phase 3: Discovery
↓ ↓ ↓
Phase 6: QA ← Phase 5: Writing ← Phase 4: Structure
```
---
## Phase 1: Requirements Clarification
Before starting, clarify with the user:
### Essential Questions
1. **Document Type**
- Research paper (conference/journal)?
- Literature review / survey?
- Thesis / dissertation chapter?
- Research proposal?
2. **Topic & Scope**
- What is the main research question or contribution?
- What is the target word count or page limit?
- Any specific research questions to address?
3. **Target Venue**
- Which conference or journal?
- Any specific formatting requirements?
- Submission deadline?
4. **Citation Format**
- IEEE (default for CS/Engineering)?
- APA (social sciences)?
- Other (ACM, Chicago)?
### User Input Template
```markdown
## Research Document Request
**Type:** [Research Paper / Literature Review / Thesis]
**Topic:** [Your research topic]
**Target:** [Conference/Journal name or "General"]
**Length:** [X pages or X words]
**Citation:** [IEEE / APA / Other]
**Deadline:** [Date if applicable]
**Special Requirements:** [Any specific guidelines]
```
---
## Phase 2: Research Planning
### Search Strategy Development
1. **Identify core concepts** - Extract key terms from the topic
2. **Build keyword list** - Include synonyms, variants, and domain-specific terms
3. **Select databases** - Choose appropriate sources:
| Database | Best For |
|----------|----------|
| Google Scholar | Broad academic search |
| IEEE Xplore | Engineering, CS |
| ACM Digital Library | Computing |
| arXiv | Preprints, CS, physics |
| PubMed | Medicine, life sciences |
| ScienceDirect | General science |
| JSTOR | Humanities, social sciences |
### Search Command Patterns (Tool-Agnostic)
Use your platform's browsing/search tool. If browsing is unavailable, ask the user to provide PDFs/DOIs/URLs (or an existing `references.bib`) and proceed from those.
Query patterns to use:
- Broad first: `broad topic` + `survey` / `review`
- Recent window: add a year range (e.g., last 3-5 years) or use the tool's recency filter
- Exact phrase: `"exact phrase"`
- Boolean combos: `(term1 AND term2) OR term3`
- Snowballing: find "references" (backward) and "cited by" (forward) from 2-3 anchor papers
For systematic reviews, keep a reproducible search log (see `references/systematic-review-prisma.md`).
---
## Phase 3: Source Discovery & Verification
### Discovery Process
**Step 1: Foundational Sources**
- Search for seminal papers and foundational work
- Look for highly-cited papers (100+ citations)
- Find survey papers on the topic
**Step 2: Recent Work**
- Search for papers from last 2-3 years
- Look for "state of the art" reviews
- Find latest developments and advances
**Step 3: Related Work**
- Papers citing key foundational works
- Papers cited by recent major papers
- Parallel approaches and alternatives
### Verification Checklist
For each source, verify:
- [ ] Published in peer-reviewed venue (journal, conference)
- [ ] Author credentials and institutional affiliation
- [ ] Publication venue reputation (check Google Scholar metrics, impact factor)
- [ ] Citation count indicates impact
- [ ] Methodology is sound and described clearly
- [ ] Relevance to your research question
### Red Flags (Exclude These Sources)
- Predatory journals (check Beall's List or journalquality.info)
- No peer review process
- No institutional affiliation
- Suspiciously high publication volume
- Pay-to-publish without legitimate review
### Source Tracking
Create a source database (and keep `references.bib` as the single source of truth):
```markdown
## Source [N]
- **Citation Key:** [e.g., smith2023transformers]
- **Title:** [Paper title]
- **Authors:** [Author list]
- **Venue/Year:** [Journal/Conference, Year]
- **Status:** [peer-reviewed / preprint / standard / dataset / software]
- **DOI:** [If available]
- **URL:** [Canonical link]
- **Citations:** [Count + date checked]
- **Relevance:** [High/Medium/Low]
- **Key Points:** [1-3 bullets: what you will cite]
- **Limitations:** [1-2 bullets]
- **Use In:** [Which section of your document]
```
See `references/source-evaluation.md` and `references/bibliography-workflows.md`.
### Paper Access Strategy
When you find a relevant paper but cannot access the full text:
1. **Check open access first:**
- Run `node scripts/resolve-papers.js --doi "10.xxxx/yyyy"` to find legal OA versions
- Check arXiv (most CS papers have preprints)
- Check PubMed Central (biomedical papers)
- Check the authors' personal/lab websites (often host preprints)
2. **Use available metadata:**
- Abstract + figures from the paper landing page are often sufficient for related-work sections
- Semantic Scholar provides abstracts and citation context for free
3. **Ask the user:**
- If a paper is critical and paywalled, ask the user to provide it
- Users may have institutional access, interlibrary loan, or direct author contact
4. **Be transparent:**
- If citing a paper you could only read the abstract of, note this limitation
- Never fabricate content from a paper you haven't read
---
## Phase 4: Document Structure
### Research Paper Structure (IMRaD)
```
1. Title
2. Abstract (150-250 words)
3. Keywords (5-7 terms)
4. Introduction
- Background and motivation
- Problem statement
- Research objectives
- Contributions (3-5 bullet points)
- Paper organization
5. Related Work / Literature Review
- Thematic organization
- Gap identification
6. Methodology / Approach
- System design (if applicable)
- Algorithm description
- Technical approach
7. Results / Evaluation
- Experimental setup
- Metrics
- Results presentation
8. Discussion
- Interpretation
- Implications
- Limitations
9. Conclusion
- Summary
- Future work
10. References
```
### Literature Review Structure
```
1. Title
2. Abstract
3. Introduction
- Review scope and objectives
- Methodology (how sources were selected)
4. Thematic Sections (organized by themes)
5. Synthesis and Discussion
- Trends and patterns
- Gaps in literature
6. Conclusion
- Summary
- Future directions
7. References
```
### Systematic Review Structure (PRISMA-Style)
```
1. Title
2. Abstract
3. Introduction (scope + research questions)
4. Methods (protocol, databases, queries, screening, extraction, appraisal)
5. Results (selection counts + evidence tables + taxonomy)
6. Discussion (implications, limitations, threats to validity)
7. Conclusion (what is known + gaps + future directions)
8. References
9. Appendices (full queries, screening reasons,Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.