academic-research-writing
Use when writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manuscript, research writing, journal submission, or needs help with academic structure, formatting, or revision.
Best use case
academic-research-writing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manuscript, research writing, journal submission, or needs help with academic structure, formatting, or revision.
Teams using academic-research-writing should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/academic-research-writing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How academic-research-writing Compares
| Feature / Agent | academic-research-writing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manuscript, research writing, journal submission, or needs help with academic structure, formatting, or revision.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Academic Research Writing
## Overview
Comprehensive toolkit for writing and reviewing computer science research papers. Combines paper writing workflows, manuscript review processes, clarity principles, and formatting standards.
## When to Use
**Writing Mode:**
- Writing new research papers (conference, journal, thesis)
- Creating survey/review papers
- Structuring technical contributions
**Review Mode:**
- Reviewing/editing existing manuscripts
- Pre-submission polish
- Addressing reviewer comments
- Collaborative editing
**Both Modes:**
- Improving academic writing clarity
- Preparing IEEE/ACM submissions
- Learning academic writing conventions
## Mode Selection
```
User request received
|
v
Is this about WRITING new content or REVIEWING existing content?
|
+---> Writing new paper -----> Use Writing Workflow
| (references/writing-workflow.md)
|
+---> Reviewing/editing -----> Use Review Workflow
| existing manuscript (references/review-workflow.md)
|
+---> Both/unclear ----------> Start with Review Workflow
to assess, then write
```
## Quick Reference
### Writing a Paper
1. **Clarify scope** - topic, venue, format (IEEE/ACM)
2. **Create outline** - section-by-section plan
3. **Draft core sections** - methodology first, then results
4. **Write supporting sections** - intro, related work, discussion
5. **Add citations** - 15-20+ references
6. **Review & polish** - use checklists
See: `references/writing-workflow.md`
### Reviewing a Manuscript
1. **Extract core message** - one sentence summary
2. **Structural pass** - overall organization
3. **Section reviews** - intro, results, discussion
4. **Scientific clarity** - claims, evidence, hedging
5. **Language polish** - terminology, voice
6. **Formatting check** - journal compliance
See: `references/review-workflow.md`
## Core Resources
| Resource | Purpose |
|----------|---------|
| `references/writing-workflow.md` | 6-step paper writing process |
| `references/review-workflow.md` | 8-step manuscript review process |
| `references/narrative-framework.md` | Section-by-section narrative structure (Problem->Solution->Evidence) |
| `references/clarity-principles.md` | Gopen & Swan sentence-level clarity |
| `references/academic-phrasebank.md` | Common academic phrases by section |
| `references/cs-conventions.md` | CS-specific writing conventions |
| `references/section-checklists.md` | Combined quality checklists |
| `references/ieee-formatting.md` | IEEE formatting specifications |
| `references/acm-formatting.md` | ACM formatting specifications |
## Templates
| Template | Purpose |
|----------|---------|
| `templates/paper-structure.md` | Introduction arc, results paragraph, discussion templates |
| `templates/methodology.md` | Core message extraction, structural assessment, language guidelines |
## Evaluation
Use `evaluators/rubric.json` for quality scoring:
- Structure and Organization (weight: 1.0)
- Scientific Rigor (weight: 1.2)
- Language and Clarity (weight: 1.0)
- Section-Specific Quality (weight: 1.0)
- Formatting Compliance (weight: 0.8)
- Citation Quality (weight: 0.8)
**Minimum threshold:** Average score >= 3.5
## Seven Core Principles
1. **Clarity over cleverness** - Scientific clarity beats stylistic elegance
2. **Narrative shapes comprehension** - Structure determines understanding
3. **Audience dictates tone** - Expert vs. general requires different framing
4. **Format signals credibility** - Professional formatting reflects rigor
5. **Claims require evidence** - Strong assertions need strong data
6. **Each section has a job** - Intro sells, Results show, Discussion interprets
7. **Constraints shape structure** - Word limits determine emphasis
## Guardrails
**Critical requirements:**
1. Preserve author voice - edit for clarity, don't rewrite
2. Claims match data - flag overclaiming immediately
3. Quantitative rigor - statistics for all comparisons
4. Logical flow - clear transitions between sections
5. Appropriate hedging - match evidence strength
6. Consistent terminology - same term for same concept
**Common pitfalls to avoid:**
- Overclaiming ("proves" when data only suggests)
- Missing context (results without interpretation)
- Buried lede (important findings hidden)
- Inconsistent terms (alternating synonyms)
- Vague descriptions ("some increase" vs "3-fold increase")
## External Guides
| Guide | Purpose |
|-------|---------|
| `external-guides/how-to-write-a-paper.md` | Practical conference paper structuring guidelines (Introduction paragraphs, experiments, tables/figures) |
## PDF Templates
- `assets/full_paper_template.pdf` - IEEE template
- `assets/interim-layout.pdf` - ACM templateRelated Skills
gpt-researcher
Run GPT-Researcher multi-agent deep research framework locally using OpenAI GPT-5.2. Replaces ChatGPT Deep Research with local control. Researches 100+ sources in parallel, provides comprehensive citations. Use for Phase 3 industry/technical research or comprehensive synthesis. Takes 6-20 min depending on report type. Supports multiple LLM providers.
deep-research
Web research with Graph-of-Thoughts for fast-changing topics. Use when user requests research, analysis, investigation, or comparison requiring current information. Features hypothesis testing, source triangulation, claim verification, Red Team, self-critique, and gap analysis. Supports Quick/Standard/Deep/Exhaustive tiers. Creative Mode for cross-industry innovation.
brutal-deepresearch
Structured deep research pipeline with confirmation gates and resume support. Generates outline, launches parallel research agents, produces validated JSON results and markdown report.
agent-market-researcher
Expert market researcher specializing in market analysis, consumer insights, and competitive intelligence. Masters market sizing, segmentation, and trend analysis with focus on identifying opportunities and informing strategic business decisions.
agent-data-researcher
Expert data researcher specializing in discovering, collecting, and analyzing diverse data sources. Masters data mining, statistical analysis, and pattern recognition with focus on extracting meaningful insights from complex datasets to support evidence-based decisions.
agency-researcher
Find and qualify real estate agencies in a given suburb
academic-search
Search academic paper repositories (arXiv, Semantic Scholar) for scholarly articles in physics, mathematics, computer science, quantitative biology, AI/ML, and related fields
academic-data-integration
When the user needs to integrate multiple data sources (Canvas API, user memory, file systems) to create comprehensive academic reports. This skill combines course information, assignment details, submission status, and user context to generate actionable insights. Triggers include requests that involve cross-referencing multiple data sources or creating consolidated academic reports from disparate systems.
academic-course-setup-automator
When the user needs to set up multiple academic courses in a learning management system (Canvas/LMS) from structured data sources. This skill automates the entire workflow extracting course schedules from emails/attachments, matching instructors from CSV files, creating courses, enrolling teachers, publishing announcements with class details, uploading syllabi, enabling resource sharing for instructors teaching multiple courses, and publishing all courses. Triggers include course schedule setup, Canvas/LMS administration, academic term preparation, instructor assignment, syllabus distribution, and multi-course management.
academic-benchmark-researcher
When the user requests information about academic benchmarks, datasets, or research papers, particularly in machine learning, deep learning, or logical reasoning domains. This skill enables systematic research of academic benchmarks by searching web sources, downloading and analyzing arXiv papers, extracting key metadata (number of tasks, training availability, difficulty levels), and compiling comparative summaries. It triggers on requests involving dataset comparisons, benchmark analysis, or academic paper research for table creation.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
blog-writing
Write compelling blog posts with proven structure — hook openings, scannable body sections, clear CTAs. Use this skill when drafting blog posts, articles, or content marketing pieces.