content-research-writer
Use when the user needs research methodology, long-form content creation, academic-style citations, fact-checking, or evidence-based writing with proper source attribution. Trigger conditions: whitepaper drafting, research article writing, source evaluation, citation management, fact-checking protocol, case study creation, evidence-based argumentation.
- Installs
- 82
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/pixel-process-ug/superkit-agents --skill content-research-writer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads content-research-writer automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Content Research Writer
Overview
Produce well-researched, authoritative long-form content with proper source attribution, structured argumentation, and evidence-based claims. This skill covers research methodology, source evaluation, citation management, outline construction, drafting workflows, fact-checking protocols, and publishing-ready formatting for articles, whitepapers, reports, and educational content.
Apply this skill whenever content must be backed by evidence, cited properly, and structured for credibility with expert audiences.
Multi-Phase Process
Phase 1: Research Planning
- Define the topic scope and target audience
- Identify key questions the content must answer
- Determine content type (article, whitepaper, case study, guide)
- Set word count target and depth level
- Establish credibility requirements (peer-reviewed, industry reports, primary data)
- Create a research timeline with milestones
STOP — Do NOT begin source discovery until the research plan is documented and scope is agreed upon.
Phase 2: Source Discovery and Evaluation
- Search academic databases (Google Scholar, PubMed, JSTOR, arXiv)
- Identify industry reports and authoritative publications
- Find primary sources (official documentation, datasets, specifications)
- Evaluate source credibility using the CRAAP test (see table below)
- Organize sources in a reference manager or structured format
- Extract key findings, statistics, and quotable passages
STOP — Do NOT begin outlining until you have sufficient Tier 1-2 sources for every core claim.
Phase 3: Outline and Structure
- Create a thesis statement or central argument
- Build hierarchical outline with main sections and subsections
- Map evidence to each section (which sources support which claims)
- Identify gaps requiring additional research
- Define transitions between sections for narrative flow
- Plan visual elements (tables, charts, diagrams, callouts)
STOP — Do NOT begin drafting until the outline is reviewed and evidence gaps are filled.
Phase 4: Drafting
- Write section by section following the outline
- Integrate citations as you write (never retrofit)
- Balance original analysis with supporting evidence
- Use topic sentences and clear paragraph structure
- Include concrete examples, data points, and case studies
- Write introduction last (after body is complete)
STOP — Do NOT move to review until all sections are drafted and all citations are in place.
Phase 5: Review and Fact-Check
- Verify every factual claim against its source
- Check all statistics for accuracy and context
- Ensure citations are complete and correctly formatted
- Review for logical consistency and argument strength
- Proofread for clarity, grammar, and style
- Have subject matter expert review if possible
Content Type Decision Table
| Content Type | Word Count | Research Depth | Audience | Citation Style |
|---|---|---|---|---|
| Blog article | 1,500-3,000 | Tier 2-3 sources | General | Inline links |
| Long-form article | 3,000-5,000 | Tier 1-3 sources | Informed readers | Parenthetical (APA) |
| Whitepaper | 3,000-8,000 | Tier 1-2 mandatory | Decision-makers | Footnotes or numbered |
| Case study | 1,000-2,500 | Primary + Tier 2 | Buyers | Inline attribution |
| Technical report | 5,000-15,000 | Tier 1 mandatory | Experts | IEEE or APA |
| Educational guide | 2,000-6,000 | Tier 1-3 mixed | Learners | Parenthetical |
Source Evaluation Framework (CRAAP Test)
| Criterion | Questions to Ask | Red Flags |
|---|---|---|
| Currency | When was it published? Updated? | > 5 years old for fast-moving topics |
| Relevance | Does it directly address your topic? | Tangential connection, different context |
| Authority | Who is the author? What are their credentials? | No author, no institutional affiliation |
| Accuracy | Is it supported by evidence? Peer-reviewed? | No citations, unverifiable claims |
| Purpose | Why does this exist? Inform, sell, persuade? | Strong commercial bias, advocacy without disclosure |
Source Tier System
| Tier | Source Type | Credibility | Use For |
|---|---|---|---|
| Tier 1 | Peer-reviewed journals, official standards | Highest | Core claims, statistics |
| Tier 2 | Industry reports (Gartner, McKinsey), textbooks | High | Market data, frameworks |
| Tier 3 | Reputable news outlets, official documentation | Good | Context, current events |
| Tier 4 | Expert blogs, conference talks, interviews | Moderate | Perspectives, opinions |
| Tier 5 | Social media, forums, Wikipedia | Low | Discovery only, never cite directly |
Citation Formats
Inline Citation Styles
# Parenthetical (APA-style)
Research shows that 73% of enterprises have adopted cloud-native architectures
(Smith & Johnson, 2025).
# Narrative
According to Smith and Johnson (2025), 73% of enterprises have adopted
cloud-native architectures.
# Footnote-style (Chicago)
Research shows significant cloud adoption.[^1]
[^1]: Smith, J., & Johnson, R. (2025). Cloud adoption trends.
*Journal of Cloud Computing*, 12(3), 45-62.
# Numbered (IEEE-style)
Research shows significant cloud adoption [1].
## References
[1] J. Smith and R. Johnson, "Cloud adoption trends," *J. Cloud Computing*,
vol. 12, no. 3, pp. 45-62, 2025.
Reference Format Templates
# Journal Article
Author, A. B., & Author, C. D. (Year). Title of article. *Journal Name*,
Volume(Issue), Pages. https://doi.org/xxxxx
# Book
Author, A. B. (Year). *Title of book* (Edition). Publisher.
# Website
Author or Organization. (Year, Month Day). Title of page. Site Name.
https://www.example.com/page
# Report
Organization. (Year). *Title of report* (Report No. XXX).
https://www.example.com/report.pdf
Content Structure Templates
Long-Form Article (2000-5000 words)
1. Hook / Opening Anecdote (100-200 words)
2. Context and Problem Statement (200-300 words)
3. Thesis / Key Insight (50-100 words)
4. Section 1: Background (400-600 words)
- Historical context
- Current state
- Key definitions
5. Section 2: Core Analysis (600-1000 words)
- Main argument with evidence
- Data and statistics
- Expert perspectives
6. Section 3: Implications (400-600 words)
- Practical applications
- Case studies
- Future outlook
7. Section 4: Counterarguments (200-400 words)
- Acknowledge limitations
- Address objections
8. Conclusion (200-300 words)
- Synthesize key findings
- Call to action or forward-looking statement
9. References
Whitepaper (3000-8000 words)
1. Executive Summary (300-500 words)
2. Introduction and Problem Statement (500-800 words)
3. Methodology (300-500 words)
4. Findings / Analysis (1500-3000 words)
- Section with data visualization
- Comparative analysis
- Case studies
5. Recommendations (500-1000 words)
6. Conclusion (300-500 words)
7. Appendices
8. References
Case Study (1000-2500 words)
1. Executive Summary (100-200 words)
2. Challenge / Problem (200-400 words)
3. Approach / Solution (300-600 words)
4. Implementation (300-500 words)
5. Results and Metrics (200-400 words)
6. Lessons Learned (200-300 words)
7. About [Company/Subject]
Writing Quality Checklist
Paragraph Level
- Each paragraph has a clear topic sentence
- Paragraphs are 3-6 sentences (avoid walls of text)
- Transitions connect paragraphs logically
- Evidence follows claims immediately
Sentence Level
- Vary sentence length (mix short and long)
- Active voice preferred over passive
- Avoid jargon without definition
- Concrete language over abstract
Document Level
- Introduction establishes the "so what" clearly
- Each section advances the central argument
- No unsupported claims
- Conclusion adds value (doesn't just repeat)
- Consistent tone and reading level throughout
Fact-Checking Protocol
Verification Steps
- Primary source check: Trace every claim back to its original source
- Cross-reference: Verify key facts with at least 2 independent sources
- Statistical validation: Check that numbers are current and in context
- Quote accuracy: Verify exact wording of all direct quotes
- Date verification: Confirm all dates and timelines
- Name and title check: Verify correct spelling and current titles
Common Fact-Checking Pitfalls
| Pitfall | Example | Prevention |
|---|---|---|
| Outdated statistics | "50% of..." from a 2018 study | Always note publication year, seek recent data |
| Misattributed quotes | Einstein didn't say most "Einstein quotes" | Trace to primary source document |
| Survivorship bias | "All successful companies do X" | Look for counterexamples |
| Correlation as causation | "Countries that eat chocolate win more Nobels" | Distinguish correlation from causation |
| Out-of-context numbers | "Revenue grew 500%" (from $1 to $5) | Always provide absolute numbers and context |
Research Tools
| Tool | Purpose | Best For |
|---|---|---|
| Google Scholar | Academic paper search | Peer-reviewed research |
| Semantic Scholar | AI-powered paper discovery | Finding related work |
| arXiv | Preprints | Cutting-edge CS/ML/Physics |
| PubMed | Medical/bio research | Health and life sciences |
| Statista | Statistics and market data | Industry data points |
| Wayback Machine | Historical web pages | Verifying past claims |
| Zotero / Mendeley | Reference management | Organizing sources |
| Perplexity | AI-assisted research | Initial discovery |
Anti-Patterns / Common Mistakes
| Anti-Pattern | Why It Fails | What To Do Instead |
|---|---|---|
| Claims without citations | Undermines credibility entirely | Cite every factual claim inline |
| Single-source assertions | One source can be wrong or biased | Cross-reference with 2+ independent sources |
| Citing secondary when primary exists | Telephone game distorts findings | Trace to and cite the original study |
| Writing introduction first | Leads to misalignment with body | Write body first, introduction last |
| Padding to reach word count | Readers detect filler immediately | Add depth or cut the target |
| Weasel words without specifics | "Some experts say" means nothing | Name the expert, cite the source |
| Retrofitting citations after drafting | Gaps in evidence go unnoticed | Integrate citations during writing |
| Ignoring counterarguments | One-sided work lacks credibility | Address objections explicitly |
| Paraphrasing too closely | Borderline plagiarism even with citation | Summarize in your own analytical voice |
| No conflict-of-interest disclosure | Erodes trust when discovered | Disclose sponsorship or affiliations upfront |
Anti-Rationalization Guards
- Do NOT skip the CRAAP test because "the source looks reputable" -- evaluate it formally.
- Do NOT use Tier 4-5 sources for core claims, regardless of convenience.
- Do NOT begin drafting without a completed outline with evidence mapped to sections.
- Do NOT publish without running the fact-checking protocol on every statistic and quote.
- Do NOT retrofit citations after writing -- integrate them as you draft.
Integration Points
| Skill | How It Connects |
|---|---|
seo-optimizer | Research content needs SEO-optimized titles, meta descriptions, and structured data |
content-creator | Research findings feed into marketing copy and social media content |
email-composer | Research summaries inform stakeholder update emails and executive briefings |
tech-docs-generator | Technical research follows similar source evaluation and citation practices |
llm-as-judge | Evaluate research content quality against rubric dimensions |
clean-code | Writing quality checklist parallels clean code principles for prose |
Skill Type
FLEXIBLE — Adapt research depth, citation formality, and structure to the content type and audience. Academic whitepapers demand Tier 1 sources and formal citations; blog posts may use a lighter approach. The fact-checking protocol and source evaluation framework are always recommended.
FAQ
What does the content-research-writer skill do?
Use when the user needs research methodology, long-form content creation, academic-style citations, fact-checking, or evidence-based writing with proper source attribution. Trigger conditions: whitepaper drafting, research article writing, source evaluation, citation management, fact-checking protocol, case study creation, evidence-based argumentation.
How do I install content-research-writer?
Run npx skills add https://github.com/pixel-process-ug/superkit-agents --skill content-research-writer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/content-research-writer/ (personal) or .claude/skills/content-research-writer/ (project).
Which AI agents can use content-research-writer?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is content-research-writer safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains content-research-writer?
It is published by pixel-process-ug in pixel-process-ug/superkit-agents. It has 82 recorded installs.
More from pixel-process-ug/superkit-agents
ui-ux-pro-max
pixel-process-ug/superkit-agents
Use when the user needs full UI/UX design intelligence — styles, palettes, fonts, UX guidelines, chart selection, and accessible, performant implementation across any supported stack. Triggers: user says "design", "UI", "UX", "color palette", "typography", "accessibility", "responsive design", "chart type", "style guide", building any user-facing interface.
frontend-ui-design
pixel-process-ug/superkit-agents
Use when designing UI components, creating component architectures, implementing responsive layouts, setting up design systems, or selecting state management solutions for frontend applications
reverse-engineering-specs
pixel-process-ug/superkit-agents
Open the skill to read its SKILL.md instructions.
canvas-design
pixel-process-ug/superkit-agents
Use when the user needs HTML Canvas, SVG graphics, data visualization, generative art, or interactive visual elements with D3.js or similar libraries. Triggers: user says "canvas", "SVG", "chart", "data visualization", "D3", "generative art", "animation", "interactive graphics", drawing on screen.
autonomous-loop
pixel-process-ug/superkit-agents
Open the skill to read its SKILL.md instructions.
mobile-design
pixel-process-ug/superkit-agents
Open the skill to read its SKILL.md instructions.
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.