技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
content-research-writer【数据与研究】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 argumentatio…
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
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.
STOP — Do NOT begin source discovery until the research plan is documented and scope is agreed upon.
STOP — Do NOT begin outlining until you have sufficient Tier 1-2 sources for every core claim.
STOP — Do NOT begin drafting until the outline is reviewed and evidence gaps are filled.
STOP — Do NOT move to review until all sections are drafted and all citations are in place.
| 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 |
| 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 |
| 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 |
# 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.
# 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
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
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
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]
| 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 |
| 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-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 |
| 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 |
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.