Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.
.claude/skills/inno-paper-writing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | — | — |
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
This skill guides the creation of formal academic research papers that meet publication standards for IEEE and ACM conferences/journals. It ensures proper structure, formatting, academic writing style, and comprehensive coverage of research topics.
When asked to write a research paper:
Follow this standard academic paper structure:
1. Title and Abstract
- Concise title reflecting the main contribution
- Abstract: 150-250 words summarizing purpose, methods, results, conclusions
2. Introduction
- Motivation and problem statement
- Research gap and significance
- Main contributions (typically 3-5 bullet points)
- Paper organization paragraph
3. Related Work / Background
- Literature review of relevant research
- Comparison with existing approaches
- Positioning of current work
4. Methodology / Approach / System Design
- Detailed description of proposed method/system
- Architecture diagrams if applicable
- Algorithms or procedures
- Design decisions and rationale
5. Implementation (if applicable)
- Technical details
- Tools and technologies used
- Challenges and solutions
6. Evaluation / Experiments / Results
- Experimental setup
- Datasets or test scenarios
- Performance metrics
- Results presentation (tables, graphs)
- Analysis and interpretation
7. Discussion
- Implications of results
- Limitations and threats to validity
- Lessons learned
8. Conclusion and Future Work
- Summary of contributions
- Impact and significance
- Future research directions
9. References
- Comprehensive bibliography in proper citation formatApply these writing conventions from scholarly research:
Tone and Voice:
Technical Precision:
Argumentation:
Section-Specific Guidelines:
Abstract:
Introduction:
Related Work:
Results:
IEEE Format (default):
ACM Format (alternative):
In-text citations:
Reference formatting (IEEE style):
[1] A. Author, B. Author, and C. Author, "Title of paper," in Proc. Conference Name, Year, pp. 123-456.
[2] D. Author, "Title of journal article," Journal Name, vol. X, no. Y, pp. 123-456, Month Year.
[3] E. Author, Book Title, Edition. City: Publisher, Year.Reference list requirements:
Step-by-step approach:
After the paper draft is complete (all sections written, references listed), remind the user that citation verification is strongly recommended before finalizing:
inno-reference-audit skill from the skill library: read skills/inno-reference-audit/SKILL.md and follow its procedure when the user wants reference verification.[CITATION NEEDED] and move on. For every reference that cannot be verified:This step is recommended whenever references were added or revised. If the user skips verification, explicitly note that citations have not been audited.
Example 1: User asks for a survey paper
User: "Write a research paper surveying recent advances in context-aware systems"
Response:
1. Clarify scope: "I'll create a survey paper on context-aware systems. A few questions:
- Should I focus on specific aspects (e.g., requirements engineering, implementation techniques)?
- What time period for 'recent' (last 5 years, 10 years)?
- Target length: 10-15 pages, or 20-30 pages comprehensive survey?
- IEEE or ACM format?"
2. After clarification, create outline showing:
- Taxonomy of context-aware systems
- Survey methodology
- Classification scheme
- Section-by-section coverage of different aspects
- Trends and future directions
3. Draft paper following survey structure with extensive related work coverageExample 2: User asks for an experimental paper
User: "Write a paper about my new algorithm for detecting hallucinations in vision-language models"
Response:
1. Gather details about:
- Algorithm approach and novelty
- Experimental setup and datasets used
- Results and metrics
- Comparison baselines
2. Structure as experimental paper:
- Introduction: motivation for hallucination detection
- Related work: existing detection methods
- Proposed method: detailed algorithm description
- Experiments: datasets, metrics, setup
- Results: quantitative comparison with baselines
- Analysis: ablation studies, error analysis
- Conclusion: contributions and future work
3. Emphasize reproducibility and empirical validationwriting_style_guide.md: Detailed academic writing conventions extracted from example papersieee_formatting_specs.md: Complete IEEE formatting specificationsacm_formatting_specs.md: Complete ACM formatting specificationsfull_paper_template.pdf: IEEE paper template with formatting examplesinterim-layout.pdf: ACM paper template| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.