Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
Research methodology guidance covering literature review strategies, source evaluation using the CRAAP test, citation management, research question formulation, methodology selection (qualitative, quantitative, mixed methods), academic writing structure, and plagiarism avoidance.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
508 lines · 2,423 words
Use this skill when:
User needs to conduct research on a topic and wants a structured approach
User wants help finding, evaluating, or synthesizing sources
User needs to develop a research question or thesis statement
Research methodology guidance covering literature review strategies, source evaluation using the CRAAP test, citation management, research question formulation, methodology selection (qualitative, quantitative, mixed methods), academic writing structure, and plagiarism avoidance.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Research Advisor skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
What it covers
When to Use
Process
Purpose
Questions to Ask the User First
Research Question Formulation
Literature Review Strategies
Source Evaluation: The CRAAP Test
Methodology Selection
Citation Management
Academic Writing Structure
Avoiding Plagiarism
Research Timeline Template
Output Format
Example
Research Plan: Remote Work and Productivity
Edge Cases
Do NOT use this skill when:
User wants a complete paper written -- this skill guides research process, not ghostwriting
User needs data analysis help -- use data analysis skills
User wants a simple factual answer -- no research methodology needed
Step 1: Define research question, scope, and purpose (academic, professional, personal)
Step 2: Develop search strategy: databases, keywords, inclusion/exclusion criteria
Step 3: Evaluate source quality: credibility, recency, relevance, methodology
Step 4: Synthesize findings: identify themes, gaps, and connections across sources
Step 5: Organize findings into structured output (annotated bibliography, literature review, or summary)
This skill helps students and researchers at all levels navigate the research process from question formulation through publication. It provides structured frameworks for finding and evaluating sources, organizing research, selecting appropriate methodologies, and writing up findings in proper academic format.
Research stage: Where are you in the process? (Brainstorming, lit review, data collection, writing, revising)
Academic level: Undergraduate, graduate (masters/PhD), or professional research?
Discipline: What field? (Sciences, social sciences, humanities, engineering, business, etc.)
Assignment type: Research paper, thesis, dissertation, literature review, journal article, or other?
Topic area: What is your general topic or area of interest?
Research question: Do you have a specific research question yet?
Methodology exposure: Have you studied research methods? Are you comfortable with qualitative, quantitative, or mixed methods?
Timeline: When is this due? What milestones do you need to hit?
Citation style: What citation format is required? (APA, MLA, Chicago, IEEE, etc.)
Resources: Do you have access to academic databases (JSTOR, PubMed, Google Scholar, your institution's library)?
Advisor/instructor requirements: Are there specific requirements or guidelines you have been given?
RESEARCH QUESTION DEVELOPMENT WORKFLOW
========================================
STEP 1: START WITH A BROAD TOPIC
"Climate change" / "Social media" / "Healthcare access"
STEP 2: NARROW TO A FOCUSED TOPIC
Ask: Who? What? Where? When? Why? How?
"How does social media use affect academic performance in college students?"
STEP 3: EVALUATE YOUR QUESTION
A good research question is:
[ ] Specific (not too broad, not too narrow)
[ ] Answerable (can be investigated with available methods and data)
[ ] Relevant (contributes to the field, has practical or theoretical value)
[ ] Original (not already fully answered in existing literature)
[ ] Complex (cannot be answered with a simple yes/no)
[ ] Ethical (can be researched without harm)
# ... (condensed) ...
EXAMPLE:
Topic: Social media and academic performance
Main RQ: "How does daily social media usage duration affect GPA among
undergraduate students at U.S. universities?"
Sub-Q1: "What is the average daily social media usage among undergraduates?"
Sub-Q2: "Is there a correlation between usage duration and GPA?"
Sub-Q3: "Does the type of social media platform moderate this relationship?"LITERATURE SEARCH PROTOCOL
============================
STEP 1: IDENTIFY KEY TERMS
Main concept 1: __________ (synonyms: __________)
Main concept 2: __________ (synonyms: __________)
Main concept 3: __________ (synonyms: __________)
STEP 2: BUILD SEARCH STRINGS
Use Boolean operators:
AND: Narrows results (social media AND academic performance)
OR: Broadens results (social media OR social networking)
NOT: Excludes terms (social media NOT marketing)
" ": Exact phrase ("academic performance")
*: Wildcard (educat* finds education, educational, educator)
Example search string:
("social media" OR "social networking") AND ("academic performance" OR GPA)
# ... (condensed) ...
STEP 6: SCREEN AND SELECT
Screening criteria:
[ ] Published in a peer-reviewed journal
[ ] Published within the last 5-10 years (unless seminal work)
[ ] Relevant to your research question
[ ] Adequate methodology
[ ] Accessible (full text available)SOURCE TRACKING TABLE
======================
Author(s) | Year | Title | Journal | Key Findings | Method | Relevance | Notes
___________|______|________________|_______________|______________|________|___________|______
___________|______|________________|_______________|______________|________|___________|______
___________|______|________________|_______________|______________|________|___________|______
THEMATIC ORGANIZATION:
Theme 1: __________
Sources supporting: __________
Sources contradicting: __________
Gap identified: __________
Theme 2: __________
Sources supporting: __________
Sources contradicting: __________
Gap identified: __________
Theme 3: __________
Sources supporting: __________
Sources contradicting: __________
Gap identified: __________
YOUR RESEARCH FILLS THIS GAP: __________CRAAP TEST FOR SOURCE EVALUATION
==================================
C - CURRENCY
When was it published or last updated? __________
Is the information current for your topic? ___
Do the links work (for web sources)? ___
Score (1-5): ___
R - RELEVANCE
Does it relate to your research question? ___
Who is the intended audience? __________
Is it at the appropriate level (not too basic, not too advanced)? ___
Have you looked at multiple sources before choosing this one? ___
Score (1-5): ___
A - AUTHORITY
Who is the author? __________
# ... (condensed) ...
TOTAL SCORE: ___ / 25
20-25: Excellent source
15-19: Good source (note any weaknesses)
10-14: Questionable source (use cautiously, corroborate)
Below 10: Do not use as a primary source| Source Type | Reliability | When to Use |
|---|---|---|
| Peer-reviewed journal articles | Highest | Primary sources for academic research |
| Government reports and data | Very high | Statistics, policy, demographic data |
| Academic books (university press) | High | Foundational concepts, in-depth analysis |
| Conference proceedings | High | Cutting-edge research, recent findings |
| Reputable news sources | Moderate | Current events, public opinion context |
| Professional/industry reports | Moderate | Applied/practical data |
| Dissertations and theses | Moderate | Detailed methodology examples, niche topics |
| Wikipedia | Low (for citation) | Starting point only; follow its references |
| Blogs, social media | Low | Public discourse analysis only |
| Predatory journals | Very low | AVOID -- Google "Beall's List" to identify |
METHODOLOGY DECISION TREE
===========================
What is your research question asking?
"How many?" / "How much?" / "Is there a relationship?"
--> QUANTITATIVE
- Surveys, experiments, statistical analysis
- Produces numerical data
- Tests hypotheses
- Large sample sizes
- Generalizable results
"What is the experience of?" / "How do people make meaning?"
--> QUALITATIVE
- Interviews, focus groups, observation, document analysis
- Produces text/narrative data
- Explores and describes phenomena
- Smaller, purposeful samples
- Rich, deep understanding
"Both -- understanding the relationship AND the experience"
--> MIXED METHODS
- Combines quantitative and qualitative
- Sequential (one then the other) or concurrent (simultaneously)
- Provides breadth AND depth
- More complex to design and executeQUANTITATIVE METHODS
=====================
EXPERIMENTAL:
- Random assignment to treatment/control groups
- Manipulates an independent variable
- Measures effect on dependent variable
- Strongest evidence for causation
QUASI-EXPERIMENTAL:
- No random assignment (uses existing groups)
- Pre/post test designs
- Weaker causal claims
CORRELATIONAL:
- Measures relationship between variables
- Does NOT establish causation
- Survey-based, observational
DESCRIPTIVE:
- Describes characteristics of a population
- Frequencies, percentages, means
- Surveys, census data
DATA ANALYSIS: t-tests, ANOVA, regression, chi-square, correlationQUALITATIVE METHODS
=====================
PHENOMENOLOGY:
- Explores lived experiences of a phenomenon
- In-depth interviews (typically 5-25 participants)
- Analysis: identify themes and essences
GROUNDED THEORY:
- Develops theory from data (bottom-up)
- Iterative data collection and analysis
- Theoretical sampling
CASE STUDY:
- Deep investigation of a specific case (person, program, event)
- Multiple data sources (interviews, documents, observations)
- Bounded by time and context
ETHNOGRAPHY:
- Studies culture of a group through immersion
- Extended observation and participation
- Thick description
NARRATIVE INQUIRY:
- Explores experiences through stories
- Life histories, oral histories
- Focuses on meaning-making
DATA ANALYSIS: Coding, thematic analysis, constant comparisonAPA (7th Edition) -- Social Sciences
In-text: (Smith, 2024) or Smith (2024)
Reference: Author, A. A. (Year). Title of work. Publisher. DOI
MLA (9th Edition) -- Humanities
In-text: (Smith 45) -- author + page number
Works Cited: Author. Title. Publisher, Year.
Chicago/Turabian -- History, some humanities
Notes-Bibliography: Footnotes + bibliography
Author-Date: Similar to APA
IEEE -- Engineering, Computer Science
In-text: [1], [2], [3] -- numbered references
Reference: [1] A. Author, "Title," Journal, vol. X, pp. Y-Z, Year.
AMA -- Medical Sciences
In-text: Superscript numbers¹
Reference: Author(s). Title. Journal. Year;Volume(Issue):Pages.RECOMMENDED CITATION MANAGERS
===============================
Tool | Free? | Best For | Key Feature
Zotero | Yes | All disciplines | Browser extension, group libraries
Mendeley | Yes | Sciences, social sci| PDF annotation, social features
EndNote | Paid | Sciences, medical | Institutional integration
RefWorks | Varies| Institutional users | Web-based, institutional access
BibTeX/LaTeX | Free | STEM, technical | Integrates with LaTeX typesetting
SET UP EARLY: Start managing citations from day one of your research.
Adding citations retroactively is painful and error-prone.STANDARD RESEARCH PAPER STRUCTURE
====================================
TITLE
- Concise, descriptive, includes key variables
- Avoid unnecessary words ("A study of...")
ABSTRACT (150-300 words)
- Purpose, method, key findings, conclusion
- Write this LAST even though it appears first
INTRODUCTION
1. Hook/context: Why does this topic matter?
2. Background: What is known about this topic?
3. Gap: What is NOT known or what is the problem?
4. Purpose: What does THIS study address?
5. Research question(s) or hypothesis(es)
6. Significance: Why does this research matter?
# ... (condensed) ...
- Brief summary of key findings
- Restate significance
- Final thought or call to action
REFERENCES
- Every source cited in text must appear here (and vice versa)
- Formatted in the required citation stylePLAGIARISM PREVENTION GUIDE
=============================
WHAT COUNTS AS PLAGIARISM:
[ ] Copying text without quotation marks and citation
[ ] Paraphrasing without citation (even if words are changed)
[ ] Using someone else's ideas without attribution
[ ] Self-plagiarism (submitting your own previous work as new)
[ ] Patchwork plagiarism (combining phrases from multiple sources)
[ ] Having someone else write your paper
HOW TO AVOID IT:
1. WHEN QUOTING (exact words):
Use quotation marks + in-text citation + page number
"The results were statistically significant" (Smith, 2024, p. 15).
2. WHEN PARAPHRASING (your words, their idea):
# ... (condensed) ...
4. Compare to the original to ensure you haven't accidentally copied phrasing
5. Add the citation
TOOLS:
- Turnitin / iThenticate (plagiarism detection -- check before submitting)
- Grammarly (has a plagiarism checker)
- Your own careful attention is the best toolRESEARCH PROJECT TIMELINE
===========================
Total time available: ____ weeks
Weeks 1-2: EXPLORATION
[ ] Explore broad topic area
[ ] Conduct preliminary literature search
[ ] Formulate research question
[ ] Meet with advisor/instructor for approval
Weeks 3-5: LITERATURE REVIEW
[ ] Systematic literature search
[ ] Read and annotate key sources (aim for 15-30 sources)
[ ] Organize sources thematically
[ ] Draft literature review section
Weeks 5-7: METHODOLOGY
[ ] Select research method
# ... (condensed) ...
Weeks 14-16: REVISION
[ ] Self-edit for clarity, logic, and grammar
[ ] Peer review (have someone else read it)
[ ] Advisor/instructor review
[ ] Final revisions
[ ] Format check (margins, citations, page numbers)
[ ] SubmitWhen advising on research, provide:
Stage assessment -- Where the user is in the research process
Research question evaluation -- Is it specific, answerable, and original?
Search strategy -- Databases, search terms, and Boolean strings to use
Source evaluation -- CRAAP analysis for any sources shared
Methodology recommendation -- Appropriate method with reasoning
Writing guidance -- Structure and organization for their specific paper type
Timeline -- Milestones with dates based on their deadline
Common pitfalls -- What to watch out for at their current stage
Next steps -- Top 3 actions to take this week
Input: "I need to research the effects of remote work on employee productivity for a college term paper. I have no idea where to start."
Output:
"How does remote work affect employee productivity compared to in-office work, and what factors moderate this relationship?"
| Database | Keywords | Filters |
|---|---|---|
| Google Scholar | "remote work" AND "productivity" AND "employee" | 2019-2024, peer-reviewed |
| JSTOR | "telecommuting" AND "performance" | Management journals |
| PsycINFO | "work from home" AND "output" | Empirical studies |
For each source, rate: peer-reviewed (Y/N), sample size, methodology (survey/experiment/meta-analysis), recency, relevance to your specific question.
Productivity metrics used (self-reported vs. objective output)
Industry/role differences
Moderating factors (home environment, management style, job type)
Pre-COVID vs. post-COVID findings (context shift)
Introduction + research question
Literature review organized by theme (not source-by-source)
Analysis of conflicting findings
Conclusion with identified gaps for future research
Start with one meta-analysis for overview, then 4 empirical studies covering different industries.
Incomplete information: Ask clarifying questions before proceeding. Do not assume details the user has not provided.
Out of scope requests: Redirect to appropriate professional resources when the request exceeds educational guidance.
Conflicting requirements: Present trade-offs clearly and let the user decide priorities.
SKILL.md
508 lines · 2,423 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Research Advisor bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for