- Home
- Skills
- Research & Analysis
- consensus map
consensus map
Map the landscape of expert disagreement and evidentiary consensus without manufacturing a false middle ground.
Free
Works with the AI Agents you already use
consensus map
Example session with this skill installed
Map the consensus and disagreement regarding the impact of four-day work weeks on employee productivity based on the provided studies from 2022 to 2024.
- Read your context and instructions
- Compiled the consensus map
I have analyzed the four studies provided, focusing on the differences in their measurement methodologies and participant populations.
Productivity Consensus Map
| Claim | Support | Challenge | Reason for Disagreement | Strength/Limits |
|---|---|---|---|---|
| Individual output increases | Henley (2023), 4DGA (2022) | TechFocus (2024) | Henley measured call centers; TechFocus measured dev teams. | High for task-based roles; low for creative roles. |
| Burnout reduction is universal | All four sources | None | Consistent reporting across all sectors and geographies. | Broadly supported across all inspected sources. |
| Revenue growth correlates to 4D | 4DGA (2022) | Academic Review (2023) | 4DGA used self-reported data; Academic Review noted selection bias. | Disputed; needs controlled longitudinal study. |
| Communication overhead increases | TechFocus (2024) | Henley (2023) | Different definitions of "productivity" (output vs. collaboration). | Insufficiently studied in non-tech environments. |
Conclusion
There is broad consensus that a four-day week reduces burnout. However, claims regarding productivity are disputed due to a lack of shared definitions. Sources measuring rote tasks show gains, while sources measuring collaborative software engineering show increased friction and overhead. The "productivity" boost is likely role-dependent rather than a universal outcome.
Next steps
- Filter the map specifically for the "Service Sector" to see if the gains hold.
- Search for 2024 data on collaboration friction to update the communication claim.
- Identify if the Academic Review's bias claim applies to the Henley study.
Connects securely to your tools. The creator never sees your data.
About this skill
Research projects often fail by forcing a middle-ground consensus or presenting a laundry list of conflicting links. This skill maps the landscape of technical and academic disagreement without manufacturing a false narrative. It helps you understand where sources actually collide and where they are simply talking about different things.
What it does
- Claim extraction breaks down complex topics into specific, testable claims that sources can directly address.
- Source tracking identifies shared underlying data to prevent redundant reporting from counting as independent agreement.
- Conflict analysis distinguishes between disagreements over facts, definitions, forecasts, or underlying values.
- Evidence weighting prioritizes methodology and sample size over the sheer volume of articles or social media popularity.
- Status classification labels findings as broadly supported, disputed, or insufficiently studied based on the evidence pool.
How it works
- Define the scope by establishing the specific question, geography, and time window for the research.
- Gather evidence from distinct source families to ensure a diverse set of primary data and credible analyses.
- Map the claims by recording specific passages from supporting and challenging sources for each point.
- Compare methodologies to determine if contradictions are real or just a result of different measurement techniques.
- Generate the map using the standardized output format to visualize the state of the debate.
Frameworks & tools
This skill is framework-agnostic and works with any agent capable of web search or document analysis. It is designed for deep research workflows in Claude, GPT-4o, or Grok.
Why this beats prompting it yourself
Standard prompts often suffer from "both-sidesism" or hallucinate a consensus that does not exist. This skill enforces a rigorous evidentiary framework that weighs source quality and tracks data lineage to avoid echo chambers.
Use cases
- Analyze conflicting scientific studies to find the variables that cause different results.
- Map the debate on emerging technologies where experts disagree on timelines and risks.
- Compare policy impact reports across different regions and economic models.
- Audit market research reports to identify where data is shared vs. independently gathered.
Known limitations
This skill will not activate for single-source summaries. It requires a set of diverse sources to function. It does not use social media engagement as a metric for evidence weight.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Requires multiple sources to function. Cannot be used for single-document summaries. Does not use social media metrics as evidence weight. Search coverage affects the finality of conclusions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 24 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected