Vibe Research
Verified@ivangdavila
npx machina-cli add skill @ivangdavila/vibe-research --openclawWhen to Use
User has a research question or knowledge gap. Agent takes ownership of the full research cycle: scanning literature, generating hypotheses, running analyses, synthesizing findings. Human provides direction and oversight, AI executes.
Quick Reference
| Topic | File |
|---|---|
| Research pipeline | pipeline.md |
| Risk mitigation | risks.md |
Core Concept
Traditional research: Human-led, human-executed
Deep research: Human-led, AI-assisted
Vibe research: Human-directed, AI-led
The human sets the question and validates outputs. The agent handles literature synthesis, hypothesis generation, data analysis, and write-up autonomously.
Core Rules
1. Full-Cycle Ownership
Agent executes the complete pipeline:
- Gap identification — What's unknown or contested?
- Literature synthesis — Scan, summarize, cross-reference sources
- Hypothesis generation — Propose testable claims
- Analysis design — Define methodology
- Execution — Run analyses, gather data
- Synthesis — Write findings with citations
2. Vision from Human, Execution from Agent
- Human provides: research question, domain constraints, success criteria
- Agent handles: reading papers, connecting ideas, running experiments, drafting
- Human validates: key decisions, final outputs, methodology choices
3. Transparent Reasoning
- Cite every claim: source, page, quote
- Show reasoning chain for hypotheses
- Log all analytical steps for reproducibility
- Flag confidence levels (high/medium/low)
4. Proactive Gap Detection
Don't wait for instructions. When analyzing a topic:
- Identify contradictions in literature
- Spot under-explored areas
- Suggest follow-up experiments if results are ambiguous
- Pull additional sources when context is insufficient
5. Hallucination Prevention
- Only claim what sources support
- Distinguish: "Source X says..." vs "I infer..."
- When uncertain, say so explicitly
- Cross-verify critical facts across multiple sources
Vibe Research Traps
- Treating AI output as ground truth → always require human validation of key findings
- Skipping methodology transparency → document every step for reproducibility
- Overwhelming human with raw output → synthesize into actionable insights
- Losing the human's analytical skills → keep them engaged in critical thinking
Overview
Vibe Research enables AI to conduct autonomous literature review, hypothesis generation, data analysis, and synthesis while humans provide vision and direction. It emphasizes transparent reasoning, source-backed claims, and reproducible steps, with proactive gap detection and risk mitigation.
How This Skill Works
The human defines the research question, domain constraints, and success criteria. The agent then scans literature, synthesizes sources, generates testable hypotheses, designs analyses, executes experiments, and drafts findings with citations. All steps are logged with reasoning chains and confidence levels to ensure reproducibility and traceability.
When to Use It
- When you have a knowledge gap and want the agent to own the full research cycle from literature review to synthesis.
- When you need AI-generated, testable hypotheses and an accompanying analysis plan.
- When transparency and traceability (citations, reasoning, step logs) are required for credibility.
- When you want proactive gap detection, contradictions, and suggested follow-up experiments.
- When outputs must be reproducible and human-validated before final decisions.
Quick Start
- Step 1: Define the research question, domain constraints, and success criteria.
- Step 2: Instruct Vibe Research to scan literature, synthesize sources, generate hypotheses, design analyses, and draft findings with citations.
- Step 3: Review outputs, validate key decisions, and finalize the write-up with source-linked citations.
Best Practices
- Define a precise research question, domain constraints, and explicit success criteria upfront.
- Require citations for every claim and demand a transparent reasoning chain linking sources to conclusions.
- Mandate step-by-step analysis logs and explicit confidence levels (high/medium/low).
- Encourage proactive gap detection and suggested follow-up experiments.
- Maintain human oversight for key decisions, final outputs, and the write-up.
Example Use Cases
- An academic literature review on a novel topic with AI-generated hypotheses and an analysis plan.
- Synthesis of evidence for a medical guideline update using cross-source validation.
- A technology landscape mapping that identifies trends, gaps, and corroborating sources.
- Cross-paper contradiction detection with proposed experiments to resolve tensions.
- A reproducible research report with full methodology, data sources, and citations.
