Longitudinal Cross Sectional Research

Longitudinal and Cross-Sectional Research

Overview

Use this skill to turn a research target into a two-part deep research report:

1. Reconstruct how the subject emerged and evolved over time. 2. Compare the subject against the current field, competitors, or substitutes.

Prioritize causal explanation, narrative readability, and source-backed judgment over list-like summaries.

Fit Check

Use this skill when the user wants:

• a deep research report instead of a short answer
• both historical development and current competitive positioning
• analysis of a product, company, organization, technology, concept, or person
• a report that explains why key turning points happened, not just what happened

Do not stop at feature comparison tables. Explain how the subject got here and what that means now.

Workflow

1. Define the target and frame

Start by identifying:

• the exact research target
• the subject type: product, company, person, technology, concept, or organization
• the likely comparison set: direct competitors, close peers, indirect substitutes, or no clear peers

Adjust the comparison dimensions to fit the subject. For example, technical route matters more for protocols than for people, while career arc matters more for people than pricing.

2. Collect source material

Gather sources for both time depth and present-state comparison.

Prefer:

• official docs, company pages, release notes, papers, blogs, filings, and interviews
• reputable reporting and industry analysis
• community evidence for user sentiment when relevant

Always anchor claims with dates when the subject evolved over time. Mark any unverified or inferential statement clearly.

3. Write the longitudinal analysis first

Tell the story from origin to present. Cover:

• origin context: what problem, belief, or market condition gave rise to the subject
• founding or first-publication moment
• major milestones in chronological order
• turning points such as launches, pivots, funding, rewrites, leadership changes, partnerships, acquisitions, controversies, or adoption milestones
• decision logic at each major turning point when it can be inferred from evidence

Do not write a dry timeline. Build a narrative with cause and effect, constraints, and tradeoffs.

4. Choose the cross-sectional mode

Use one of these modes:

• No clear direct competitors: explain why the category is new, narrow, or hard to enter; then analyze likely substitutes and emerging challengers.
• One or two direct competitors: compare each one in depth.
• Three or more competitors: choose the three to five most representative ones and compare the rest briefly if needed.

Compare along dimensions that fit the target, such as:

• technical route or underlying method
• product shape, business model, or operating model
• target users and use cases
• strengths and obvious weaknesses
• pricing, scale, or resource base
• user sentiment and community reputation
• ecosystem position and likely trajectory

5. End with synthesis

Finish with a "Longitudinal-Cross-Sectional Synthesis" section that answers:

• What position does the subject occupy today?
• Which parts of that position come from historical path dependence?
• What opportunities and risks are most visible from the current landscape?
• What future direction is most likely, and which part is inference?

This section should add a fresh judgment, not just compress earlier sections.

Writing Standard

Write like a strong long-form reported analysis, not a management slide deck.

• Make readability the top priority.
• Use human language and concrete details.
• Ground judgment in evidence before interpretation.
• Separate confirmed facts from inference.
• Keep the longitudinal section narrative-driven.
• Keep the cross-sectional section analytical, but still readable and alive.

Output Shape

Default order:

1. Longitudinal analysis 2. Cross-sectional analysis 3. Longitudinal-Cross-Sectional Synthesis

Use tables only as support. The core analysis should stay in prose.

Reference

Read references/method.md when you need the full English prompt template, detailed dimension list, or the original reporting-style constraints.

Longitudinal and Cross-Sectional Research Method

Use this reference when the user wants the full prompt logic, a more detailed report scaffold, or a reusable prompt template.

Prompt Template

## Variable Definition

Research target = Hermes Agent

(Every mention of "research target" below refers to the subject defined above. When reusing this prompt, only replace the value on the right-hand side.)

---

You are a senior technical and business research analyst. Produce a complete deep research report on the research target using the longitudinal and cross-sectional method.

This method contains two dimensions:

### 1. Longitudinal Analysis

Along the time axis, reconstruct the full development of the research target from origin to the present.

Requirements:

1. Origin tracing
Explain the background that gave birth to it. Which technologies, ideas, unmet needs, or market conditions led to its emergence? Who were the founders, core contributors, or main drivers? What did the surrounding industry look like at the time?

2. Birth moment
State the first release, founding, launch, or publication date as clearly as possible, along with the target's earliest form and positioning.

3. Evolution path
Trace the key milestones in chronological order from origin to the present. Include, where relevant: major releases, funding events, team changes, strategic pivots, architectural shifts, adoption milestones, major partnerships, acquisitions, controversies, or crises.

4. Decision logic
At each major turning point, reconstruct the likely reasoning behind the decision whenever evidence permits. Why did the target choose path A instead of path B? What constraints or pressures shaped the choice?

5. Narrative requirement
Do not write a dry year-by-year list. Tell the development as a story with causality, context, and momentum. Pull in relevant people, events, and environmental factors whenever they help explain the arc.

---

### 2. Cross-Sectional Analysis

Take the current moment as the slice of analysis and compare the research target with peers, competitors, or substitutes in the same space.

First determine the competitive situation:

- Scenario A: No direct competitors.
If the target belongs to a genuinely new or highly unique category, skip one-by-one direct comparison. Instead explain why direct competitors are absent. Is the category too new, the barriers too high, or the market too small? From which direction are future challengers most likely to appear? Which indirect substitutes or previous-generation solutions are the closest reference points?

- Scenario B: A small number of competitors (one or two).
Compare each competitor in depth.

- Scenario C: A crowded field (three or more competitors).
Choose the three to five most representative competitors for detailed comparison and mention the rest briefly if useful.

Comparison dimensions should be adapted to the subject, but commonly include:

1. Core differences
- Technical route, core method, or underlying logic
- Product form, business model, or organizational model
- Target users, audience, and best-fit scenarios
- Core strengths and obvious weaknesses
- Pricing strategy, resource input, or scale

2. User perspective
What is actual user sentiment for each option? Which advantages and frustrations appear most often in communities, reviews, or practitioner discussions? Does real usage differ from official positioning?

3. Ecosystem position
What role does the research target play in the larger landscape? What gap does it fill, or whom does it compete against head-on?

4. Trend judgment
Based on the comparison, what is the likely direction of the research target in the competitive landscape? What are the clearest opportunities and risks?

---

### 3. Writing Style Requirements

This should not read like a cold consulting memo. Write a deep research piece that can carry a reader from beginning to end.

1. Prioritize readability.
Write like a strong long-form feature or reported analysis, with pacing and scene-setting where useful.

2. Let narrative drive the longitudinal section.
Explain why a breakout, pivot, or turning point happened when it did. Avoid note-like release histories.

3. Offer judgment, but only after evidence.
Facts first, interpretation second. Explicitly label any inference or uncertainty.

4. Use plain language.
Avoid empty business cliches. Prefer concrete details and examples.

5. Keep the comparison alive.
Do not turn the cross-sectional analysis into a text-only spec sheet. Explain how each competitor actually lives in the market and why users choose it.

---

### 4. Length Guidance

Adjust length to the complexity of the target.

- Longitudinal analysis: usually the main body, roughly 6,000 to 15,000 words when the assignment is truly deep.
- Cross-sectional analysis: roughly 3,000 to 10,000 words depending on the number of meaningful competitors.
- Synthesis: roughly 1,500 to 3,000 words with fresh integrated judgment.
- Full report: often 10,000 to 30,000 words for a full deep research deliverable.

Do not shorten the report at the cost of skipping important turning points.

---

### 5. Output Requirements

1. Present the longitudinal analysis first, then the cross-sectional analysis.
2. Keep the longitudinal section primarily narrative, not a bare list.
3. You may use a comparison table to support the cross-sectional section, but the core argument must stay in prose.
4. End with a "Longitudinal-Cross-Sectional Synthesis" section that combines historical arc and present-day competitive position into one judgment.
5. Cite sources or dates whenever possible.
6. If any information cannot be verified, label it as inference, rumor, or unverified rather than inventing certainty.

Subject Types

This method works well for:

• products and tools
• companies and organizations
• technical concepts, protocols, or frameworks
• notable people whose development arc matters

Adapt the comparison dimensions to the subject, but keep the core rule unchanged:

• Longitudinal analysis pursues time depth.
• Cross-sectional analysis pursues present-day breadth.
• The final synthesis turns both into judgment.