Concept Map GeneratorSAFE

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: concept-map-generator
description: "Generate structured concept maps from academic texts automatically"
metadata:
  openclaw:
    emoji: "🧠"
    category: "tools"
    subcategory: "knowledge-graph"
    keywords: ["concept map", "knowledge representation", "text mining", "ontology", "semantic extraction", "mind map"]
    source: "wentor-research-plugins"
---

# Concept Map Generator

A skill for automatically generating structured concept maps from academic texts, lecture notes, and research papers. Covers concept extraction using NLP techniques, relationship identification, hierarchical organization, and export to visual formats. Concept maps differ from mind maps in that they explicitly label relationships between concepts, making them more suitable for representing scientific knowledge.

## Concept Map Fundamentals

### Structure of a Concept Map

A concept map consists of three elements: concepts (nodes), linking phrases (labeled edges), and propositions (concept-link-concept triples that form meaningful statements).

```
Concept Map Elements:

Concept: A perceived regularity or pattern designated by a label.
  Examples: "DNA replication", "enzyme", "natural selection"
  Representation: boxes or ovals containing short noun phrases

Linking Phrase: Words that connect two concepts to form a proposition.
  Examples: "is catalyzed by", "requires", "leads to", "is a type of"
  Representation: labeled arrows between concept nodes

Proposition: A meaningful statement formed by two concepts and a link.
  Example: [DNA replication] --requires--> [DNA polymerase]
  This reads: "DNA replication requires DNA polymerase"

Cross-links: Connections between concepts in different domains or
  branches of the map, showing integrative understanding.
```

### Concept Maps vs Mind Maps

```
Feature            Concept Map           Mind Map
--------------     ------------------    ------------------
Structure          Network (graph)       Tree (hierarchical)
Relationships      Labeled explicitly    Implied by proximity
Root node          May have multiple     Single central topic
Cross-links        Encouraged            Rare
Best for           Deep understanding    Brainstorming
Scientific use     Knowledge modeling    Idea generation
Reading direction  Follow arrow labels   Center outward
```

## Automated Concept Extraction

### NLP Pipeline for Extraction

```python
import spacy

def extract_concepts(text, nlp_model="en_core_web_sm"):
    """
    Extract candidate concepts from academic text using NLP.

    Strategy:
    1. Extract noun phrases as concept candidates
    2. Filter by frequency and specificity
    3. Merge overlapping spans
    4. Rank by TF-IDF relevance
    """
    nlp = spacy.load(nlp_model)
    doc = nlp(text)

    # Extract noun phrases
    candidates = []
    for chunk in doc.noun_chunks:
        # Remove determiners and leading adjectives for cleaner concepts
        clean = chunk.text.strip()
        if len(clean.split()) <= 4:  # Keep manageable length
            candidates.append(clean.lower())

    # Count frequencies
    from collections import Counter
    freq = Counter(candidates)

    # Filter: keep concepts mentioned at least twice
    concepts = [c for c, count in freq.most_common() if count >= 2]

    return concepts
```

### Relationship Extraction

```python
def extract_relationships(text, concepts, nlp_model="en_core_web_sm"):
    """
    Extract relationships between concepts using dependency parsing.

    Identifies verb phrases connecting known concepts in the same sentence.
    """
    nlp = spacy.load(nlp_model)
    doc = nlp(text)
    concept_set = set(concepts)

    triples = []
    for sent in doc.sents:
        sent_text = sent.text.lower()
        # Find which concepts appear in this sentence
        found = [c for c in concept_set if c in sent_text]

        if len(found) >= 2:
            # Extract the verb connecting them
            verbs = [token.lemma_ for token in sent
                     if token.pos_ == "VERB"]
            if verbs:
                for i in range(len(found)):
                    for j in range(i + 1, len(found)):
                        triples.append({
                            "source": found[i],
                            "target": found[j],
                            "relation": verbs[0],
                            "sentence": sent.text
                        })

    return triples
```

## Hierarchical Organization

### Building Concept Hierarchies

Academic concept maps benefit from hierarchical organization, placing the most general, inclusive concepts at the top and progressively more specific concepts below.

```
Hierarchy Construction Algorithm:

1. Identify superordinate concepts:
   - Concepts that appear in titles, abstracts, section headings
   - Concepts with the most outgoing relationships
   - Concepts that subsume other concepts (hypernyms)

2. Identify subordinate concepts:
   - Concepts that are instances or types of superordinates
   - Concepts with high specificity (long noun phrases)
   - Concepts that appear only in methods/results sections

3. Assign levels:
   Level 0: Domain (e.g., "machine learning")
   Level 1: Subdomains (e.g., "supervised learning", "unsupervised learning")
   Level 2: Methods (e.g., "random forests", "k-means clustering")
   Level 3: Details (e.g., "Gini impurity", "elbow method")

4. Add cross-links between branches:
   e.g., "random forests" --uses--> "bootstrap sampling"
         (links supervised learning to statistical methods)
```

### Strategies for Academic Papers

```
Input: Research paper
Output: Concept map organized by paper structure

Section-Based Extraction:
  Introduction -> Key concepts, research questions, theoretical framework
  Methods -> Methodological concepts, tools, techniques, variables
  Results -> Findings, measurements, statistical outcomes
  Discussion -> Interpretations, implications, limitations

Connection Types in Academic Maps:
  "is

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.