Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
concept-cartographer
Try itAuto-generate prerequisite maps for learning any topic — shows what to learn first, what depends on what, and the optimal learning path. Use when starting to learn something new and feeling lost about where to begin.
What it does
Concept Cartographer builds prerequisite maps for any topic. When you want to learn something new — say, "quantum computing" or "macroeconomics" — it maps out what you need to know first, what builds on what, and creates an optimal learning sequence. It eliminates the "where do I start?" paralysis…
The skill document
Concept Cartographer
Overview
Concept Cartographer builds prerequisite maps for any topic. When you want to learn something new — say, "quantum computing" or "macroeconomics" — it maps out what you need to know first, what builds on what, and creates an optimal learning sequence. It eliminates the "where do I start?" paralysis that stops most self-learners.
The tool constructs a directed acyclic graph (DAG) of concepts, identifies your current knowledge baseline, and generates a personalized learning path that respects prerequisite dependencies.
When to Use
- You want to learn a complex topic but don't know the prerequisites
- You're overwhelmed by the breadth of a new field and need a sequence
- You want to identify gaps in your knowledge before tackling an advanced topic
- You're planning a self-study curriculum for a new skill or domain
- Don't use for: single-task tutorials ("how to set up nginx") — use when the topic has a learning curve with multiple prerequisites
How It Works
- Concept Graph — Define topics and their prerequisites as a DAG
- Topological Sort — Compute valid learning orders that respect dependencies
- Knowledge Audit — Mark which concepts you already know
- Path Finding — Generate the shortest path from your current knowledge to the target
- Critical Path — Identify the longest prerequisite chain (the bottleneck)
- Export — Render the map as JSON, text tree, or Mermaid diagram for visualization
Quick Start
# Map prerequisites for a topic using the built-in knowledge base
python scripts/cartographer.py map "machine learning"
# Generate a learning path from your current knowledge
python scripts/cartographer.py path "machine learning" --known "python,basic-math,statistics"
# Visualize the concept map as a Mermaid diagram
python scripts/cartographer.py visualize "machine learning" --format mermaid
# Audit your knowledge — find gaps before starting
python scripts/cartographer.py audit "quantum computing" --known "linear-algebra,python"
# List all topics in the knowledge base
python scripts/cartographer.py topics
Built-in Knowledge Base
The tool ships with prerequisite maps for common domains:
- Programming: Python, JavaScript, SQL, Algorithms, Data Structures
- Math: Calculus, Linear Algebra, Statistics, Discrete Math
- ML/AI: Machine Learning, Deep Learning, NLP, Computer Vision
- Science: Physics, Chemistry, Biology, Quantum Computing
- Business: Economics, Accounting, Finance, Marketing
- Web: HTML, CSS, React, Node.js, Databases
You can also define custom concept graphs (see references/custom-graphs.md).
Workflow: Planning a Learning Journey
Step 1: Map the territory
python scripts/cartographer.py map "deep learning"
This shows the full prerequisite tree — everything you'd eventually need to know.
Step 2: Audit your current knowledge
python scripts/cartographer.py audit "deep learning" --known "python,linear-algebra,basic-statistics"
This highlights what you already know (✓), what you're missing (✗), and what's partially covered (~).
Step 3: Generate your personalized path
python scripts/cartographer.py path "deep learning" --known "python,linear-algebra" --output my_plan.json
This produces the optimal sequence, skipping what you know and focusing on gaps.
Step 4: Visualize
python scripts/cartographer.py visualize "deep learning" --format mermaid --output diagram.md
Paste the Mermaid output into any Markdown viewer to see the concept map.
Learning Path Output
🎯 Target: Deep Learning
📊 Current knowledge: 2 concepts (python, linear-algebra)
⏱️ Estimated new concepts to learn: 8
🛤️ Critical path length: 6 steps
LEARNING PATH:
1. ☐ Calculus (prerequisites: ✓) — derivatives needed for gradient descent
2. ☐ Probability (prerequisites: ✓) — foundational for ML
3. ☐ Statistics (prerequisites: ✓ probability)
4. ☐ Machine Learning Basics (prerequisites: ✓ python, ☐ statistics)
5. ☐ Neural Networks (prerequisites: ☐ ML basics, ☐ linear algebra ✓)
6. ☐ Deep Learning (prerequisites: ☐ neural networks)
└── 🎯 TARGET REACHED
Common Pitfalls
- Skipping prerequisites to save time. The critical path exists for a reason. Skipping calculus to learn ML leads to confusion and slower progress overall.
- Trying to learn everything at once. The path is sequential for a reason. Master each step before moving to the next.
- Overestimating your knowledge. Be honest in the audit. "I watched a YouTube video about it" ≠ "I know it."
- Ignoring the critical path. The longest dependency chain determines your minimum time to competence. Focus there first.
- Treating the map as gospel. Prerequisites are guidelines, not laws. Some people learn best non-linearly — adjust as you go.
Verification Checklist
-
cartographer.py map "machine learning"prints the prerequisite tree -
cartographer.py path "machine learning" --known "python"generates a learning sequence -
cartographer.py audit "quantum computing" --known "linear-algebra"shows gaps -
cartographer.py visualize "machine learning" --format mermaidproduces Mermaid syntax -
cartographer.py topicslists all topics in the knowledge base
References
references/custom-graphs.md— how to define your own concept mapsreferences/learning-theory.md— the cognitive science of prerequisite sequencing
Related skills
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Site audit, content writing, and competitor analysis for organic search rankings.
More from voronindenis5
Browse all skillsPryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.
Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.
Use when you realize your photos/code/documents exist in exactly one place (or your 'backup' is a external drive in the same room as the computer) — audits your actual data-loss risk against the 3-2-1 rule (3 copies, 2 media, 1 offsite) asset by asset, scores blast radius (ransomware encrypts synced copies too), prices honest recovery (professional recovery lab $300-3000 vs $0), generates the minimum-cost redundancy plan for YOUR asset list, and produces a restore-test drill because an untested backup is a hope, not a backup.
Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.
Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.