- Home
- Skills
- Education & Learning
- Chalk: Fact-Checked Tutor Mode
More screenshots
Works with the AI Agents you already use
Chalk: Fact-Checked Tutor Mode
A pedagogical tutoring skill that uses active recall, anti-hallucination fact-checking, and structural diagrams.
Free
Chalk: Fact-Checked Tutor Mode
Example session with this skill installed
/chalk teach me about Singly Linked Lists. I have my style.md set to visual-learner.
- Read your context and instructions
- Compiled the chalk
I have loaded your style.md profile and initiated the teaching log. We are starting with Linked List basics.
Singly Linked List: The Chain Analogy
A Singly Linked List is a linear data structure where elements are not stored in contiguous memory locations. Think of it like a
treasure hunt: each clue tells you where the next clue is, but you can't jump to the middle without following the trail from the start.
Term Definition:
Node: The basic building block. It contains two things: the
Data (what you want to store) and a
Next Pointer (the address of the next node).
- Head: The very first node in the list. If you lose this, you lose the whole list.
Structural Diagram:
graph LR
Head --> A[Data: 10 | Next] --> B[Data: 20 | Next] --> C[Data: 30 | Next: NULL]
Active Recall Quiz:
If you are at the
Head node and you want to get to the third node, why can't you just "jump" there like you would with an Array index?
Next steps
- Answer the quiz question above to demonstrate understanding of sequential access.
- We will then implement a
Nodeclass in Python using your "brute force first" preference. - I will log this progress to
chalk-log.mdonce we finish the implementation.
Connects securely to your tools. The creator never sees your data.
About this skill
Technical educators and students often struggle with LLMs that prioritize agreeability over accuracy. Chalk is a pedagogical skill that replaces passive explanation with a rigorous teach-and-test loop designed to catch both student misconceptions and AI hallucinations. It transforms a standard chat into a structured tutoring environment that enforces active recall and cross-references claims against external ground truth.
What it does
- Active Recall Enforcement delivers small units of information followed by mandatory quizzes to ensure retention before moving forward.
- Anti-Hallucination Guardrails implement a two-tier fact-checking system, using subagents to verify high-stakes claims like Big-O complexity or formulas against real-world sources.
- Pedagogical Linting scans explanations for teaching-order bugs, ensuring all terms are defined and prerequisites are met before introducing complex topics.
- Structural Visualization generates ASCII or Mermaid diagrams for data structures, recursion call stacks, and pointer logic to provide mental models.
- Session Continuity maintains a detailed
chalk-log.mdto track quiz scores, open bugs in understanding, and specific "pick-up" points for future sessions.
How it works
- Initialize by typing
/chalkor "teach me [topic]" to trigger the learning loop and load yourstyle.mdpreferences. - Execute Loop by consuming one concept at a time, completing a mandatory "explain-it-back" gate or quiz before the next module unlocks.
- Verify Claims by requesting
/chalk check <claim>to trigger a subagent retrieval that attempts to refute the stated fact with external sources. - Sync Vault by pointing the agent to an Obsidian or local directory to incorporate existing notes into the context while flagging contradictions in those notes.
Frameworks & tools
This skill is optimized for Obsidian vaults and local Markdown environments. It uses Mermaid for diagramming and requires an agent capable of tool-use for web retrieval and subagent spawning to handle high-stakes fact-checking.
Why this beats prompting it yourself
Standard prompts often fail to catch their own errors and tend to "dump" information rather than teaching it. Chalk forces the agent into a disciplined pedagogical structure that identifies the root cause of a student's mistake rather than just correcting the surface slip.
Use cases
- Master complex Data Structures and Algorithms with automated Big-O verification.
- Audit existing study notes for technical inaccuracies or missing prerequisites.
- Prepare for technical interviews using a spaced-repetition loop that targets weak spots.
Known limitations
Obscure facts without stable web sources may still result in plausible but incorrect claims. Tier 2 fact-checking requires an environment that supports subagent delegation and web access.
Obscure facts lacking stable online sources may still result in errors. Tier 2 verification requires an environment supporting subagent delegation and internet access.
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 any payment.
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 forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account