PrepKit is an advanced instructional framework based on the ADDIE model, specifically tailored for AI agents to design and develop elite training materials for informatics competitions like NOI, CSP, and GESP.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install prepkit
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install prepkit using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is PrepKit: Informatics Olympiad Lesson Preparation Framework?
PrepKit is a specialized curriculum engineering framework designed to guide AI agents in creating highly engaging, high-quality teaching materials for informatics olympiad training (NOI/CSP/GESP). Rather than enforcing a rigid, one-size-fits-all lesson template, it provides multi-dimensional quality benchmarks, cognitive design rules tailored for 14-year-old high school students, and specialized narrative styles.
By leveraging this framework within Openclaw Skills, AI agents can dynamically determine the most effective presentation structure based on the specific computer science concept being taught. It balances meticulous instructional analysis with creative execution, ensuring that lectures, slides, code examples, and problem sets remain pedagogically sound, logical, and highly interactive.
PrepKit: Informatics Olympiad Lesson Preparation Framework Use Cases
- Preparing lesson plans, lecture notes, and presentation slides for NOI, CSP, and GESP informatics olympiad courses.
- Generating structured C++ programming problem sets and homework exercises featuring embedded narrative world-building.
- Standardizing multi-level curriculum design spanning introductory, intermediate, and advanced competitive programming tracks.
- Refining AI-generated technical materials to remove repetitive patterns, improve formatting consistency, and optimize content for offline or domestic network compatibility.
How PrepKit: Informatics Olympiad Lesson Preparation Framework Works
- Analysis Phase: The AI agent processes the user's specific lesson requirements, identifying the exact target audience, target competition level (Entry-level, Raised-level, or NOI-level), and prerequisite knowledge.
- Design Phase: The agent structures a cohesive narrative storyline, maps out an emotional engagement curve, and maps the chronological flow of core technical concepts.
- Development Phase: The agent produces fully populated lecture assets (Marp Markdown or HTML handouts), embedded example code solutions, and differentiated assignments.
- Implementation Phase: Detailed tracking mechanics record classroom execution parameters and student engagement notes.
- Evaluation Phase: The agent measures lesson outcomes against built-in quality checklists to continually refine future content iterations.
PrepKit: Informatics Olympiad Lesson Preparation Framework Setup
To integrate this framework into your Openclaw ecosystem, place the underlying SKILL.md file along with its companion modules into your active agent skill repository.
# Navigate to your agent skills repository
cd openclaw-agent/skills/
# Create a target directory for the preparation kit framework
mkdir -p prepkit/modules prepkit/references prepkit/assets
# Clone or move your localized modules into place
mv path/to/framework/modules/*.md prepkit/modules/
mv path/to/framework/references/*.md prepkit/references/
Ensure that the allowed tools (Read, Write, Edit, and AskUserQuestion) are properly initialized within your agent configuration protocol.
PrepKit: Informatics Olympiad Lesson Preparation Framework Data Schema & Taxonomy
PrepKit enforces a clean file hierarchy and system taxonomy to store metadata, track curriculum levels, and handle file delivery.
Taxonomy Matrix
| Level | Difficulty Range | Competition Target |
|---|---|---|
| Entry-Level | 1-5 | CSP-J, GESP Levels 1-4 |
| Raised-Level | 5-8 | CSP-S, GESP Levels 5-6 |
| NOI-Level | 7-10 | NOI, Provincial Selection |
Asset Handling Protocols
- Presentation Handouts: Slide decks formatted in Markdown must explicitly conclude with the suffix
_pptto be recognized and indexed by the database. - Supported File Types: System natively aggregates
.pdf,.html, and.mdformats. - Network Dependencies: Third-party assets must favor domestic-friendly CDNs like unpkg.com, explicitly avoiding cdjs or blocked jsDelivr endpoints to guarantee stable loading in isolated target networks.
PrepKit: Informatics Olympiad Lesson Preparation Framework Advanced Features
- ADDIE Workflow Adaptability: Supports complete multi-stage execution for comprehensive curriculum overhauls, as well as fast-track generation bypassing preliminary analysis if the client supplies pre-compiled constraints.
- Built-in Self-Iterative Loop: Includes automated feedback processing at the end of each stage module, allowing the AI agent to optimize its content generation parameters based on human corrections and edge-case errors.
- Integrated Narrative Universe: Features a unified characters framework (e.g., Teacher Feng, Principal Liu, Teacher Wang) to construct immersive, cohesive programming story problems across separate training modules.
- Human-centric Tuning Rules: Integrates explicit mitigation guidelines designed to eliminate generic AI phrases, monotonous formatting structures, and unassisted abstract code dumps.
SKILL.md
Loading
Related Openclaw Skills
agent-token-usage
A utility to accurately calculate, aggregate, and display cumulative LLM token usage across all OpenClaw agents, featuring a Python CLI and an optional Control UI analytics button.
Alibaba Cloud ECS Snapshot-Based Disaster Recovery Backup
An automated Alibaba Cloud ECS disaster recovery and backup automation agent skill for cross-AZ full-instance and disk-level recovery.
alibabacloud-pts-pilot
An execution-free performance testing router that intelligently intercepts user intents and delegates Alibaba Cloud PTS actions to dedicated sub-skills.
PPTX Add Slides
An advanced automation script that inserts new slides into existing PPTX files with 100% style and layout consistency by cloning slide XML elements.
AgentNOMOS Governance Preflight
A read-only governance preflight tool that evaluates proposed AI agent actions for authorization, boundaries, risks, and required evidence before execution.
AI-Generated Code Format Review
A dedicated Java formatting review skill designed to automatically audit and correct naming, comments, structure, and style discrepancies in AI-generated code.
Featured*
