project-workshop-generator
Skill4 starsChanged 3 months agoMITView on GitHub
A universal workshop generator that analyzes ANY codebase to create structured onboarding material (Markdown + Remotion scripts). It automatically identifies the tech stack, project goals, and setup procedures to produce tailored training for developers and managers. Use when a user says "create a workshop", "generate onboarding docs", "explain this project to the team", or "make a video presentation" for any repository. Outputs -> structured Markdown workshop + Remotion slide script.
- Reads credentials
In this repository4 other files it gives its agents.
- ai-act-auditSkill
- privacy-auditSkill
- store-listingSkill
- store-review-preflightSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Before generating any content, the agent MUST:
- Very specific: line 16
Identify Stack: Check for package.json (JS/TS), requirements.txt/pyproject.toml (Python), Cargo.toml (Rust), go.mod (Go), etc.
- Very specific: line 17
Identify Architecture: Look for src/, app/, lib/, migrations/, docker-compose.yml, or kubernetes/ directories.
- Very specific: line 18
Extract Vision: Read README.md, docs/, or any high-level architecture diagrams to understand the "Why" and "Who" of the project.
- Distinctive: line 22
ALWAYS generate the workshop using this universal 5-module framework, tailored to the discovered data:
- Distinctive: line 56
Use the project's name as the main title.
- Distinctive: line 57
Create slides for each module using the data extracted during the discovery phase.
- Distinctive: line 58
Ensure the template is valid React/Remotion code.
- Distinctive: line 62
Language: DEFAULT to the language of the README.md or the user's prompt.
- Distinctive: line 63
Agnosticism: Never assume a specific technology (like Supabase or GitHub) unless you have confirmed its presence in the current repository.
- Distinctive: line 64
Self-Correction: If documentation is missing, the skill should guide the user on how to provide the missing context before generating the …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Universal Project Workshop Generator
This skill transforms any repository into a comprehensive 5-module workshop. It is stack-agnostic and adapts its content based on the identified architecture and project type.
Workflow
1. Project Discovery (MANDATORY)
Before generating any content, the agent MUST:
- Identify Stack: Check for
package.json(JS/TS),requirements.txt/pyproject.toml(Python),Cargo.toml(Rust),go.mod(Go), etc. - Identify Architecture: Look for
src/,app/,lib/,migrations/,docker-compose.yml, orkubernetes/directories. - Extract Vision: Read
README.md,docs/, or any high-level architecture diagrams to understand the "Why" and "Who" of the project.
2. Workshop Structure
ALWAYS generate the workshop using this universal 5-module framework, tailored to the discovered data:
- Module 0: Prerequisites Check
- Required software versions
- Access/credentials needed
- Expected attendee skill level (beginner / mid / senior)
- Module 1: Vision & Strategy (Management focus)
- Context: Project goals, target users, and key value proposition.
- Business Impact: ROI or strategic importance identified from documentation.
- Module 2: Technical Deep Dive (Developer focus)
- System Architecture: High-level overview of the identified stack and components.
- Data Flow: Explanation of how the core feature works (e.g., Request -> Controller -> DB).
- Module 3: Setup & Configuration (Hands-on)
- Environment: Toolchain installation (e.g., "Install pnpm and Docker").
- Bootstrap: Step-by-step commands to get the project running locally.
- Secrets: List of required environment variables found in
.env.exampleor config files.
- Module 4: Usage & Workflow (Standard users)
- Main Features: How to use the primary functionality of the project.
- Dev Workflow: How to run tests, linting, and build commands.
- Module 5: Practical Exercises (Labs)
- The Lab: Generate 2-3 exercises at different difficulty levels:
- Easy: reproduce an existing feature
- Medium: add a small new feature
- Hard: debug a broken scenario
- The Lab: Generate 2-3 exercises at different difficulty levels:
Remotion Video Scripting
Generate a generic workshop-video.tsx that acts as a slide deck.
- Use the project's name as the main title.
- Create slides for each module using the data extracted during the discovery phase.
- Ensure the template is valid React/Remotion code.
Guidelines
- Language: DEFAULT to the language of the README.md or the user's prompt. If none is detectable, use English.
- Agnosticism: Never assume a specific technology (like Supabase or GitHub) unless you have confirmed its presence in the current repository.
- Self-Correction: If documentation is missing, the skill should guide the user on how to provide the missing context before generating the workshop.
- Accuracy: Base setup instructions ONLY on actual files found in the repo (e.g., don't suggest
npm installif there's only ayarn.lock).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

