A curated ChatGPT and Codex distribution of MIT-licensed engineering, AI/ML, and productivity workflows, matured for automatic routing. It includes 42 focused Skills for requirements, specs, tickets, multi-agent spec implementation, TDD, debugging, review, session retrospectives, architecture, research, AI model development, data remediation, statistical ML best practices, J-space cognitive reasoning, autonomous goal contracts, skill conductor authoring, repository safety and setup, TypeScript package boundaries, workflow design, handoffs, teaching, course exercise scaffolding, and long-form writing. Host-specific duplicates and repository-development noise are excluded.
Install
- 1Add it in ChatGPT
Open Plugins in the ChatGPT sidebar (web or desktop), search for “Matt Skills Curated” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it.
Skills 15
- AI Data Remediation
Self-healing pipeline & data anomaly fixes
- AI Engineering
ML model training, fine-tuning, and serving
- Code Review
Review a diff on standards and spec
- Codebase Design
Vocabulary for deep-module design
- Diagnosing Bugs
Diagnose hard bugs and regressions
- Domain Modeling
Build and sharpen a domain model
- Engineering Workflow Guide
Route work to the right skill
- Git Safety Guardrails
Protect destructive git operations
- Goal Prompt Synthesis
Synthesize autonomous goal prompts and contracts
- Grill Me
Sharpen a plan through interview
- Grill with Docs
Grill a design and write its docs
- Grilling
Stress-test thinking a round of questions at a time
- Handoff
Compact a conversation into a handoff
- Implement
Build work from a spec or tickets
- Implement Spec
Implement a whole spec as one PR across task tickets
Things to ask
- “Choose the best engineering workflow for this task and execute it”
- “Turn this idea into a buildable engineering plan”
- “Diagnose this bug, fix it, and verify the result”
Related
SuperpowersPlan, develop, and debug codeplugin · by Jesse Vincent · 294k stars