AI, ML, and Model Platforms Skills
AI, ML, and Model Platforms Skills
Section titled “AI, ML, and Model Platforms Skills”Skills for model APIs, ML platforms, training workflows, and AI product integration.
Use this category when you know the broad job but still need to decide which skill is worth invoking. Start from the task, then check the source, dependency, first run, and exit conditions.
Skills in this category
Section titled “Skills in this category”| Skill | Best for | Source |
|---|---|---|
| Gemini API Dev Skill | Provides best practices for developing Gemini-powered apps with the Gemini API. | officialskills.sh |
| Vertex AI API Dev Skill | Guides Gemini-powered app development on Google Cloud Vertex AI. | officialskills.sh |
| Hugging Face CLI Skill | Uses the Hugging Face CLI for Hub operations. | officialskills.sh |
| Hugging Face Model Trainer Skill | Trains models with TRL workflows such as SFT, DPO, GRPO, and GGUF conversion. | officialskills.sh |
| Replicate Skill | Discovers, compares, and runs AI models through Replicate. | officialskills.sh |
How to choose
Section titled “How to choose”- Build against fast-moving model APIs with provider-specific constraints.
- Run ML platform workflows without losing track of credentials and artifacts.
- Compare model or platform choices through concrete tasks.
Avoid this category when
Section titled “Avoid this category when”- The task needs current model pricing or policy and the source has not been checked.
- Sensitive datasets would be uploaded without review.
- The expected result is scientific validation rather than workflow guidance.
Decision table
Section titled “Decision table”| Check | Guidance |
|---|---|
| Main dependency | Model provider account, API key, dataset, or SDK context |
| Best first use | Use a small example request, dataset, or model operation before production workflows. |
| Smallest safe scope | Start with a low-risk example, preview environment, small file, or read-only target so the result can be reviewed. |
| When to switch | If the task falls outside this category’s real boundary, go back to the Awesome Skills overview and choose a closer category. |
Reading order
Section titled “Reading order”- Gemini API Dev Skill - Provides best practices for developing Gemini-powered apps with the Gemini API.
- Vertex AI API Dev Skill - Guides Gemini-powered app development on Google Cloud Vertex AI.
- Hugging Face CLI Skill - Uses the Hugging Face CLI for Hub operations.
- Hugging Face Model Trainer Skill - Trains models with TRL workflows such as SFT, DPO, GRPO, and GGUF conversion.
- Replicate Skill - Discovers, compares, and runs AI models through Replicate.
Nearby categories
Section titled “Nearby categories”- Browser, Testing, Quality - Skills for browser automation, local app checks, Core Web Vitals, accessibility, and web quality review.
- Frontend and Design - Skills for UI composition, framework patterns, design reviews, and frontend implementation decisions.
- Deployment and Platform Ops - Skills for deploying, configuring, and operating cloud platforms and hosting providers.
- Security and Review - Skills for threat modeling, static analysis, code review, and security-focused investigation.
Sources
Section titled “Sources”- VoltAgent Awesome Agent Skills: https://github.com/VoltAgent/awesome-agent-skills
- officialskills.sh: https://officialskills.sh/
- Agent Skills standard: https://agentskills.io/