AI Agent Skills

Explain a topic through a presentation that combines sky photography with translucent content cards. Useful for visual briefings with a calm, spacious atmosphere.

Show the same prompt across several interfaces, then assemble the results into a launch reel. Supply real examples that support the capability being shown.

Present a product interface on a device in a dark studio setting. Plan the scroll, key interaction and final brand frame around your actual interface.

Tell a product story through a prompt, streamed answer, follow-up action and final result inside an app interface. Plan the script around a real workflow.

Explain a software change through a fast view of the diff, a readable summary and capability scenes. Supply the actual change and the audience-facing result.

Organize analytics, customers, finances and planning inside a calm admin workspace. Define the real data and daily management tasks before building the views.

Style an authorized portrait with directional light, texture and deliberate empty space. Useful for a personal profile or an editorial portrait layout.

Objection-Reversal Launch Film is a video workflow available on Skillry. Its source catalog highlights Create Storyboard · Create Social Brand Video · Oversized Display Type · Accelerating Zoom Cuts · Dark Glass Cards. Compare the public examples with your brief before choosing this skill.

Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom mode…

Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase and N8N on…

Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-s

Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization…

Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire codebases, long logs, massive documents, or mult…

Use this to pick or switch the LLM behind a feature, based on evidence instead of hype or the newest release. Trigger on "which model should I use", "is GPT/Claude/Gemin…

Obsidian plugin for AI chat, workflow automation, and semantic search — supports Gemini, OpenAI, OpenRouter, Grok, Ollama, and CLI backends