Skills

Bdistill Knowledge Extraction

@sickn33

Low Risk

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

evolution

@sickn33

Low Risk

This skill enables makepad-skills to self-improve continuously during development.

Devcontainer Setup

@sickn33

Low Risk

Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.

Earllm Build

@sickn33

Low Risk

Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.

Gha Security Review

@sickn33

Low Risk

Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.

Hugging Face Evaluation

@sickn33

Low Risk

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

imagen

@sickn33

Low Risk

AI image generation skill powered by Google Gemini, enabling seamless visual content creation for UI placeholders, documentation, and design assets.

Skill Check

@sickn33

Low Risk

Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

Azure AI Voicelive Java

@sickn33

Low Risk

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

Conversation Memory

@sickn33

Low Risk

Persistent memory systems for LLM conversations including

Repo Scan

@affaan-m

Low Risk

Agent skill: Repo Scan