Agent Skills by Christian M
Showing 32 vetted skills indexed across 1 GitHub repositories.
docker-open-webui-deploy
Deploy Open-WebUI via Docker or Python venv with port mapping and data persistence.
model-manager-gui-spec
Serve a lightweight GUI on port 8081 for model load/unload and GPU metrics via llama.cpp router proxying.
ssrn-search
Search SSRN papers via Google Scholar snippets and OpenAlex metadata.
router-troubleshooting
Diagnose and recover M5 router startup failures by cleaning INI entries and terminating rogue processes.
openwebui-clear-embedding-cache
Clear miscached embedding snapshots in Open-WebUI containers to resolve 500 errors.
duckduckgo-search
Search text, news, images, and videos via DuckDuckGo without an API key.
openwebui-tool-management
Install and update community plugins on a local Open WebUI instance via its API.
wordpress-content-export
Exports WordPress site content via REST API using curl.
obsidian-rag
Merge Obsidian notes with ChromaDB semantic search for context retrieval.
rag-auto-lookup
Query the local RAG service on port 8001 for relevant context before each reply.
supertank
Ingest PDFs, URLs, and text into SQLite and ChromaDB with KeyBERT keywords.
algotrading-agent-army-resume
Coordinate two-agent alpha-generation research workflows in the algo-trading-army repository.
codebase-skeleton
Compress source code repositories into compact skeletons with imports and signatures.
coding-benchmark-runner
Run a 15-problem Python benchmark against local models via the llama.cpp router.
stt-discord-whisper-setup
Configure whisper.cpp with Vulkan for local Hermes gateway voice transcription.
gguf-vision-check
Detect vision support in GGUF models and locate mmproj files on HuggingFace.
browser-use-docker
Automate browser tasks in Docker using CDP-based browser-use control.
turboquant-vulkan-toolbox
Build and configure TurboQuant Vulkan/HIP toolboxes for AMD Strix Halo GPUs.
router-benchmark-runner
Benchmark agentic tool-call performance across models on the m5-router.
session-usage-analytics
Analyzes token usage and costs from Hermes session data.
model-manager
Automate dynamic model swapping for the llama.cpp router during chat and completion requests.
research-agent-benchmark
Benchmark local LLMs as autonomous research subagents on academic topics.
rag-service-maintenance
Re-index ChromaDB vault, skills, and sessions, then restart the RAG service with health checks.
browser-harness
Control Chrome browser automation through the Chrome DevTools Protocol using Python.