Popular repositories Loading

1. offload-harness offload-harness Public

   Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude Code.

   Go 3

2. gemini-super-gem-creator gemini-super-gem-creator Public

   Claude Cowork skill for building expert-level Gemini Gems with persistent Drive memory and NotebookLM grounding

   Python 2

3. humanize-presentations humanize-presentations Public

   Remove AI tells from slide decks without destroying the ones that were deliberate. An agent skill for de-slopping existing .pptx files.

   2 1

4. Quick-Agent-Deployer Quick-Agent-Deployer Public

   [v1.2] Cowork skill that deploys local AI agents. 18+ models, multi-provider cloud overflow, potato-to-Grace Hopper hardware support. Ollama + llama-server + llamafile.

   1

5. meta-router meta-router Public

   A capability router for Claude Code — surfaces the most relevant installed skills per prompt via a local hybrid-retrieval hook. Fully local, fail-open.

   Go 1

6. repo-craft repo-craft Public

   Claude Code skill — GitHub repo management + contribution orchestrator. 12 profiles, 13 instrumented refs, 4 playbooks.

   Shell