Offload summarisation, drafting, triage, classification and other non-reasoning text work from Claude Code to locally-installed models (MLX, Docker Model Runner or Ollama), keeping content on-device and the main context window free. Saving API tokens is a side effect, not the point.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin delegate-local in IsmaelMartinez/delegate-local. Commands read from the repo's manifest — 7 days ago.
delegate-localUse this skill to read a large text input on this machine instead of in your own context, by piping it in chunks to a local model (MLX, Ollama or Docker Model Runner) via `delegate.sh` for a short, anchored answer you spot-check. MUST use when the input is too large to be worth reading in full (a lo
Precise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server — no cloud, no npm.
Skills for MLX-VLM: command-line and server inference, convert/quantize, adding new models, benchmarking, contributing, cached-model listing, and reproducible GitHub issues.
8 skills
Run AI models locally with Ollama - free alternative to OpenAI, Anthropic, and other paid LLM APIs. Zero-cost, privacy-first AI infrastructure.
1 skill · 1 command
Shows a plain-English rewrite of each Claude Code assistant message, produced by a local LLM (ollama, default), the Anthropic API, or any OpenAI-compatible API. Display-only.
1 skill · 1 command · hooks
Local-first LLM branching & debugging. Treat AI context windows like a Git repo — capture, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, and MCP for agents.
1 skill · 1 command · 1 agent · 1 MCP server
Produces detailed law-school case briefs of United States judicial opinions in a fixed nine-section structure: memory jogger, facts, procedural history, judicial votes, holding, opinion-by-opinion analysis, five future-application hypotheticals, critique, and verified key quotations. Also builds vote tables, cross-case consistency tables, perspective-based critiques, and LaTeX in article, Beamer and casebook-chapter formats. Use whenever someone asks to brief a case, analyse or explain an opinion, summarise a decision for students, generate hypotheticals from a holding, critique a judgment, tabulate how justices voted, or convert case analysis to LaTeX. Triggers on "brief this case", "case brief", "explain the holding", "what did the court hold", "hypotheticals based on", "critique this opinion", "vote table", "Beamer presentation", "chapter brief", and on any reference to a judicial opinion or Supreme Court decision in a teaching context. Requires web search to verify quotations, votes and holdings.
200 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.