Plugins

诉讼分析工具 - 判决书深度分析，生成上诉/再审决策支持

Academic literature orientation skill. PICO/SPIDER frameworks, systematic review structure, 8-section DOCX guide. Research-pack convention. Path-B from megaprompt 09.

Academic literature orientation skill. PICO/SPIDER frameworks, systematic review structure, 8-section DOCX guide. Research-pack convention. Path-B from megaprompt 09.

Install the full Liusir skill collection as one plugin.

MCP tools + /feedback commands + PreToolUse hook + live review surface (markdown + injectable widget).

Project rules in a Markdown file that Claude re-injects right when they apply: every prompt, or just before it edits a matching file. Edits apply on the next prompt, no restart. A SessionStart hook injects the always-on rules once as a fallback, and it's a way to tell whether per-prompt injection is actually wired.

Live Wires CSS framework for editorial websites with layout primitives and baseline rhythm

Real-time communication and voice agent integration with LiveKit. Enables AI agents to participate in video, audio, and messaging sessions.

Branded, interactive, self-maintaining user's manuals with a note-to-ticket pipeline and optional Jira or GitHub Issues sync.

Obtain temporary Lix API tokens via CLI with human email approval

Liz Osborn's canonical patterns library — ONE home for her reusable agents, skills, and tools. Available in every Claude Code session in every project, so the same pattern means the same thing wherever invoked. v0.1.1 (2026-06-16): adds drift-watcher agent — read-only oversight agent for long multi-repo executions, validated in production twice before promotion.

Use /ljg-roundtable <topic> to launch a structured roundtable discussion on any topic

from ccf/claude-code-ccf-marketplace

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.2

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4

Plugin from it-bens/ai-tools

Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching an AI feature without cost architecture. NOT for RAG design or prompt quality (separate skills).

5 working methods for llm engineering: agent-memory, mcp-server, prompt-engineering, rag-pipeline, and more

MCP server that offloads bounded LLM tasks from Claude Code to cheaper local (LM Studio, Ollama, vLLM, llama.cpp) or remote (OpenRouter) models. Profile-based configuration with ensemble mode, auto-batching, and secret scanning.

Unified multi-provider LLM gateway: GitHub Copilot, Kimi, MiniMax, GLM

A portable GTD skill for Claude Code: capture / clarify / organize / engage / review over plain-Markdown lists in memory/gtd/. The bundled skill auto-activates; /gtd and /gtd-* commands are included. Calendar writes are confirmation-gated and fail-closed.

Find and fix LLM-isms in documents

Guidance for writing effective LLM prompts and agent instructions, with current per-provider model notes.

logic-master (Codex) and frontend-master (Gemini) skills for code optimization and UI/UX tasks

Build and maintain a persistent LLM-powered wiki/knowledge base. Ingest sources, build interlinked pages, query with citations.

LLM Wiki vault plugin (develop from repo root)

Bootstrap and query LLM-maintained project wikis before planning or implementation.

A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.

Generate a navigable, version-controlled multi-page Markdown wiki from a codebase, engineered for on-demand retrieval as Claude's context while staying human-readable. Two-pass outline-then-fill generation across a parallel agent swarm of planner, diagram author, page writers, and index synthesizer; consumes a code-atlas index as ground truth when present, else self-scans. Pure static Markdown (no embeddings), Mermaid diagrams derived from the dependency graph, per-page source provenance, and git-blob hash-diff staleness detection that regenerates only stale pages. A SessionStart hook loads the wiki index at session start

A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, and OpenCode.