691 tagged LLM, measured the same way as everything else here.
Browse within: agentskills 159prompt-engineering 117Science 100agents-md 100claude-code-plugin 50openai 23agentic-workflows 22ai-assistant 21self-hosted 19x402 18knowledge-base 16litellm 16model-context-protocol 16local-first 15
rootwarp/claude-code-plugins-monorepo
Plugin Claude Code
Bundles 2 skills, 9 agents · 537 tokens together
Multi-agent development team orchestration with planning and execution pipelines.
rootwarp/claude-code-plugins-monorepo
Plugin Claude Code
Bundles 6 skills · 0 tokens together
Go development tools for Claude Code.
rootwarp/claude-code-plugins-monorepo
Plugin Claude Code
Bundles 4 skills · 0 tokens together
Python development tools for Claude Code.
Plugin Claude Code
Bundles 1 skill · 60 tokens together
Systematically fact-check AI-generated research reports against primary sources. Catches the five recurring failure modes of LLM research: unit/scale errors, fabricated interpolation, source conflation, stale data, and attribution laundering.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 198 tokens together
Agent-driven knowledge base with immutable raw sources, mutable wiki pages, BM25 search, code analysis, and self-checking lint. Use when managing knowledge bases, importing documents, writing wiki pages, or parsing source code.
cyanheads/medical-codes-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Decode, search, validate, and crosswalk US medical codes — ICD-10-CM, ICD-10-PCS, HCPCS Level II, RxNorm — over a bundled offline index.
Plugin Claude Code
Bundles 4 skills · 932 tokens together
Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…
emergent-wisdom/understanding-graph
Plugin Claude Code
Bundles 10 skills, 2 MCP servers · 541 tokens together
A persistent medium for fluid, emergent understanding.
Plugin Claude Code
Bundles 2 skills, 1 hook, 1 MCP server · 98 tokens together
Rewrites Claude-English into plain English: sycophantic openers, hedging filler and padded phrasing out, facts, code blocks, names and numbers untouched. Runs an open-weights model on dedicated GPUs, so text never reaches a commercial AI provider.
ChristinaAndrinopoyloy/claude-skills
Plugin Claude Code
Bundles 2 skills · 231 tokens together
A curated collection of Claude skills for content creation and developer workflows.
OC-NeuralSense/reader-first-writing-skills
Plugin Claude Code
Bundles 12 skills, 3 agents · 2,729 tokens together
A reader-first writing system: structure, draft, diagnose, revise, and review documents across argument architecture and sentence-level prose, with fidelity-preserving revision and independent review. Routes by writing goal (plan, compose, diagnose, restructure, revise, adapt, compare, review, finalize, teach).
Plugin Claude Code
Bundles 5 commands, 3 hooks, 1 MCP server · 73 tokens together
Context-budget manager for Claude Code. Warns before auto-compact and long-context accuracy degradation, checkpoints finished work so you can shed it, gates large file reads to subagents, recalls context evicted by compaction, guards against unrelated context switches, and audits unused agents/skills.
Plugin Claude Code
Bundles 23 commands, 3 agents · 382 tokens together
Engine for an LLM-curated second brain. Karpathy LLM-wiki pattern with anti-lissage spec, FR-by-default content, three query postures.
Plugin Claude Code
Bundles 5 skills, 17 commands, 5 agents · 1,166 tokens together
Pack orienté gestion de produit pour corpus : types d'entités PM, angles de revue et transferts beads adaptés aux équipes produit francophones.
Plugin Claude Code
Bundles 26 skills · 858 tokens together
D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, as a working toolchain: an agent embodied in a directory, three operators (FACTOR / ADJOIN / CHRISTEN), and a gate that catches a missing closure at the syntax level.
Ryuketsukami/agent-work-protocol
Plugin Claude Code
An always-on operating protocol for coding agents: build only what's asked, surface ambiguity as Q/A/P/E/X, scale process to task size, and verify before claiming. Injected into every session via a SessionStart hook.
taishi-i/awesome-japanese-nlp-slides
Plugin Claude Code
Search tools for awesome-japanese-nlp-slides: find Japanese NLP presentation slides and lecture materials.
Plugin Claude Code
Bundles 3 skills, 1 command, 3 hooks, 1 MCP server · 358 tokens together
A team knowledge-base workflow plugin that connects coding agents to an MCP knowledge-base server. It provides skills for starting a work brief, recording events, and saving the finished record.
Plugin Claude Code
Bundles 4 skills, 2 hooks, 1 MCP server · 289 tokens together
AI Context Continuity Engine — warns before the context window degrades, hands off a faithful 7-bucket brief, and keeps a decision/evidence ledger across sessions and models.
Plugin Claude Code
Automatic long-term memory for Claude Code via Hindsight. Recalls relevant memories before each prompt and retains conversation transcripts after each response.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 60 tokens together
Read and compare Scripture across 86 translations in 32 languages. No API key required.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 82 tokens together
Browse-use for Claude Code: drive a real browser (vision + DOM + stealth fallback ladder) to operate any web app that has no usable API. Self-improving — learns and compiles skills.
Plugin Claude Code
Bundles 1 skill · 38 tokens together
Offline, zero-dependency tool-router for MCP. Funnels many tools down to a ranked shortlist for a natural-language query — no embedding model, no network — so the model reads 8 tools instead of 200. Funnel advises, model decides.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 58 tokens together
Local-first, ownable memory for Claude Code — automatic recall + capture, one SQLite file you own. No API key.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: