687 tagged LLM, measured the same way as everything else here.
Browse within: agentskills 159prompt-engineering 117Science 100agents-md 100claude-code-plugin 49openai 23agentic-workflows 22ai-assistant 21self-hosted 18x402 18knowledge-base 16litellm 16local-first 15model-context-protocol 15
Plugin Claude Code
Bundles 2 commands, 1 MCP server · 28 tokens together
Smart git diff context for LLMs and AI agents: budgeted fragment selection, deterministic, MCP server included.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 58 tokens together
Operate a local mergetrain queue with agent instructions and a human-gated deploy tool.
huguryildiz/ieee-acm-paper-writing
Plugin Claude Code
Bundles 1 skill · 151 tokens together
Evidence-bounded drafting, rewriting, auditing, and venue adaptation for IEEE and ACM engineering manuscripts.
Plugin Claude Code
Bundles 5 skills, 3 hooks · 338 tokens together
Architecture guardrails for Claude Code — automatically injects declared module boundaries into Claude's context when it edits files near a spec.
Plugin Claude Code
Bundles 10 commands, 48 agents · 3,595 tokens together
A full product team for a solo PM or founder. Specialist agents run the product loop — discovery, strategy, prioritization, specs, launch, measurement — while the human confirms a small number of gates.
product-on-purpose/writing-style-catalog
Plugin Claude Code
Bundles 3 skills · 178 tokens together
Composable writing instructions on four orthogonal axes (Voice, Tone, Style, Format): pick one entry per axis and the builder assembles a ready-to-paste prompt prefix that steers any LLM toward a precise register, reasoning pattern, and layout. Ships 97 curated entries, 1193 worked examples, 158 diff-pairs, and 14…
satyamamarpandey/ClaudeTokenSAP
Plugin Claude Code
Clarifies vague build prompts, carries forward compaction memory, summarizes source files, and protects Claude Code context by gating oversized noisy reads.
Codeblockz/langchain-community-plugin
Plugin Claude Code
Bundles 3 skills, 5 commands, 2 agents, 1 MCP server · 334 tokens together
Unofficial Claude Code plugin for LangChain and LangGraph. Agents, RAG pipelines, and LCEL chains with best practices.
Plugin Claude Code
Bundles 2 skills, 4 commands, 2 agents · 279 tokens together
Recursive Language Model integration for Claude Code using rlm-rs CLI. Enables processing documents far exceeding context windows via chunking and recursive sub-LLM calls.
Plugin Claude Code
Plugin marketplace listing 1 plugin: novada-mcp.
Plugin Claude Code
Bundles 1 skill · 67 tokens together
Minimal response mode for agents, with automatic lifecycle hook injection.
Plugin Claude Code
Bundles 2 skills · 187 tokens together
Professional writing skills for AI coding agents: anti-slop editing that makes drafts sound human, and technical content writing with runtime voice calibration.
Plugin Claude Code
Bundles 1 command, 1 agent · 125 tokens together
Call K-EXAONE 236B (LG AI Research, served by FriendliAI) from Claude Code via the opencode CLI: /k-exaone.
Plugin Claude Code
Bundles 1 skill, 1 command · 144 tokens together
Multi-model workflows: /council (round-based deliberation across Claude, Codex, and K-EXAONE) and the korean-report writing skill.
Thomaszhou22/self-discover-skill
Plugin Claude Code
AI agents self-compose reasoning structures from seed modules.
Plugin Claude Code
Bundles 9 skills, 1 MCP server · 454 tokens together
Shippo connects you to USPS, UPS, FedEx, DHL, and 40+ carriers, so you can handle a shipment end to end right inside Claude. Compare live rates and pick the cheapest or best option, buy and print labels (domestic and international, with customs declarations), validate and standardize addresses, and track packages…
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 46 tokens together
Preflight risk linting for MCP & agent tools. Before you add or edit an agent-tool config, CallLint recommends scanning the blast radius — SAFE / REVIEW / BLOCK / UNKNOWN with evidence. Advisory and non-blocking; never executes the server it judges.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 34 tokens together
Smart JSON-to-TOON conversion with pragmatic auto-gating for LLM prompts.
Plugin Claude Code
Bundles 1 skill · 101 tokens together
Requires a task result to survive two consecutive independent adversarial reviews before completion.
Plugin Claude Code
Bundles 1 skill · 114 tokens together
Runs guarded metric-driven experiments with holdout gates, immutable evidence provenance, and replay-safe recovery.
Plugin Claude Code
Bundles 1 skill · 30 tokens together
Briefly describe what this skill does and when Claude should use it.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 95 tokens together
Persistent, governed memory for Claude Code. Remember decisions once; recall them in every future session, across every tool on the team.
Plugin Claude Code
Bundles 1 command, 5 hooks · 36 tokens together
Deterministic, hook-based memory for Claude Code: async LLM capture off the hot path, keyword recall in-hook, plain-markdown store you can grep.
Plugin Claude Code
Bundles 2 skills, 18 commands, 1 agent, 1 hook · 871 tokens together
One memory, every AI. Shared memory management for all your coding agents — organized, lean, and reversible.