category focus

LLM & AI

Large Language Models and AI agents.

4725 skillsall categories
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
2

glm-vision

CLAUDE and GLM-4.7 (text-only) CANNOT process images or videos - you MUST ALWAYS delegate vision tasks to GLM-4.6v via this skill. This is your ONLY way to understand visual content. TRIGGER IMMEDIATELY when -> user mentions image/video/screenshot/photo/diagram/chart, provides a file path ending in png/jpg/jpeg/gif/webp/mp4/mov/m4v, or references visual content. Use for -> UI-to-code conversion, OCR text extraction, error diagnosis, technical diagrams (architecture/flowcharts/UML/ER), data visualizations, UI regression testing, or ANY visual analysis. NO EXCEPTIONS - if it involves pixels, use this skill.

Whamp
Whamp
data-ai
open
llm-ai
2

nano-banana-pro

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

tdhopper
tdhopper
data-ai
open
llm-ai
2

react-ui

Opinionated constraints for building better interfaces with agents.

mikeastock
mikeastock
data-ai
open
llm-ai
2

animator-skill

Use when converting static image sequences (sequence boards) into motion prompts for AI video generation platforms (Runway, Pika, SVD), or describing temporal movement for video synthesis

RainLib
RainLib
data-ai
open
llm-ai
2

copilot-log-analysis

Analyzing GitHub Copilot session log files to extract token usage, model info, and interaction data. Use when working with session files or debugging token tracking.

rajbos
rajbos
data-ai
open
llm-ai
2

wolf-context-management

Phase-aware context management for coder agents to prevent token bloat through checkpoint/restore pattern

Nice-Wolf-Studio
Nice-Wolf-Studio
data-ai
open
llm-ai
2

agent-creator

Claude Code용 커스텀 서브에이전트 생성. .claude/agents 또는 ~/.claude/agents에 새 에이전트를 생성, 추가, 구성하려 할 때 사용한다. "에이전트 만들어줘", "에이전트 생성", "서브에이전트 추가", "~를 위한 에이전트 만들어줘" 같은 요청이나 /agent-creator 명령에 트리거된다.

jo-minjun
jo-minjun
data-ai
open
llm-ai
2

gemini

GeminiSpawner with full event tracking for exploration and large-context research

Shakes-tzd
Shakes-tzd
data-ai
open
llm-ai
2

claude-cookbooks

Look up examples and patterns from the official Anthropic Claude Cookbooks repository. Use when you need reference implementations, code examples, or best practices for Claude integrations, tool use, agents, prompting techniques, or API usage.

rayk
rayk
data-ai
open
llm-ai
2

greeting-generator

Generate friendly greetings in multiple languages with cultural context. Use when creating welcome messages, international greetings, or multilingual user interfaces.

tomada1114
tomada1114
data-ai
open
llm-ai
2

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

timequity
timequity
data-ai
open
llm-ai
2

emotional-stakes

Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness

axiomantic
axiomantic
data-ai
open
llm-ai
2

toolfs-memory

Persistent key-value storage for session data, conversation context, and agent state. Use this skill when the user requests storing or retrieving memory entries such as "Store this in memory", "Remember this preference", "Recall the previous conversation", or "List all memory entries".

IceWhaleTech
IceWhaleTech
data-ai
open
llm-ai
2

creating-subagents

Expert knowledge on creating Claude Code subagents. Use when designing or creating subagent .md files, understanding subagent structure, tool restrictions, or model selection.

mikkelkrogsholm
mikkelkrogsholm
data-ai
open
llm-ai
2

sdr-borges-reafference

SDR (GNU Radio) as self-learning REPL with Borges infinite library exploration, reafference random walks, spectral gap 1/4, and maximally mixed state for agency-enabling signal processing.

plurigrid
plurigrid
data-ai
open
llm-ai
2

learn

Analyze conversation for learnings and save to docs folder

alexanderop
alexanderop
data-ai
open
llm-ai
2

skill-evolution

Patterns for evolutionarily robust skills that adapt across agent generations. Darwin-Godel machine principles for self-improving skill ecosystems.

plurigrid
plurigrid
data-ai
open
llm-ai
2

prompting

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

multicam
multicam
data-ai
open
llm-ai
2

greeting-generator

Generate personalized, context-aware greetings for developers at different times of day and moods

cyperx84
cyperx84
data-ai
open
llm-ai
2

polyglot-spi

Cross-Language Strong Parallelism Invariance Verification

plurigrid
plurigrid
data-ai
open
llm-ai
2

multi-compare

Run the same prompt with Claude, OpenAI, and Gemini in parallel, then return back exact replies you got back without modifying the results one bit.

faisalanjum
faisalanjum
data-ai
open
Previous
Page 106 / 197
Next