Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
LLM & GenAI Engineering
292LLM apps, prompts, RAG, embeddings, model gateways, inference utilities.
Specializations
0specializations
0repos
0skills
0MCP servers
0agents
evo
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
LLM & GenAI Engineering
94971
workshop
Give your coding agent the power to write and run agent evals.
LLM & GenAI Engineering
81734
skillgrade
"Unit tests" for your agent skills
LLM & GenAI Engineering
49835
aigc-reduce
降低学术论文 AIGC 查重率的 Claude Code Skill | A Claude Code skill for reducing AIGC detection rates in academic papers
LLM & GenAI Engineering
29611
dspy-agent-skills
Production-grade DSPy 3.2.x agent skills + validated end-to-end examples for Claude Code and Codex CLI — fundamentals, evaluation, GEPA, BetterTogether, and RLM.
LLM & GenAI Engineering
24322
SkillCompass
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
LLM & GenAI Engineering
2248
skills
Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation
LLM & GenAI Engineering
14414
patina
Detects and rewrites AI writing patterns in Korean, English, Chinese, and Japanese. Runs as a skill for Claude Code, Codex CLI, Cursor, and OpenCode, or as a standalone Node.js CLI.
LLM & GenAI Engineering
14222
DM-Code-Agent
Lightweight, auditable Python code agent (~1500 LOC) — ReAct + Planner + Reflexion + Hybrid RAG, with SWE-bench Lite eval and trace replay.
LLM & GenAI Engineering
13812
claude-skill-model-fingerprint
这是一个为 Claude Code / AI Agent 设计的诊断技能（Skill）。它通过自省式分析和多项特定的压力测试，帮助用户检测当前使用的 API 是否为官方原版的 Claude 4.6 模型，或者是否存在第三方中转、提示词注入与封装。
LLM & GenAI Engineering
793
MCPtrace
MCP server: using eBPF to tracing your kernel
LLM & GenAI Engineering
689
skill-optimizer
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
LLM & GenAI Engineering
659
buyer-eval-skill
B2B software vendor evaluation skill for Claude Code — domain-expert questions, vendor AI agent conversations, evidence-based scoring
Agent Engineering
624
code-graph-mcp
AST knowledge graph MCP server for Claude Code — semantic search, call graph traversal, HTTP route tracing, impact analysis. Auto-indexes 10 languages via Tree-sitter.
LLM & GenAI Engineering
386
grape
Graph Retriever Analysis and Performance Evaluation
LLM & GenAI Engineering
315
claude-skill-seo-geo-optimizer
Production-ready Claude skill for comprehensive SEO/GEO optimization. Analyzes content for traditional search engines + AI platforms (ChatGPT, Perplexity, Claude, Gemini). Includes entity extraction, schema generation, and multi-format audit reports.
LLM & GenAI Engineering
314
benchmark-research-skill
Claude Code skill for benchmark research. Survey papers to find datasets, metrics, and evaluation protocols used in a research direction.
LLM & GenAI Engineering
301
manusiawi
Claude skill that strips AI writing patterns from Malaysian BM text. 32 BM patterns + Indonesian intrusion detection + 24 English patterns.
Data & ML Engineering
275
embedded-review
Embedded/firmware code review skill for AI agents. Memory safety, interrupt correctness, RTOS pitfalls, hardware interfaces, C/C++ traps. STM32/Cortex-M/FreeRTOS focused.
Agent Engineering
274
semantic-trap-detector
Detect and fix semantic traps in Claude Skills that cause LLM hallucinations
LLM & GenAI Engineering
273
TandemKit
Planner/Generator/Evaluator orchestration harness for Claude Code (and Codex)
Agent Engineering
252
claude_telemetry
OpenTelemetry wrapper for Claude Code CLI that logs tool calls, token usage, costs, and execution traces to Logfire, Sentry, Honeycomb, or Datadog. Drop-in replacement that swaps 'claude' command for 'claudia'.
LLM & GenAI Engineering
243
ad-creative-evaluator
Claude agent skill: Score any video ad with an AI expert panel. 8-dimension rubric + 3 specialist personas.
Writing & Content
230
skill-reviewer
Candid reviews of Claude Code skills. File:line citations. Ranked actions. No filler.
LLM & GenAI Engineering
225