MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Impl
OfficialSkillMIT★ 40k in collectionNo key
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT e
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.
SkillMIT★ 288No key
AI Skills Bank is a unified, multi-tool platform designed to aggregate, manage, and route AI skills across various workflows and AI assistants (such as Antigravity, Claude Code, Cursor, and Copilot).
SkillMIT★ 13No key
洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.
SkillMIT★ 18No key
Mistral MCP server for document extraction: invoices, contracts and typed JSON from text, Markdown or OCR. Six-tool core, chat, vision, audio, stdio and Streamable HTTP.
Node.jsMIT★ 15No key
Improve, debug, benchmark, or refactor an existing Agent Skill from conversation evidence, execution traces, user corrections, eval failures, or target skill files.
SkillMIT★ 2Few starsNo key
AI-powered CSV and Excel analysis tool for semantic text classification, sentiment analysis, survey response processing. Uses DeepSeek V3, GPT-4, Ollama LLMs. 5000+ rows per hour. Python pipeline.
SkillMIT★ 2Few starsNo key
A FastMCP server that provides shell command execution, file system access, and process inspection over the MCP Streamable-HTTP transport. Built for homelab operations agents that need to read files,
PythonMIT★ 1Few starsNo key
Evidence-led intelligence for decoding Douyin social commerce videos—from local subtitle OCR to product-integration strategy and audit-ready reports.
SkillMIT★ 4Few starsNo key
A governed GA4 semantic layer in dbt + MetricFlow on BigQuery, queryable by humans and by LLM agents over MCP. The README is a metric definition document: every metric states its definition, assumptio
PythonMITFew starsNo key
Codex skill for reviewing agent failures, avoiding rule bloat, and choosing the smallest verified improvement.
SkillMITFew starsNo key
Claude VObS：个人 AI 操作系统的开源参考实现。基于 Claude Code + VSCode + Obsidian 三端架构，零行手写代码。
SkillMIT★ 8No key
Audit and clean up Claude Code's persistent memory system — MEMORY.md, memory files, lessons, and ADRs
SkillMIT★ 3Few starsNo key
MCP server for Brazilian personal finance. OFX/CSV parsing with per-bank quirk fixes, PT-BR transaction categorization (rules → LLM cascade), CPF/CNPJ validation, and CNAE lookup. Works with any MCP-c
PythonMIT★ 1Few starsNo key
Behavioral diff for AI-written code. Your agent changed 40 files — Veris tells it what behavior actually changed and whether any of it was verified. MCP-native, checker-resolved call graph, tamper-evi
Node.jsMIT★ 1Few starsNo key
Forge battle-tested CLAUDE.md files that actually get followed. Audit, score, and generate CLAUDE.md with anti-slop rules, plan enforcement, and verification gates.
SkillMIT★ 3Few starsNo key
Universal document processing: extract, chunk, enrich, embed, validate
PythonMIT★ 3Few starsNo key
Turns Indian GST tax invoices into government INV-01 JSON. Tells you exactly what it couldn't read, and never invents a value to fill a gap. MCP server with OCR, deterministic extraction, and a ground
PythonMITFew starsNo key
Tool-call guard for JavaScript agents: tainted tool results never reach a network, email, exec, file or payment sink. Pinned tools, budgets, fail-closed, zero dependencies, benchmark numbers published
Node.jsMIT★ 3Few starsNo key
Claude Code skill for static audit of OpenClaw config and agent proposals — llms.txt-first research, F1–F12 incident library, Notion-bridged Galatea audit workflow.
SkillMITFew starsNo key
Detects which instruction file Claude Code actually loads (CLAUDE.md still wins if present) and generates a cross-tool AGENTS.md with real module boundaries and data flow rules, not just setup command
SkillMITFew starsNo key
Model Context Protocol server that fronts the open-source accounting suite's deterministic tools: bank-statement and OFX parsing, document classification, workpaper-spec validation, exact money math,
PythonApache-2.0★ 2Few starsNo key
An evidence-driven, platform-independent Agent Skill for reviewing substantial code modules and cross-file features.
SkillMITFew starsNo key
Who stands behind it
