MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
针对DSH：添加第三方中转站模型时上下文长度被默认256K问题（DeepSeek Harness小完善计划其一）· Agent Skill 维修手册
SkillCC-BY-4.0★ 2Few starsNo key
Empirical research into how agent platforms implement Agent Skill loading, management, and presentation. Benchmark skills and per-platform findings.
SkillCC-BY-4.0★ 6No key
AI Agent 系统工程深读笔记 | 从 LLM→Agent→Orchestrator 的架构演进、关键技术与工程实现 | Session Management · Context Engineering · Tool Registration · Harness Engineering
SkillCC-BY-4.0★ 2Few starsNo key
Harness Engineering — a practical guide to the platform layer of coding agents (Claude Code & Codex): skills, hooks, config, permissions, reasoning effort. EN / 한국어 / 日本語 / 中文.
SkillCC-BY-4.0★ 2Few starsNo key
Large Result Offloading (LRO) -- a token-aware strategy for managing large tool outputs in LLM context windows. Includes empirical evaluation and formal specification.
SkillCC-BY-4.0Few starsNo key
Three composable Claude Code skills that make long sessions cheaper by cutting re-sent context at phase boundaries.
SkillCC-BY-4.0Few starsNo key
OfficialHosted by authorCC-BY-4.0★ 60No key
A practical, community-driven checklist for pentesting MCP servers. Covers traffic analysis, tool-call behavior, namespace abuse, auth flows, and remote server risks. Maintained by Appsecco and licens
SkillCC-BY-4.0★ 42No key
Missing operating-system primitives for agent runtimes: disposable sessions, models as workers, context as virtual memory, artifacts as the system of record. A specification in progress.
SkillCC-BY-4.0★ 1Few starsNo key
Intent Engineering: the engineering discipline for the human side of AI-led systems | 意图工程:AI 主导系统中面向「人」这一侧的工程学科
SkillCC-BY-4.0★ 1Few starsNo key
🧩 A type-safe and composable architecture for modular monolith development in TypeScript.
SkillCC-BY-4.0★ 5No key
A minimal, AI friendly standard for your docs folder
SkillCC-BY-4.0★ 4Few starsNo key
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
SkillCC-BY-4.0★ 91No key
16 structured AI skills for product & design teams, Discovery to Shipping. Works with Claude, ChatGPT, Gemini.
SkillCC-BY-4.0★ 2Few starsNo key
Agent Harness 学习指南与面试题库 — 零基础到系统理解，73 张图解 + 37 道题 + Pi/dsh 架构深潜（中文）
SkillCC-BY-4.0★ 3Few starsNo key
Open study guide for the Anthropic Claude Certified Architect (Foundations) exam: agent loop, context management, tools & schemas, sub-agents, hooks, MCP. Concepts + 29 practice questions with worked
SkillCC-BY-4.0★ 1Few starsNo key
A readable notation for verified AI-agent loops: goals, context, authority, cycles, verifiers, stop rules, and return artifacts.
SkillCC-BY-4.0★ 2Few starsNo key
Taiwan law and court decisions for your AI: statutes, articles and rulings, read-only.
Hosted by authorCC-BY-4.0★ 1Few starsNo key
Every FileMaker 26 function and script step, compressed to ~7,000 tokens: names, signatures, return types, script step IDs, and platform support. Small enough to keep in context as part of an AI skill
SkillCC-BY-4.0★ 5No key
16 reusable AI sales skills for early-stage founders — prospecting, discovery, pilots, follow-up and validation metrics. Works with ChatGPT, Claude, Gemini and Spinnable. CC BY 4.0.
SkillCC-BY-4.0Few starsNo key
Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98%
SkillCC-BY-4.0★ 23No key
LEASH — Lightweight Encrypted Agent Secret Handling. A proposed companion standard to MCP for secure, auditable, human-controlled secret access by AI agents.
SkillCC-BY-4.0★ 8No key
Security checklist and reference audit configuration for MCP (Model Context Protocol) server deployments
SkillCC-BY-4.0★ 2Few starsNo key
Who stands behind it
