Model Context Protocol agent skills, page 104

Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.

learningmatter-mit/AtomisticSkills

A skill your agent uses when stuck in circular debugging, when solutions aren't working despite multiple attempts, or when the user expresses frustration with lack of progress.

Microck/ordinary-claude-skills

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers.

Microck/ordinary-claude-skills

Create compelling story-format summaries using UltraThink to find the best narrative framing.

Microck/ordinary-claude-skills

Generate typed TypeScript SDKs for AI agents to interact with MCP servers.

Microck/ordinary-claude-skills

Diagnose local Stata, MCP, package, startup, graph-export, and permissions issues.

brycewang-stanford/Auto-Empirical-Research-Skills

Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication, or Stata errors.

brycewang-stanford/Auto-Empirical-Research-Skills

Skill Development Rules

parcadei/Continuous-Claude-v3

本技能用于检索、核验、筛选、比较或总结中国司法案例、判例、判决、裁定、裁判文书、裁判要旨、裁判观点和法院倾向，可完成案情分析、类案检索、全文阅读、补充检索、真实性核验、关联度排序和裁判理由摘要。

infometa/workbuddyskills

本技能用于对中国大陆企业开展法律尽职调查，以及起草、生成、修改、完善、审查或复核法律尽职调查报告；支持投融资、并购、常年法律顾问合规体检、供应商或合作方、融资方、上市前专项及其他专项尽调。

infometa/workbuddyskills

用于访问乐享知识库平台的专用 skill。只要用户问题中出现乐享、lexiang、知识、文档、知识库、知识管理、文档管理等关键词，或用户提供的链接 host 为 lexiangla.com，就应优先调用本 skill，而不是使用其它工具或技能替代。本 skill…

infometa/workbuddyskills

A skill your agent uses for page-deliver application code generation, page creation, publishing, deployment, going live, MCP enablement, or runtime access/control of deployed HRClaw applications.

infometa/workbuddyskills

Skill 制作与审查方法。用于新建或优化 Skill、MCP/CLI/API 配置与环境检查、功能降级、五阶段审查、触发和脚本实测、打包及用户级安装。

infometa/workbuddyskills

腾讯乐享（lexiangla.com / csig.lexiangla.com）知识库专用操作。仅在用户消息包含 lexiangla.com 链接、或明确提及『乐享/云知/Lexiang/知识库』关键词时触发。覆盖搜索、创建、编辑、上传、下载、Token 配置。⚠️ 通用『创建文档』『编辑页面』『写文章』『公众号选题』『情感咨询』等无乐享上下文的请求不属于本 Skill 范围，应立即退出。

infometa/workbuddyskills

北大法宝官方法律检索 MCP Skill。涉及「法律」「法规」「法条」「司法解释」「判例」「案号」「类案」「合同审查」「合规清单」「裁判规则」「指导案例」「劳动争议」「民法典」「公司法」「数据合规」等关键词时使用。提供 5 个工具：法条语义检索 searcharticle、法条精确查询 getarticle、法规列表 getlawlist、案例语义检索…

rongxinzy/RongxinAI

Build MCP (Model Context Protocol) servers including tool definition, schema design, authentication, error handling, and Claude Code integration.

asgard-ai-platform/skills

Integrate and operate Shopline in Taiwan e-commerce context via mcp-shopline.

asgard-ai-platform/skills

Issue and manage Taiwan e-invoices via ezPay (加值服務中心) through mcp-ezpay-einvoice.

asgard-ai-platform/skills

Integrate NewebPay (藍新金流) for Taiwan e-commerce via mcp-newebpay.

asgard-ai-platform/skills

Manage Harness RBAC roles, role assignments, permissions, and resource groups via MCP v2 tools.

harness/harness-skills

Track Harness template dependencies, usage, and adoption via MCP v2 tools.

harness/harness-skills

Alias for /origin:handoff — symmetric brief/debrief naming. An agent skill from davepoon/buildwithclaude.

davepoon/buildwithclaude

Full inbox management across all channels — WhatsApp (wacli), Email (Gmail MCP), Slack (MCP), Telegram (user-auth MCP), Discord (webhook + REST read), Notion (MCP — comments, mentions, assigned…

davepoon/buildwithclaude

Cross-chain token swaps, quotes, portfolio and prices across 14 chains via the Suwappu DEX MCP server.

BankrBot/skills

Generates one integration/E2E test from an approved test case spec using existing project patterns.

HoangNguyen0403/agent-skills-standard

Stream live swarm events using the Monitor tool for real-time observability

ruvnet/ruflo

Read-only on-chain research for pump.fun and other meme-token launchpads (Solana / BSC / X Layer / TRON).

nirholas/three.ws

Find contacts stalled at funnel stages (abandoned cart, signed-up-but-no-trial, trial-but-no-convert), draft stage-appropriate re-engagement emails, and schedule sends via your ESP — with dedupe so…

cognyai/claude-code-marketing-skills

Audit an email marketing program for revenue leaks — missing flows, dormant high-value subscribers, under-segmentation, promo gaps, stale automations — ranked by estimated $ impact

cognyai/claude-code-marketing-skills

Full technical + content SEO analysis — uses live Search Console + Bing data when connected

cognyai/claude-code-marketing-skills

Monitor SEO rankings, queries, and indexing via Search Console MCP

cognyai/claude-code-marketing-skills

Mine your actual subject-line history from Klaviyo / Mailchimp / Rule / Get a Newsletter, find the patterns that work for YOUR list, and generate tuned candidates

cognyai/claude-code-marketing-skills

Pre-ship code review by a fresh-context Opus reviewer that checks the change against this project's hard rules — a false green, a channel rebuilt field by field, engine purity, schema versions…

guardana/guardana

Этот скилл MUST быть вызван для поиска по документации платформы 1С — методы, функции, синтаксис, API.

Arman-Kudaibergenov/1c-ai-development-kit

Search 21st.dev component registry for production-ready React components.

yonatangross/orchestkit

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP.

yonatangross/orchestkit

Error pattern analysis and troubleshooting for Claude Code sessions.

yonatangross/orchestkit

Reference for the Storybook MCP server itself (@storybook/addon-mcp): 6 tools across 3 toolsets (dev, docs, testing), availability detection, and per-agent toolset filtering.

yonatangross/orchestkit

Autonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds.

AI4Scientist/nano-scientist

Autonomous multi-round research review loop. An agent skill from AI4Scientist/nano-scientist.

AI4Scientist/nano-scientist

Autonomous multi-round research review loop. An agent skill from AI4Scientist/nano-scientist.

AI4Scientist/nano-scientist

Autonomous multi-round research review loop. An agent skill from AI4Scientist/nano-scientist.

AI4Scientist/nano-scientist

Query Funda AI for analyst-grade research synthesis via MCP or raw structured market data via the REST API, choosing the right surface per request.

criptogus/agent-evolve-network

A skill your agent uses when investigating or safely modifying Uptime Kuma v2 monitors.

mvanhorn/printing-press-library

Use the Printing Press companion for AgentPool to inspect official capacity signals, run privacy-safe diagnostics, and delegate to the official agentpool CLI.

mvanhorn/printing-press-library

Printing Press CLI for Doordash. An agent skill from mvanhorn/printing-press-library.

mvanhorn/printing-press-library

Printing Press CLI + MCP for Goodreads, read and write — rate books (GraphQL RateBook/UnrateBook), write/publicize reviews, add to and create shelves, home feed, friends, recommendations…

mvanhorn/printing-press-library

Printing Press CLI/MCP for confirmed TikTok Shop Seller APIs.

mvanhorn/printing-press-library