Model Context Protocol

A skill your agent uses when the host coding agent should control an AutoDL or SSH server from the local machine, run remote commands, and explicitly upload or download selected files.

haibarazz/awesome-codex-research

Measure retrieval quality using evaluateretrieval (MRR@5 and Recall@5) and getindexstats.

lyonzin/knowledge-rag

Installs Reticle's dev-only SDK in a running web app and verifies user-facing changes by driving a real flow, returning a verdict with the file and line to fix.

reticlehq/reticle

Ad-hoc web scraping, site mapping, and full-site crawling via Firecrawl MCP.

seranking/seo-skills

Prisma CLI commands reference covering all available commands, options, and usage patterns.

curvenote/curvenote

Review Agent Builder tool registrations for availability scoping, MCP hygiene, description quality, return value design, single responsibility, and annotation correctness.

elastic/kibana

Inspect Horizon cloud offers and companions, control explicitly authorized companion workers, use a worker Local Network Bridge, or ask for GitHub access from a cloud worker through public MCP tools.

peters/horizon

Foundational cross-cutting context for Dataverse / Power Platform work — scope and the skill map, the tool-capability reference, the safety rules, and the safe change lifecycle.

microsoft/Dataverse-skills

Looks up live Azure retail prices by SKU, service or region through the Azure MCP pricing tool, estimates template costs and compares regions, price types and savings plans.

thomast1906/github-copilot-agent-skills

发布内容到小红书，支持图文笔记和视频笔记。自动判断发布类型，校验标题和素材，用户确认后发布. An agent skill from autoclaw-cc/xiaohongshu-mcp-skills.

autoclaw-cc/xiaohongshu-mcp-skills

A skill your agent uses when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell.

Sma1lboy/rove

Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.

Goldziher/basemind

Rank root-cause hypotheses and propose the smallest safe fix.

antonbabenko/deliberation

Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill.

BuilderIO/skills

Populate a project's shared OpenSEO context — site scope, goals, positioning, competitors, key pages, and preferences — plus MCP checks and Search Console intake.

every-app/open-seo

Set up OpenSEO in the current AI agent. An agent skill from every-app/open-seo.

every-app/open-seo

Verify the OpenSEO MCP server end-to-end on a local dev server — protocol-level correctness against real DataForSEO, then a headless-agent consumer probe that tests tool ergonomics (descriptions…

every-app/open-seo

P4 stream workflows — creation, branching, merging, copying, integration, switching, and spec management via P4 MCP tools.

perforce/p4mcp-server

Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.

openai/openai-agents-python

Covers all non-grid Ignite UI for Angular UI components: application scaffolding and setup, form controls (inputs, combos, selects, date/time pickers, calendar, checkbox, radio, switch, slider)…

IgniteUI/igniteui-angular

Scaffolds a local Codewhale plugin bundle with a versioned manifest, namespaced skills under it, and an explicit trust review before anything in the bundle is enabled.

codewhale-hq/Codewhale

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

davila7/claude-code-templates

Lets an agent read, write and maintain its own memory in a Brain folder of an Obsidian-compatible vault, while keeping the user's own notes read-only.

itechmeat/open-second-brain

Triage a bug or unexpected behavior. An agent skill from enmanuelmag/agent-harness-kit.

enmanuelmag/agent-harness-kit

Query Fintel (fintel.io) institutional market data through its REST API or official MCP server.

himself65/finance-skills

Search, install, publish, review, and update Marketplace plugins — Skills, MCP connectors, and Experts/Squads (专家/专家团) — through the unified plugin API.

Mininglamp-OSS/octo-cli

Search the Unity asset database using a search filter string.

IvanMurzak/Unity-MCP

A skill your agent uses when the task involves creating, reading, editing, updating, fixing, or undoing notes on the CSIRT HedgeDoc/HDOC instance through the edithdoc MCP server, including any hdoc.

Th4nat0s/Chall_Tools

Domain playbook for optimization missions — any task whose goal is to move a metric: performance, latency, throughput, memory, cost, score, quality, compression, ranking, solver, model/eval, and…

Intelligent-Internet/zenith

Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser.

disler/bowser

Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to…

mxyhi/ok-skills

A skill your agent uses when authoring, planning, or running a declarative sbxenv.yaml file for Docker Sandboxes (sbx env create/run/plan/exec/rm), even if the user just says they want to "check in…

docker/skills

Builds and debugs MCP servers and clients in TypeScript or Python, from tool and resource definitions to transport setup and inspector-based protocol checks.

Jeffallan/claude-skills

A skill your agent uses when a research workflow needs verified academic source retrieval through literature-search MCP interfaces available in the current session before evidence extraction.

openJiuwen-ai/sciencediscovery

Searches for, installs and helps create agent skills in Cherry Studio when you ask or when a built-in skill falls short, then returns to the original task.

CherryHQ/cherry-studio

Workflow skill for driving the CalculiX MCP server over .inp decks — model inspection, in-place design-variable edits, ccx solve, .dat result reading, and resultmesh.json export for the viewer.

Cai-aa/CAE-Agent-Hub

Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审. An agent skill from Sibyl-Research-Team/AutoResearch-SibylSystem.

Sibyl-Research-Team/AutoResearch-SibylSystem

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

AnastasiyaW/codex-claude-code-config

Systematic methodology for diagnosing GnollHack crash reports from the Sentry MCP server.

hyvanmielenpelit/GnollHack

A skill your agent uses when the user wants to release a new version.

s-morgan-jeffries/apple-mail-fast-mcp

角色创建师，基于剧情生成详细的人物角色卡，包括性格、习惯、人物关系网。当需要创建或完善角色信息时使用. An agent skill from jeffstric/ZJT.

jeffstric/ZJT

How to install, configure, and use the chorus CLI — install it, manage agents with chorus agents (add/remove/list), the connection environment variables, and MCP operations via chorus mcp.

Chorus-AIDLC/Chorus

Builds a ranked calendar of dated events such as earnings, regulatory decisions, flows and macro releases, ordered by what each can change, with prep owners and a weekly preview.

ginlix-ai/LangAlpha

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布).

TencentCloudBase/CloudBase-AI-Toolkit

Set up compliance exports, drift detection, evaluations, scoring, and learning analytics

ucsandman/DashClaw

Static linter for an Aeon instance's configuration that catches silent failures such as unquoted schedules, duplicate keys, unconfigured skills and broken MCP references.

aeonfun/aeon

Run a deep full-text search across every Remnic memory. An agent skill from joshuaswarren/remnic.

joshuaswarren/remnic

Audits Prometheus recording and alerting rules through a connected Prometheus MCP server, finds gaps and noisy alerts, and drafts improved rule-group YAML.

prometheus/prometheus-mcp