Best MCP servers skills, page 19

Editing, cutting, trimming, pacing, and timeline restructuring in the DaVinci Resolve MCP.

samuelgursky/davinci-resolve-mcp

Explains how to add an end-to-end test scenario to remindb, choosing between a direct API test and an MCP test and using the shared helpers and fixtures.

radimsem/remindb

Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

homeassistant-ai/ha-mcp

Creates an MCP work item from conversation context, anchoring it under the right container, inferring type and priority and pre-filling the required notes.

jpicklyk/task-orchestrator

A decision tree for an agent changing its own setup: edit memory directly, request approval for packages and MCP servers, and delegate code edits to a builder agent.

nanocoai/nanoclaw

Guides production character modeling in Blender through MCP: proportions, edge loops for faces and joints, clothing as separate meshes, hair, and animation-ready topology.

arjun988/blender-skills

Routes an agent inside Cherry Studio to the right first-party tool or bundled runtime for local scripts, documents, memory, schedules, knowledge bases, MCP servers and more.

CherryHQ/cherry-studio

Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket /…

warpdotdev/warp

Publishing and release workflow with semantic-release and GitHub Actions

adeze/raindrop-mcp

Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns

alirezarezvani/claude-code-skill-factory

Scaffold a new UniFi MCP tool with model, function, tests, and docs

enuno/unifi-mcp-server

A skill your agent uses for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.

fmflurry/settings-opencode

Directs iOS build, test and clean operations through the execute_xcode_command MCP tool instead of raw xcodebuild in the shell, with parameter-level retries on failure.

conorluddy/xclaude-plugin

List, find, and show Azure resources across subscriptions or resource groups.

microsoft/GitHub-Copilot-for-Azure

MCP playbook for browsing and reading SiYuan notes. An agent skill from yangtaihong59/siyuan-plugins-mcp-sisyphus.

yangtaihong59/siyuan-plugins-mcp-sisyphus

How to extend Wizard via /evolve. An agent skill from teddytennant/wizard.

teddytennant/wizard

Indexes agentmemory's MCP tools by purpose, with a save-then-recall quick start and a reference file listing exact parameters.

rohitg00/agentmemory

Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.

thedotmack/claude-mem

Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost…

comet-ml/opik-mcp

Execute work through an OverClick MCP board. An agent skill from ustoppble/overclick.

ustoppble/overclick

Check release readiness and trigger the release pipeline for Azure SDK packages.

Azure/azure-sdk-for-android

Search for software composition analysis (SCA) dependency risks in a SonarQube project (project key optional when MCP integration already defines the default project)

SonarSource/sonarqube-agent-plugins

使用 vivado-mcp 离线查询 VCD 波形，定位复位、X/Z、信号变化和握手问题；需要新证据时从已选 XSim 仿真导出有限窗口，不把波形查询当测试判定。

mapleleavessssssss-wq/vivado-mcp

A skill your agent uses for maintainer-requested pull request repairs in kicad-mcp-pro; maps changes to repository-native validation gates and safety constraints.

oaslananka/kicad-mcp-pro

Inspects OmniRoute's MCP server status, lists its tools and scopes, invokes a tool directly, and manages its audit logs.

diegosouzapw/OmniRoute

Play a local audio file through the system's default speakers using Sonilo's MCP server.

sonilo-ai/skills

把用户的可复用需求封装成标准化的 Agent-CLI 工具，并用 myagents tool add 注册进 MyAgents 工具注册表——注册后所有未来会话（builtin / DSH / Claude Code / Codex 全 runtime）的 AI 都会在 system prompt 里自动发现它。触发场景：(1) 用户说「把 XX…

hAcKlyc/MyAgents

Verify API requests in tests. An agent skill from stacklok/toolhive-studio.

stacklok/toolhive-studio

Ahrefs API analyst (extension). An agent skill from AgriciDaniel/claude-seo.

AgriciDaniel/claude-seo

Student weekly assignment planner for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

vishalsachdev/canvas-mcp

Walks through building AI agents that run Solana operations such as token deploys, NFT minting, swaps and staking with SendAI's toolkit, in chat or fully autonomous mode.

internet-court/internet-court-skill

Shows a dashboard for one project, or a table of all projects, from the claude-view MCP server: sessions, branches and contribution data.

tombelieber/claude-view

Teaches the agent to process, ingest, analyze, and compare WebM, MP4, and GIF video recordings using vision-memory-mcp and state-memory-mcp.

putervision/state-memory-mcp

A skill your agent uses when an existing e2a MCP connection, inbox, custom domain, protection policy, webhook, or message delivery is failing or unclear.

tokencanopy/e2a

Drives a live browser through the Playwright MCP server to navigate, inspect, fill forms and screenshot pages, with snapshot-first habits and output-size care.

Hainrixz/editor-pro-max

Method clarity-driven planning workflow using zen-mcp tools (chat, planner, consensus).

VCnoC/Claude-Code-Zen-mcp-Skill-Work

A skill your agent uses when the user wants to try BlockRun's free typed-judgment endpoint (POST api.blockrun.ai/v1/decide, served by OpenJev) on their own data from Claude Code — yes/no, labelled…

BlockRunAI/blockrun-mcp

Audit or report on AI agent security posture across Copilot Studio, Microsoft 365 Copilot, Microsoft Foundry, and third-party agents.

SCStelz/security-investigator

Use official hosted Memtrace documentation before guessing, web search, or stale local copies.

syncable-dev/memtrace-public

Debug a failed Activepieces flow run end-to-end: given a flow run id (or BullMQ job id), find why it failed, cross-referencing the live BullMQ job + Postgres rows (SSH script on the DevOps box), the…

activepieces/activepieces

A skill your agent uses when writing, drafting, scheduling, or improving a Slack message, announcement, or reply sent via the Slack MCP tools (slacksendmessage, slacksendmessagedraft…

slackapi/slack-skills-plugin

5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness.

ruvnet/metaharness

Explores a Spring Boot application and builds primary context: tech stack, module structure, domain entities, REST endpoints.

Amplicode/spring-skills

Runs a three-step daily briefing that refreshes the official Anthropic docs, diffs them against a saved baseline and adds a digest of guide and Claude Code releases.

FlorianBruniaux/claude-code-ultimate-guide

A skill your agent uses when adding a new MCP server to the public MCP catalog (mcp-catalog/data) or preparing/reviewing a catalog-entry PR.

archestra-ai/archestra

Decides whether a web search in Alibaba Cloud Bailian (Model Studio) workflows uses the model's built-in search or the Bailian MCP, based on the connection type.

modelstudioai/cli

AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。

fancyboi999/ai-engineering-from-scratch-zh

MemoryWhale debugging; compiler failures; terminal diagnostics.

wuisabel-gif/MemWhale