探索 MCP Server 与 Agent Skill

io.github.TencentBlueKing/bk-ci/design-patterns

在 BK-CI 中判断何时使用工厂、策略、责任链、观察者、模板方法、装饰器等设计模式时使用。当用户要重构可扩展结构、统一模式选型、理解项目里的模式落点时优先使用。

io.github.TencentBlueKing/bk-ci/database-design

设计 BK-CI 数据库表、DDL 脚本、索引、分表或数据归档策略时使用。当用户提到表结构、字段设计、索引优化、SQL 脚本命名、分片、归档迁移时优先使用。

io.github.cosmicstack-labs/mercury-agent-skills/docker-patterns

Master Dockerfile optimization, multi-stage builds, docker-compose patterns, security hardening, and image size reduction techniques for production-grade containerization.

io.github.openclaw/openclaw/real

Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.

io.github.jamditis/claude-skills-journalism/mobile-debugging

Remote JavaScript console access and debugging on mobile devices. Use when debugging web pages on phones/tablets, accessing console errors without desktop DevTools, testing responsive designs on real devices, or diagnosing mobile-specific issues. Covers Eruda, vConsole, Chrome/Safari remote debugging, and cloud testing platforms.

io.github.NousResearch/hermes-agent/popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

io.github.NousResearch/hermes-agent/codebase-inspection

Inspect codebases w/ pygount: LOC, languages, ratios.

io.github.expo/expo/expo-api-docs

Write TSDoc comments for Expo SDK APIs following official conventions. MUST USE when introducing new user-facing TypeScript APIs in expo-* packages - document APIs correctly from the start, not as an afterthought. Also use when improving existing documentation. Covers @platform, @example, @deprecated, @default annotations, third-person declarative style, blockquote notes, and type export patterns for docs generation.

io.github.gridaco/grida/security

How to handle `GRIDA-SEC-<id>` security boundaries in the Grida repo. Triggers when you encounter a `GRIDA-SEC` tag in source/docs, when modifying files under any tagged path, or when adding a new prevented- vulnerability record. Each `GRIDA-SEC-<id>` identifies a structural trust boundary documented in `/SECURITY.md`. This skill explains the contract, mandates a security review before committing changes to any tagged file, and shows how to register a new id. Use whenever "GRIDA-SEC" appears in context.

io.github.binrogithub/1-3-Cloud-Adoption-Skills/CSS-Autoscaling-Benchmark-Skill

Benchmark and autoscaling test harness for Huawei Cloud CSS (OpenSearch). Use when the task is to evaluate CSS performance, run load tests, validate query quality, test data-node horizontal autoscaling, or generate consolidated benchmark reports for CSS clusters.

io.github.Arindam200/awesome-ai-apps/implement-universal

Harness-agnostic version of `/implement`. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as `agents/software-engineer.md` and `agents/tester.md` instead of being launched as subagents. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), adopts the software-engineer role to implement, then switches to the tester role to verify (logic tickets only). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket. Trigger when the user types `/implement-universal`, asks to "implement task NNN without subagents", or is running in a harness (Cursor, Windsurf, plain Claude API client, etc.) that doesn't support Claude Code's `Task` tool.

io.github.sickn33/antigravity-awesome-skills/git-pr-review

Generate a concise and structured PR description from commit history with minimal token usage

io.github.slopus/happy/agent-browser

Browser automation CLI for AI agents. Use this when asked to test something in a real browser.

io.github.ForceInjection/domain-driven-design-skills/automation-strategy-melodic-software-claude-code-plugins-b69ff37b

Plan test automation strategies including ROI analysis, automation candidate selection, framework evaluation, and maintainable automation architecture.

io.github.ForceInjection/domain-driven-design-skills/automation-pluginagentmarketpla-custom-plugin-qa

Production-grade test automation skill covering Selenium, Cypress, Playwright, Appium with POM architecture, retry logic, and CI/CD integration

io.github.ForceInjection/domain-driven-design-skills/automation-scripts-miles990-claude-software-skil

Build automation, task runners, and scripting tools

io.github.ForceInjection/domain-driven-design-skills/automation-refactor-macroman5-automationhelper-plu

Expert automation workflow refactoring tool for Power Automate, n8n, Make, Zapier and other platforms. Optimizes existing flows by improving performance, reliability, maintainability, and best practices compliance. Triggers when user wants to improve, optimize, refactor, correct values, enhance, or modernize workflows. Analyzes JSON, suggests improvements, outputs refactored flow maintaining original functionality unless changes requested.

io.github.ForceInjection/domain-driven-design-skills/automation-builder-ddunnock-claude-plugins

Analyze codebases and generate Claude Code automation infrastructure including commands, scripts, and templates for systematic task execution. Use when the user wants to create reusable automation workflows, generate .claude/commands files, create supporting bash/python scripts, build markdown templates for structured outputs, or establish multi-step task execution frameworks that work across projects.

io.github.ForceInjection/domain-driven-design-skills/automation-language-selection-csheng-dot-claude

Choose between Shell and Python for generated automation code based on task traits. Use when automation language selection guidance is required.

io.github.ForceInjection/domain-driven-design-skills/css-fundamentals-pluginagentmarketpla-custom-plugin-css-22670519

CSS fundamentals - selectors, specificity, box model, positioning, units

io.github.ForceInjection/domain-driven-design-skills/cursor-mem-chachamaru127-claude-code-harness

Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'past decisions'. Do NOT load for: 通常のコーディング、一時的なメモ、実装作業。

io.github.ForceInjection/domain-driven-design-skills/cursor-debate-go-go-golems-docmgr-1fb60d22

Run a research-first, multi-perspective debate to explore complex technical decisions (trade-offs, architecture choices, integration strategies) using concrete codebase evidence. Use when the user asks to "debate" approaches, compare options, or needs a structured exploration before deciding.

io.github.a5c-ai/babysitter/browser-automation

Automate browser interactions using Playwright, Puppeteer, or Selenium — scraping, testing, and workflow automation for web applications.

io.github.a5c-ai/babysitter/mobile-sensor-integration

Integrate mobile device sensors — accelerometer, gyroscope, GPS, camera, and biometric APIs for iOS and Android.