“[mp-skills CLI, Node.js 18+]” 共 2,650 个结果
io.github.langbot-app/LangBot/langbot-deploy
部署并配置 LangBot 实例——Docker / Docker Compose、Kubernetes、config.yaml 模型、Box 沙箱运行时、插件运行时，以及全局 API key。在生产或自托管环境中安装、部署、升级或配置 LangBot 时使用。触发语包括 deploy langbot、langbot docker、langbot compose、langbot kubernetes、langbot config.yaml、langbot box runtime、langbot global api key。
io.github.thedotmack/claude-mem/childhood
Babysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.
io.github.OpenHands/OpenHands/verify-openhands
This skill should be used to "verify OpenHands features", "test the Canvas UI like a user", "drive Agent Canvas", "check a UI change in the real app", "create or update the feature map", "run the daily pass" or "run the weekly feature audit". Ships control-openhands (launch, doctor, browser, LLM profiles, conversations, evidence, map tooling, cleanup) and the maintained map of every user-facing feature.
io.github.Significant-Gravitas/AutoGPT/pr-test
使用 docker compose、agent-browser 与 API 调用对 PR/分支进行 E2E 手动测试。当用户要求手动测试 PR、端到端测试某功能，或对运行中的系统执行集成测试时触发。
io.github.thedotmack/claude-mem/mem-search
搜索 claude-mem 的跨会话持久记忆数据库。当用户问「我们之前解决过这个吗」「上次 X 是怎么做的」，或需要既往会话的工作时使用。
io.github.CherryHQ/cherry-studio/find-simplifications
Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.
io.github.vinta/awesome-python/scan-github-stars
Scan the maintainer's GitHub stars for README.md addition candidates; incremental by default, `full` rejudges stars judged before.
io.github.vinta/awesome-python/preview-verdicts
当裁剪扫描、批量条目编辑或结构调整需要在改动 README.md 之前由维护者审查时，生成交互式保留/删除裁决预览（带逐行反馈控件的 HTML 页面），并处理维护者粘贴回来的反馈 JSON。
io.github.DietrichGebert/ponytail/ponytail
强制采用真正可行的最懒方案：最简、最短、最少。模仿一位见惯一切资深工程师的姿态：先质疑任务是否根本不必存在（YAGNI），优先标准库而非自写代码、平台原生能力而非引依赖、一行而非五十行。支持强度档位：lite、full（默认）、ultra。适用于任何编码任务：编写、新增、重构、修复、审查、设计代码以及选择库或依赖。当用户说 ponytail、be lazy、lazy mode、最简方案、minimal solution、YAGNI、do less、shortest path，或抱怨过度设计、膨胀、模板代码、不必要的依赖时也应使用。不用于非编码请求（通识、文章、翻译、摘要、菜谱）。
io.github.vinta/awesome-python/review-prs
分诊开放的 PR——先基于 diff 初筛，把准入判断交给 audit-the-list，然后在 GitHub 上合并或关闭。当维护者要求审查 PR、处理 PR 队列，或判断某个 PR 是否应当合并时触发。
io.github.Significant-Gravitas/AutoGPT/write-frontend-tests
分析当前分支相对 dev 的 diff，为改动的前端页面/组件规划集成测试并编写。当用户要求编写前端测试、补充测试覆盖，或说为我的改动写测试时触发。
io.github.Significant-Gravitas/AutoGPT/pr-review
评审 PR 的正确性、安全性、代码质量与测试问题。当用户要求评审 PR、检查 PR 质量或对 PR 给出反馈时触发。
io.github.Significant-Gravitas/AutoGPT/perf-compare
Shared measurement recipe for AutoGPT performance work. Compares a baseline and a candidate in Sentry (two releases, two environments such as preview pr-<n> deploys, or two time windows) per transaction: count, p50/p95/p99, failure rate, and a trace-clustered bootstrap verdict of faster / slower / no detectable change / not enough data, with exit codes agents can branch on. Works for span duration, web vitals (measurements.lcp) or any numeric span field. TRIGGER when an agent needs to show a change made the backend or frontend faster or slower, compare a preview against a control or dev, check a release after merge on dev or prod, or check for regressions.
io.github.anthropics/skills/claude-api
Claude API / Anthropic SDK 参考——模型 id、定价、参数、流式输出、工具调用、MCP、agent、缓存、token 计数、模型迁移。触发条件：提示中出现任何 Claude/Anthropic 相关名称（Claude、Anthropic、Fable、Opus、Sonnet、Haiku 等）；用户询问 LLM 相关问题（定价/选型/限额/缓存）时不要凭记忆回答；或任务属于 LLM 类且未指明供应商。仅当明确针对其他供应商（OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama）时跳过。
io.github.microsoft/PowerToys/ui-tests-migration
将 PowerToys UI 测试从 WinAppDriver/Selenium 迁移并稳定到 Microsoft.PowerToys.UITest.Next 与 winappcli。适用于移植、新建 UITest 工程、CI flaky 测试、本地 Hyper-V 虚拟机持续验证、可重置的干净基线运行、Settings IPC 鉴权/测试签名、Explorer/Shell 选择、预览 handler、缩略图提供程序、快捷键激活、有状态进程生命周期、WinUI/WebView 合成视觉基线，以及跨窗口/前台失焦问题。涵盖 API、脚手架、测试设计、诊断、agent 化执行与 CI 加固。关键词：UI test、UITestAutomation.Next、winappcli、WinAppDriver、Selenium、Settings IPC、Authenticode、local VM、Hyper-V、checkpoint、flaky、CI stability、WebView2。
io.github.DietrichGebert/ponytail/ponytail-audit
Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit.
io.github.DietrichGebert/ponytail/ponytail-audit
Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.
io.github.DietrichGebert/ponytail/ponytail-review
审查 diff 中的过度工程。找出该删的东西：重复造的标准库、多余依赖、投机性抽象。每条发现一行。
io.github.nukeop/nuclear/making-demo-videos
Use when making a demo, tutorial, or feature video of Nuclear. Covers driving the app with WebDriver and real cursor input, recording with OpenScreen, generating voiceover, music, background images, and Nuki mascot images, and composing the video in Remotion (packages/videos).
io.github.strapi/strapi/likec4-dsl
Use when working with `.c4`/`.likec4` files or LikeC4 CLI/config questions where exact DSL/CLI syntax is required, especially for strict command/snippet-first answers, validate/export flags, predicates `*`/`_`/`**`, deployment snippets, dynamic views, or relationship extension matching.
io.github.thedotmack/claude-mem/cloud-sync
设置或检查 claude-mem 与 cmem.ai Pro 的云同步。当用户说「set up cloud sync」「sync my memories」「cmem pro」「cloud backup」「sync status」，或希望备份/同步记忆数据库到其 cmem.ai 账户时使用。
io.github.stablyai/orca/computer-use
通过 orca computer 对可见的本地应用窗口进行 OS/窗口级检视与输入:原生应用、外部浏览器窗口(Chrome、Edge、Safari)和应用 webview。不适用于 Orca 内置浏览器(用 orca-cli)或纯页面自动化(用 Playwright 或 CDP)。
io.github.elie222/inbox-zero/cloud-dev-environment
用于本地开发的 Cursor Cloud VM 配置与服务启动说明。
io.github.payloadcms/payload/ui4-review
Review UI4 CSS migrations for proper token usage. Checks that CSS variables are used instead of hardcoded values.
