「Data Analysis」搜索结果 — MCP 与 Agent Skill

backward-compat

io.github.tabler/tabler/backward-compat

Keep a change to `@tabler/core` backward compatible, so a patch or minor release never breaks a project that updates. Use before renaming, removing or changing the meaning of anything a user can touch — a class, a `--tblr-*` custom property, a Sass variable, mixin or function, a `data-*` attribute or option, a JS export, an event, a file under `dist/`, a default value — and whenever a changeset on `dev` looks like it needs a `major` bump. Also consult it proactively when a cleanup or refactor in `core/` deletes something, since "dead" code is often somebody's API. Covers what counts as public API, the `deprecated` files where compatibility code lives, the alias patterns, the `check:compat` gate, and what to do when a break cannot be avoided.

source

在 SkillsMP 查看

共享库规范

SkillSkillsMP

io.github.tabler/tabler/shared-lib

把逻辑移出 Astro frontmatter 到 `shared/lib/*.ts`，并用 vitest 测试覆盖。当 frontmatter 膨胀到不止拼装类名、demo 数据需要整形或格式化、同一辅助函数出现在两个组件中，或用户要求在 `shared/` 下写 helper、工具或单元测试时使用。涵盖该位置的归属内容、模块约定、同级 `*.test.ts` 规则、确定性 demo 数据，以及本仓库使用的严格 TypeScript 模式。

source

在 SkillsMP 查看

v8-security-triaging

SkillSkillsMP

io.github.nodejs/node/v8-security-triaging

Guides the initial analysis and impact assessment of a V8 security report, strictly excluding implementation or fixing.

source

在 SkillsMP 查看

gke-ai-troubleshooting-tpu-mxla-hang

SkillSkillsMP

io.github.google/skills/gke-ai-troubleshooting-tpu-mxla-hang

Diagnose GKE Cloud TPU multi-slice training hangs (Megascale `HANG_DETECTED` logs and hang monitored events) using the ML Diagnostics `Megascale XLA (MXLA) Hang Analyzer` (`gcloud alpha mldiagnostics monitored-events`) and 1-minute Cloud Monitoring multi-slice latency metrics (`kubernetes.io/container/multislice/*`). Distinguishes XLA compiler/HLO launch divergence and host data-input stalls from TPU chip, SparseCore, ICI, or network fabric faults. Use when multi-slice TPU training jobs freeze without progressing steps, emit `HANG_DETECTED`, or stall in collective operations. Don't use for gradual step-time throughput drops without hangs (use gke-ai-troubleshooting-tpu-performance-degradation) or pod preemption/eviction restarts (use gke-ai-troubleshooting-jobset-interruption).

context7-mcp(实时库文档)

SkillSkillsMP

io.github.upstash/context7/context7-mcp

通过 Context7 MCP 服务器获取最新的按版本区分的库文档和代码示例。用户询问任何库、框架、SDK、API、CLI 工具或云服务(含 API 语法、配置、安装说明、版本迁移、CLI 用法、库特定调试)时使用;调用第三方库生成代码时使用;用户指明版本(如 Next.js 15、React 19)时使用。React、Vue、Next.js、Prisma、Supabase、Express、Tailwind、Django、Spring Boot 等知名库同样适用,因为训练数据可能未反映最新变化。库文档优先于网络搜索。不用于:重构、从零编写脚本、业务逻辑调试、代码审查、通用编程概念,或用户已提供相关文档时。

source

在 SkillsMP 查看

alint-ruleset

SkillSkillsMP

io.github.lobehub/lobehub/alint-ruleset

Maintain LobeHub's model-backed alint rule set in packages/alint: author a rule, calibrate its false positives against real source, decide its severity (warn vs error) from real PR data, and track its token cost. Use for adding or narrowing an alint rule, classifying findings as true/false positives, promoting or demoting a rule, or running the weekly rule-set review.

source

在 SkillsMP 查看

create-plugin

SkillSkillsMP

io.github.ToolJet/ToolJet/create-plugin

Creates, scaffolds, updates, or validates a ToolJet marketplace plugin (connector, integration, or data source) under marketplace/plugins/ from an OpenAPI spec, Postman collection, npm package, database driver, or API docs. Use when asked to create, build, generate, scaffold, add, update, check, or validate a marketplace plugin, connector, or data source. Not for built-in connectors in plugins/packages/.

source

在 SkillsMP 查看

find-docs(文档检索)

SkillSkillsMP

io.github.upstash/context7/find-docs

为任意开发者技术检索最新文档、API 参考和代码示例。只要用户询问特定库、框架、SDK、CLI 工具或云服务——包括 React、Next.js、Prisma、Express、Tailwind、Django、Spring Boot 等知名库——就使用本技能,因为训练数据可能未反映最近的 API 变更或版本更新。以下情况务必使用:API 语法问题、配置项、版本迁移问题、提到库名的 "how do I" 问题、涉及库特定行为的调试、安装说明,以及 CLI 工具用法。即使认为已知答案也应使用——不要依赖训练数据中的 API 细节、签名或配置项,务必对照当前文档核实;库文档与 API 细节优先于网络搜索。

source

在 SkillsMP 查看

perf-compare

SkillSkillsMP

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.

source

在 SkillsMP 查看

motion-graphics（动态图形）

SkillSkillsMP

io.github.heygen-com/hyperframes/motion-graphics

以运动本身传递信息的短设计型 motion graphic——动态字体、数字滚动、图表/数据可视化呈现、logo 片头/品牌定格、下三分之一字幕条/浮层/社媒 overlay、动画地图（区域高亮、地点连线、缩放到某地）、推文/新闻文章/标题动画、网页/UI 动画（滚动、光标、callout），或将真实图片的几何结构融入图表。通常 10 秒以内（最长约 30 秒），无旁白与真人实拍；渲染为 MP4 或透明 overlay。更长的/有旁白的/多场景的用 /general-video；不明确的用 /hyperframes。

source

在 SkillsMP 查看

gateguard

SkillSkillsMP

io.github.affaan-m/ECC/gateguard

PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit and NotebookEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.

source

在 SkillsMP 查看

browser-extract(浏览器数据提取)

SkillSkillsMP

io.github.ruvnet/ruflo/browser-extract

通过已存储的 browser-templates 模板或一次性 DOM 查询提取结构化数据;在内容送入模型前强制执行 AIDefence 的 PII 与提示注入过滤。

source

在 SkillsMP 查看

test-collaboration

SkillSkillsMP

io.github.affaan-m/ECC/test-collaboration

Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit/integration/contract/E2E/smoke classification, bug-to-test regression protection, consumer/provider contract testing, test-necessity review, and pre-delivery evidence review.

source

在 SkillsMP 查看

test-collaboration

SkillSkillsMP

io.github.affaan-m/ECC/test-collaboration

Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit/integration/contract/E2E/smoke classification, bug-to-test regression protection, consumer/provider contract testing, test-necessity review, and pre-delivery evidence review.

source

在 SkillsMP 查看

启用 Partial Prefetching（Next.js）

SkillSkillsMP

io.github.vercel/next.js/next-partial-prefetching-adoption

在 Next.js 应用中开启 Partial Prefetching 并消化其给出的洞察。当用户要启用或接入 Partial Prefetching、切换 partialPrefetching 标志、用 export const prefetch = 'partial' 让路由接入、审计 Link prefetch={true} 行为、用 instant() 测试保护已预取的 UI，或解决 instant-link-prefetch-partial 与 instant-shell-url-data 洞察时使用。

source

在 SkillsMP 查看

browser-use 开源库文档

SkillSkillsMP

io.github.browser-use/browser-use/open-source

基于 browser-use 开源库编写 Python 代码的文档参考。凡涉及 Agent、Browser、Tools 配置、导入 browser_use 的代码、@sandbox 部署、支持的 LLM 模型、Actor API、自定义 tools、lifecycle hooks、MCP 服务器搭建、Laminar 或 OpenLIT 监控/可观测性，以及 browser-use 安装、prompt 策略、敏感数据处理时都适用。不适用于 Cloud API/SDK 用法与定价——用 cloud skill；也不适用于通过 CLI 命令直接驱动浏览器——用 browser-use skill。

source

在 SkillsMP 查看

React Hook Form 规范（Supabase）

SkillSkillsMP

io.github.supabase/supabase/react-hook-form

在 monorepo 内正确使用 React Hook Form——数据流、订阅、reset、脏状态、数字输入以及受控输入规则。在编写或修改任何表单代码、给已有表单加字段、使用 watch/useWatch/formState/getValues/setValue/reset、把表单接入 dialog 或 sheet、或实现提交/取消底栏之前先加载本 skill，即使改动看起来很简单。仓库中普遍存在 RHF 反模式，不加载本 skill 会照抄它们。表单布局与选用组件请再加载 studio-ui-patterns。

source

在 SkillsMP 查看

ci-metrics

SkillSkillsMP

io.github.pytorch/pytorch/ci-metrics

Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics. Use when users ask about CI duration, job failures, queue times, workflow trends, runner health, dashboard data, or PyTorch infrastructure metrics.

source

在 SkillsMP 查看

禁用无检查索引访问 no-unchecked-indexed-access

SkillSkillsMP

io.github.thedaviddias/Front-End-Checklist/no-unchecked-indexed-access

审计 tsconfig.json 是否缺少安全标志、审查数据处理流水线中用到数组索引访问的代码，或排查 TypeScript 未捕获的运行时 undefined 错误时使用。

source

在 SkillsMP 查看

禁用显式 any no-explicit-any

SkillSkillsMP

io.github.thedaviddias/Front-End-Checklist/no-explicit-any

审查 TypeScript 文件的类型安全回退、评审处理外部数据的函数，或代码库中存在 @typescript-eslint/no-explicit-any 的 ESLint 警告时使用。

source

在 SkillsMP 查看

浏览器缓存 browser-caching

SkillSkillsMP

io.github.thedaviddias/Front-End-Checklist/browser-caching

排查页面加载缓慢、资源过大或渲染延迟，落实“启用浏览器缓存”时使用。在 DevTools、Lighthouse 或真实数据中确认实际瓶颈后再提改动建议。

source

在 SkillsMP 查看

浏览器性能审计 browser-required

SkillSkillsMP

io.github.thedaviddias/Front-End-Checklist/browser-required

排查页面加载缓慢、资源过大或渲染延迟，落实“执行浏览器端性能审计”时使用。在 DevTools、Lighthouse 或真实数据中确认实际瓶颈后再提改动建议。

source

在 SkillsMP 查看

CSS 体积优化 css-file-size

SkillSkillsMP

io.github.thedaviddias/Front-End-Checklist/css-file-size

排查页面加载缓慢、资源过大或渲染延迟，落实“优化 CSS 文件体积”时使用。在 DevTools、Lighthouse 或真实数据中确认实际瓶颈后再提改动建议。

source

在 SkillsMP 查看

requirements-clarification

SkillSkillsMP

io.github.asgeirtj/system_prompts_leaks/requirements-clarification

Clarify a material user-owned product decision before substantive implementation commitments. Use only when request and named/governing evidence still leave a choice that would materially change scope, platform support, user-facing surface, data/API contract, domain values, project placement, or cross-system architecture; also use when a truncated request omits such a choice. On the initial turn, inspect only named or governing requirements evidence, then ask directly without loading: prefer structured input; ask one blocking outcome question or at most three coupled questions; wait. After the answer, load the body before write or delegation. Do not use for implement/build/fix/debug/refactor work when expected behavior is settled, plan/design deliverables owned by Plan, complexity/greenfield/integration alone, agent-owned technical choices, locally discoverable facts, reversible defaults, permission to begin, or stop/no-tool turns. Never re-ask supplied facts or turn clarification into refusal.