研究与知识

retrieving-developer-knowledge

20Kresearch-knowledge

Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query) or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax, IAM permissions, official documentation, architectural comparisons, or product choice overviews. Don't use for local filesystem lookups or non-Google documentation.

google-cloud-filestore-autoscale

Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds (custom thresholds apply globally across projects in session memory), or preventing out-of-space outages. Don't use for Cloud Storage (GCS) buckets, Persistent Disk block storage, or NetApp Volumes.

pua-en

针对重复失败、被动行为、完成质量问题或明确要求“更努力”的性能辅导模式。采用结构化故障排查和证据优先的交付习惯。

tanweai

datalineage-summary

Summarizes Google Cloud Data Lineage graphs to help users debug data quality issues and understand data provenance for BQ/GCS. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).

hindsight-docs

面向AI代理的完整Hindsight文档。使用此文档了解Hindsight架构、API、配置和最佳实践。

vectorize-io

notebooklm

18Kresearch-knowledge

Google NotebookLM 的完整 API 实现，支持全功能代码化 / 编程访问，包含 Web 界面尚未开放的高级特性。可创建笔记本、添加数据源、生成各类衍生内容（Artifacts）并支持多格式下载。可通过显式输入 `/notebooklm` 或触发相关意图（如“制作关于 X 的播客”）来激活。

teng-lin

deepeval

18Kresearch-knowledge

DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools, retrieval, or agent behavior from eval failures. AI agents are the primary use case. Covers Python SDK, pytest eval suites, CLI generation, traced evals, Confident AI reporting, and agent-driven improvement loops. DO NOT TRIGGER for unrelated generic pytest, non-AI test setup, or non-DeepEval observability work unless the user asks to compare or migrate to DeepEval; for instrumenting an app with DeepEval tracing, @observe, or framework integrations (use the `deepeval-tracing` skill); or for raw OpenTelemetry / OTLP export without the deepeval package (use the `deepeval-otel` skill).

confident-ai

context-fundamentals

17Kresearch-knowledge

此技能应用于解释或推理上下文工程的基础概念：什么是上下文、上下文窗口的构成、注意力机制的工作原理、U型注意力曲线、为什么上下文质量比数量更重要，以及理解所有其他上下文工程决策所需的思维模型。用于概念解释、入门培训和背景阅读。将操作性工作路由到专门技能：调试注意力失败转到context-degradation，令牌效率工作转到context-optimization，对话摘要转到context-compression，项目形态决策转到project-development。

muratcankoylan

datalineage-bigquery-asset-impact-analysis

17Kresearch-knowledge

Analyzes the downstream impact (blast radius) when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast radius or impact analysis for a BigQuery table or view. - Assessing the consequences of modifying, deleting, or pausing updates to a BigQuery asset. - Identifying downstream dependencies (tables, dashboards, processes) of a BigQuery asset. Don't use for: - General BigQuery querying or data analysis (use BigQuery-related tools instead). - Non-BigQuery assets (e.g., Cloud Storage files) unless they are part of the BigQuery lineage. - Creating or modifying lineage links directly.

local-seo

17Kresearch-knowledge

Audit a Google Business Profile, compare it to local competitors, and map Maps visibility around a location.

skill-creator

16Kresearch-knowledge

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

vercel-labs

bigquery-ai-ml

16Kresearch-knowledge

利用 BigQuery 内置的机器学习与生成式 AI（GenAI）能力进行高级数据分析。适用于编写 SQL 查询以实现时间序列预测、数值预测、异常检测、关键驱动因素分析、语义搜索或向量检索、文本分类、相似度计算、内容摘要生成、语言翻译、模型评估、按语义条件过滤，以及在 BigQuery 中调用生成式 AI 能力等场景。请勿用于处理常规的 BigQuery 数据集、数据表或作业管理需求。

agent-platform-deploy

把 Model Garden 中的开源模型或自定义权重部署到 Agent Platform 端点、查看正在进行的部署进度，或通过取消部署模型及删除端点来清理资源。适用于以下场景：主动部署模型、列出 Model Garden 中可用的模型目录（CATALOG）、检查特定模型是否支持部署（`gcloud ai model-garden models list-deployment-config`）、查询部署成本、排查部署报错（如配额限制），以及取消部署/清理端点。拷贝并部署 1P 微调模型（1P Tuned Model）时也使用本 Skill。如果是纯查询/探索类问题，例如“X 部署了吗？”、“列出我的端点”或“哪些区域有运行中的模型？”，请勿使用本 Skill，而应使用 `agent-platform-endpoint-management`。如果是公共 Vertex AI 部署，请使用 `vertex-deploy` Skill；如果是运行模型评估，请使用 `agent-platform-eval-flywheel` Skill。

gemini-api

当用户询问企业级环境下的 Gemini 使用，或明确提到 Vertex AI、Google Cloud 或 Agent Platform 时使用。本 Skill 指导如何在 Agent Platform 上通过 Google Gen AI SDK 使用 Gemini API，涵盖 SDK 的用法（Python、JS/TS、Go、Java、C#），以及多模态输入、工具调用、媒体生成、上下文缓存、批量预测和 Live API 等核心能力。

papercuts

将真实、反复出现的仓库摩擦记录到 .agents/PAPERCUTS.md — 令人困惑的设置、不稳定的仓库命令或脚本、仓库内误导性错误、过时的生成文件，或会浪费下一位贡献者时间的非显而易见的陷阱。也用于审查、去重和解决现有条目。记录前严格把关：只有仓库本身能修复的摩擦才算数。绝不记录代理自身的沙箱/权限错误、shell 脚本错误、瞬时波动或仓库无法改变的第三方工具怪癖。

openseo-review-web-content

为 OpenSEO 网站（web/）撰写和审核内容——博客文章、指南、功能页面、常见问题解答。提炼出品牌一致、实用、准确内容的理念。在 web/content 或 web/src 中添加或编辑面向用户的文案时使用。

seo-flow

13Kresearch-knowledge

FLOW框架集成：基于证据的SEO，使用“发现→利用→优化→获胜”循环。从FLOW知识库（41个提示，CC BY 4.0）中提取特定阶段的AI提示。当用户提到“FLOW”、“FLOW框架”、“seo flow”、“基于证据的SEO”、“发现利用优化获胜”或需要特定阶段的SEO提示时使用。

agricidaniel

seo-cluster

12Kresearch-knowledge

基于 Google 搜索结果（SERP）重合度的语义主题聚类工具，专为内容架构规划设计。本工具通过实际的 Google 搜索结果重合度（而非单纯的文本字面相似度）对关键词进行精准聚类，设计中心辐射式（Hub-and-Spoke）内容集群与内链矩阵，并生成交互式可视化视图。若安装了 claude-blog，还可直接自动化执行内容创作。当用户提到“topic cluster”（主题聚类）、“content cluster”（内容集群）、“semantic clustering”（语义聚类）、“pillar page”（柱页/核心页）、“hub and spoke”（中心辐射架构）、“content architecture”（内容架构）、“keyword grouping”（关键词分组）或“cluster plan”（集群计划）时使用。

agricidaniel

seo-backlinks

12Kresearch-knowledge

反向链接画像分析：引荐域名、锚文本分布、毒性链接检测、竞争对手差距分析。支持免费 API（Moz、Bing Webmaster、Common Crawl）和 DataForSEO 扩展。当用户提及反向链接、链接画像、引荐域名、锚文本、毒性链接、链接差距、链接建设、拒绝或反向链接审计时使用。

agricidaniel

merge-ready

12Kresearch-knowledge

Take a branch from "code exists (or is about to)" to "ready for the maintainer's final review" — multi-axis subagent review with verified findings, fixes, ci:check, checkpoint commits, and an updated PR. Use whenever the user says a feature/fix/branch should be "merge ready", asks to get changes ready for review, or appends this to a build request ("build X and make it merge-ready").