Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

安装量: 3
GitHub Stars: 7778
最近更新: 9月10日

MIT21 文件

查看详情 →

kacperkapusciak

社区

goldie

- Create App Store and Play Store screenshots and preview videos for an iOS or Android app. goldie explores the app on a simulator or emulator, writes argent flows, renders framed screenshots and a preview video, and opens a local studio with the finished store page. Use this skill when the user asks for store screenshots, store assets, a preview video, or mentions goldie. Also use it to change assets goldie made before: new headlines, a different background or bezel, or a new screenshot order.

安装量: 3
GitHub Stars: 2166
最近更新: 9月17日

build-review-interface

Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

error-discovery

Run error analysis on a dataset. Build a review UI, select diverse samples, monitor annotations, and organize failure modes.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

eval-audit

Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-discovery, write-judge-prompt, or validate-evaluator instead).

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

evals-start

Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

evaluate-rag

Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

generate-synthetic-data

Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

validate-evaluator

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

write-judge-prompt

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

安装量: 3
GitHub Stars: 1150
最近更新: 9月16日

aspire-deployment

WORKFLOW SKILL — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, AWS, or preview Radius. WHEN: \"deploy Aspire app\", \"publish Aspire artifacts\", \"deploy to Azure Container Apps\", \"generate Kubernetes artifacts\", \"deploy to Radius\", \"tear down Aspire deployment\". INVOKES: aspire CLI, Aspire docs, target cloud/container CLIs. FOR SINGLE OPERATIONS: use generic Azure, Kubernetes, Docker, AWS, or Radius tools only when no Aspire AppHost exists.

安装量: 3
GitHub Stars: 87
最近更新: 9月22日

crypto-com-app

Execute crypto trades (buy, sell, swap, exchange), manage cash deposits and withdrawals, and query account balances, market prices, and transaction history via the Crypto.com APP API. View weekly trading limits, portfolio positions, bank accounts, and payment networks. Use when the user wants to trade cryptocurrency, deposit or withdraw cash, check bank account details, view deposit instructions, or manage fiat wallet operations. Supports BTC, ETH, CRO, and 200+ tokens across fiat and crypto wal

安装量: 3
GitHub Stars: 19
最近更新: 8月29日

humanize-writing

Remove signs of AI-generated writing from English and Russian text without changing what it says. Use whenever the user wants text to sound less like a model and more like a person, even if they don't say "humanize": 'sounds like AI,' 'too robotic,' 'humanize this,' 'de-AI this,' 'sounds like ChatGPT,' 'make it natural,' 'too polished,' 'too generic.' Russian triggers: 'убери нейросетевость,' 'звучит как ChatGPT,' 'сделай по-человечески,' 'слишком канцелярски,' 'оживи текст,' 'слишком гладко,' '

安装量: 3
GitHub Stars: 12
最近更新: 9月23日

3d-web-experience

Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences.

安装量: 3
GitHub Stars: 4.7万
最近更新: 9月22日

nuxt

Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing. Use when working with Nuxt apps, server routes, useFetch, middleware, or hybrid rendering.

安装量: 3
GitHub Stars: 5915
最近更新: 6月23日

clerk-sms-logs

Debug Clerk-delivered SMS (phone verification codes, OTPs) using the sms. Application Logs. Understand the delivery lifecycle — sms.accepted, sms.delivered, sms.failed, sms.undeliverable, sms.unconfirmed — read the normalized failure reason, and follow one message across events by its trace. Use when a user reports "I never got the code", a phone number won't verify, or SMS delivery to a country/carrier looks broken.

安装量: 3
GitHub Stars: 76
最近更新: 9月22日

visualize

Generate beautiful, on-brand HTML artifacts — reports, diagrams, diff reviews, slide decks, plans, recaps, dashboards. Loads on creation intents ("create a plan", "make me an implementation plan", "generate a diagram", "build a slide deck", "draft a recap", "visualize this", "render this as HTML", "make me a status update") and exploration intents ("show me three layouts", "explore document shapes", "compare visual treatments", "explore a new design system", "compare replacement brand directions

安装量: 3
GitHub Stars: 36
最近更新: 9月16日

react-seo-skills

Guides SEO and AI-search visibility for Next.js, Astro, and React apps in Cursor, Claude Code, and Codex. Use when setting up metadata, Open Graph, Twitter cards, Schema.org JSON-LD, sitemaps, robots.txt, optional llms.txt, keyword research, clustering, auditing SEO, improving discoverability, or setting up structured data. Covers Next.js App Router, Pages Router, Astro, and Vite + React SPAs. Matches JavaScript or TypeScript to the project language.

安装量: 3
GitHub Stars: 4
最近更新: 9月9日

frontend-desing

Create distinctive, production-grade frontend interfaces with strong visual identity. Use when building or improving web UIs to avoid generic design and produce polished, memorable results.

安装量: 3
GitHub Stars: 0
最近更新: 6月16日

sepia-hemingway

Use when a user asks to write or revise fiction in the Hemingway manner, or asks for strong de-AI on a story; applies Sepia's built-in Hemingway voice profile.

安装量: 3
GitHub Stars: 2754
最近更新: 9月20日