Claude Code 与 Codex 的 AI Agent 技能 · 第 128 页

 ░▒▓███████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░  
░▒▓█▓▒░      ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░ 
░▒▓█▓▒░      ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░ 
 ░▒▓██████▓▒░░▒▓███████▓▒░░▒▓████████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░  
       ░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░ 
       ░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░ 
░▒▓███████▓▒░░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░░▒▓██████▓▒░░▒▓███████▓▒░

为你的 AI 智能体查找、分享并部署可复用技能

npm i -g skhub

cost-allocation

Per-tenant, per-feature, per-query RAG cost tracking. Covers token counting (tiktoken, Anthropic count_tokens), structured metadata logging, aggregation in BigQuery/Snowflake/ClickHouse, dashboards (Grafana, Metabase), LangSmith and Langfuse native cost reports, and budget alerts. Schema + example queries. USE WHEN: user mentions "RAG cost", "cost per tenant", "cost per query", "token counting", "chargeback", "showback", "LangSmith cost", "Langfuse cost", "budget alerts" DO NOT USE FOR: reducing cost - use `rag-production`; batch-discount strategy - use `batch-inference`; routing for cheaper models - use `llm-gateway`

e2e-testing

End-to-end testing workflow with Playwright for browser automation, visual regression, cross-browser testing, and CI/CD integration.

summarize

Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize

triage-validation

Finding validation before writing any report

ai-distributed-training

Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.

liuyao

六爻铜钱卦占卜技能。核心理念："解一卦就是传一道，说一言就是传一智"。支持真实/虚拟起卦，集成儒道哲学。

pirate-weather

Pirate Weather integration. Manage data, records, and automate workflows. Use when the user wants to interact with Pirate Weather data.

browser-automation

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 2025. Critical distinction: Testing automation (predictable apps you control) vs scraping/agent automation (unpredictable sites that fight back). Different problems, different solutions. Use when "playwright, puppeteer, browser automation, headless, web scraping, e2e test, end-to-end, selenium, chromium, browser test, page.click, locator, playwright, puppeteer, browser, automation, testing, scraping, headless, e2e, selenium, web-testing" mentioned.

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

deep-research

对给定选题进行联网深度研究，收集整理资料用于后续内容创作。自动检测可用的网络搜索工具（WebSearch 或 MCP 搜索工具），无可用工具时回退到 DDGS。输出结构化的 Markdown 资料汇总，包含来源引用。

pr-to-lint-rule

Convert a recurring PR review comment into an automated lint rule with tests and CLAUDE.md annotation

wireframing

Low/high fidelity wireframes, user flows, information architecture, prototyping techniques, and design iteration processes

juicebox-security-basics

Apply Juicebox security best practices. Trigger: "juicebox security", "juicebox api key security".

app-launch

When the user wants to plan a launch strategy for a new app or major update. Also use when the user mentions "app launch", "launch plan", "launch checklist", "pre-launch", "launch day", or "how to launch my app". For ongoing ASO after launch, see aso-audit. For paid acquisition during launch, see ua-campaign.

mistral-debug-bundle

Assemble a content-free Mistral diagnostic bundle with hashes, schema facts, and explicit exclusions. Use when escalating a persistent integration problem. Trigger with "build a Mistral debug bundle", "prepare Mistral support evidence", or "sanitize Mistral diagnostics".

obsidian-bases

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

build-dmg

Build a distributable macOS DMG from an Xcode project via the bundled local helper — archive → export → package into one signed artifact. Resolves the project/workspace, scheme, team ID, and export options, regenerates the project first when `xcodegen` is detected, then runs `helpers/build-dmg.sh` from the project root instead of inlining xcodebuild. User-only workflow that touches code signing and provisioning: it never GUESSES the signing identity, never overwrites `ExportOptions.plist` without approval, and reports the built DMG path, version, and signing status. Use only when the user explicitly asks to build or package a DMG.

capawesome-cloud

Guides the agent through setting up and using Capawesome Cloud for Capacitor and Cordova apps. Covers three core workflows: (1) Native Builds — cloud builds for iOS and Android (Capacitor, Cordova, or native projects), signing certificates, environments, Trapeze configuration, and build artifacts; (2) Live Updates — OTA updates via the @capawesome/capacitor-live-update or @capawesome/cordova-live-update plugin, channels, versioning, rollbacks, and code signing; (3) App Store Publishing — automated submissions to Apple App Store (TestFlight) and Google Play Store. Includes CI/CD integration for all workflows. Do not use for non-Capacitor, non-Cordova mobile frameworks such as React Native or Flutter.

发现 AI Agent Skills