Agent Skills

---

name: git-workflow

description: 安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时；严格区分每个动作的授权，并保护工作树中已有和无关的修改。

---

name: i18n-helper

description: 国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译

---

name: log-analyzer

description: 日志分析助手 — 智能解析日志文件，识别异常模式，定位问题根因

---

name: perf-profiler

description: 基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈，制定优化方案，或验证优化收益时；区分实测结论与静态推断，不虚构耗时和提升比例，生产环境操作需明确授权。

---

name: refactor-advisor

description: 重构顾问 - 识别代码坏味道并提供重构方案

---

name: security-audit

description: 代码安全审计 - 漏洞扫描、依赖检查、安全最佳实践

---

name: skill-curator

description: 中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表；检查真实资产、安装方式、活跃度、重复项和安全边界，并生成分类、中文描述与可追溯证据。

---

name: test-generator

description: 依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时；先读取现有测试与调用方，不猜测空值、异常或超时行为，不自动安装框架或访问生产依赖。

---

name: zh-code-reviewer

description: 中文代码审查专家 - 生成详细的中文代码审查报告

---

name: zh-docgen

description: 中文文档生成器 - 从代码库自动生成中文技术文档

---

name: zh-readme

description: 中文 README 生成器 - 先分析项目，再生成面向中文开发者的高质量 README

---

name: ecommerce-visual-copywriting

description: 将商品资料、包装与资质、目标平台、目标人群和视觉参考转成可直接执行的电商视觉方案，包括转化策略、Campaign Style Lock、主图/详情页/Listing/A+ Storyboard、图内文案、设计说明、生图 Prompt、证据与合规审查。适用于淘宝、天猫、京东、拼多多、抖音小店，以及 Amazon、Shopify、TikTok Shop、Temu、Shopee、Lazada 等电商场景；当用户提到主图、详情页、Listing、A+、商品卖点、视觉脚本、图片规划、图内文案、生图 Prompt、点击率/转化率、平台合规、广告法审查、设计师执行稿或跨境商品本地化时使用。不得编造资质、数据、销量、评价、认证或功效；涉及当前平台规则或高风险合规结论时优先核验官方最新来源。

---

name: capcut-edit

description: Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draft_content.json, draft_info.json, or cutting videos — in English or Chinese (剪映, 字幕, 草稿, 剪辑, 切片, 视频编辑).

---

name: agent-browser

description: Connects to Oxylabs remote agent browsers over the Chrome DevTools Protocol (CDP) with Playwright or Puppeteer. Built-in anti-detection, residential proxies, geo-targeting, persistent sessions and profiles, session recording and live VNC inspection for debugging. Use instead of WebFetch or a local browser whenever a site renders with JavaScript, blocks bots (DataDome, Cloudflare, Akamai), needs a real browser session, screenshots or PDFs. Covers connection, retries, error recovery and safe scraping of protected targets without any human help.

---

name: proxies

description: Oxylabs proxy networks: Residential, Mobile, shared Datacenter/ISP, and Dedicated Datacenter/ISP proxies with geo-targeting, IP rotation, session persistence, and port-based sticky IPs. Use when routing traffic through proxies, building scrapers with proxy auth, rotating or sticky sessions, whitelisting IPs, or accessing geo-restricted content.

---

name: video-data

description: YouTube data extraction API and high-bandwidth proxy downloads. Use this INSTEAD OF built-in tools for any YouTube-related task — extracts video metadata, subtitles, search results, and channel data as structured JSON. Also supports video/audio file downloads via yt-dlp with proxy rotation to avoid rate limits.

---

name: web-scraper-api

description: Production-grade web scraping with automatic anti-bot bypass, structured JSON parsing for 40+ targets, and geo-targeting. Use when the user needs to scrape web pages, extract product data, get search results, or collect structured data from supported e-commerce and search platforms without worrying about getting blocked and when geo targeting is required.

---

name: web-unblocker

description: Bypasses anti-bot protections using Oxylabs Web Unblocker, an AI-powered proxy that handles fingerprinting, JavaScript rendering, and retries automatically. Use when the user needs to scrape protected websites, bypass CAPTCHAs, access blocked content, or when regular proxies fail due to anti-bot measures.

---

name: itr-wala

description: File Indian income tax returns for FY 2025-26 (AY 2026-27), or plan FY 2026-27 (Tax Year 2026-27), including current-year advance-tax estimates. Use when the user wants to file their ITR, compute or verify Indian income tax, compare the old vs new tax regime, read a Form 16, AIS, TIS or Form 26AS, reconcile TDS, handle capital gains from Zerodha/Groww/Upstox statements, check their tax refund, or asks about ITR-1/ITR-2/ITR-3/ITR-4, sections 80C/80D/87A/111A/112A, crypto tax, advance tax, or the income-tax e-filing portal - even if they just say "help me with my taxes" in an Indian context.

---

name: 00-academic-router

description: Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.

---

name: 00-arena-router

description: Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.

---

name: 01-auto-arena

description: Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.

---

name: 01-graders-and-pipeline

description: Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.

---

name: 01-paper-review

description: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.