luckycat133
- 17 skills
- 0 followers
- 7 hours ago last updated
- ▌ Pytest · luckycat133Pytest test suite for public-social-account-analyzer. Use for regression tests, mock platform transport, URL validation, stop_reason semantics, immutable workspace boundaries, and report escaping.
- ▌ Web Scraping · luckycat133Public web scraping and collection for public-social-account-analyzer. Use for platform collection adapters, Cookie handling, URL allowlist/canonicalization, browser fallback, rate limiting, and retry strategies.
- ▌ Social Media Analysis · luckycat133Social-media account content analysis pipeline for public-social-account-analyzer. Use for platform adapters (Bilibili/Douyin/Weibo/Xiaohongshu), content classification, business insights, taxonomy drafts, and immutable analysis workspaces.
- ▌ Public Social Account Analyzer · luckycat133 bundleAnalyze specific public creator, brand, or institutional accounts on B站/哔哩哔哩、抖音、微博、小红书. Use for 内容策略、选题栏目、发布节奏、公开互动效率、高低表现共同点、评论区需求、最近N条/日期窗口内容审计. Accept a verified homepage or a nickname/handle that the agent first resolves and verifies; user-provided CSV/JSON can supply external evidence but is not automatically a sealed CLI collection. Do not use for unsupported-platform collectors (including 公众号、YouTube、Instagram、TikTok), private messages, backend analytics, inferred private audience profiles, media downloading, posting, or account-control automation.
- ▌ React Doctor · luckycat133 bundleRun after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
- ▌ Traecnclaw MCP · luckycat133 bundleOperate TraeCN through TRAECNclaw's focused stdio MCP tools. Use when an MCP-capable agent must send or stop work, choose a workspace/model/mode/conversation, inspect or change Trae settings through its UI, manage conversations, or resolve an exceptional question or command approval. Queueing, waiting, recovery, notifications, routine non-command questions, and keep/revert gates are gateway-managed.
- ▌
- ▌ Agent Skills Setup · luckycat133 bundleUse when a user wants to migrate, back up, restore, compare, or move AI-coding-agent context across Cursor, Claude Code, Codex, Cline, Copilot, Windsurf, Gemini CLI, or another supported profile, including switching computers. Handles reviewed Skills, instructions/rules, and MCP with secret redaction, preview, verification, and rollback.
- ▌ MCP Builder · luckycat133 bundleGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
- ▌ Gemini Assist · luckycat133 bundleUse this skill when the user wants a second opinion, critique, code or design review, current-web search that names its sources, image or screenshot understanding, file, URL, or mixed-input understanding, or Deep Research. Prefer this focused skill over the gemini-web-mcp compatibility skill for pure assistance and understanding workloads. Do not use it for pure image, video, or music generation, Gemini account administration, or repository development; route those requests to the creation, account, or development capability instead.
- ▌ Gemini Web MCP · luckycat133 bundleUse this skill when an agent should extend itself with Gemini Web: get a second opinion, search current web sources, understand images/files/URLs, run Deep Research, generate or edit image/video/music artifacts, or explicitly work with Gemini account data. Route by user intent instead of loading every tool. This skill is the compatibility router; prefer the focused gemini-assist skill when only assistance and understanding are needed. Do not use for repository implementation, tests, CI, packaging, or releases—use gemini-web-mcp-development instead.
- ▌ Gemini Web MCP Development · luckycat133 bundleDevelop, refactor, evaluate, package, and release gemini-web-mcp as three focused agent capability products: Gemini assistance and understanding, multimodal creation, and explicit Gemini account management. Use for repository audits, MCP surface design, task-first Agent Skills, shared services, long-operation recovery, artifacts, live compatibility, tests, packaging, or releases.
- ▌ UX Audit · luckycat133 bundleRun UX walkthroughs and QA sweeps on live web apps using browser automation. Walks through apps as a real user, flags friction points and usability issues, tests CRUD operations, and produces ranked audit reports. Trigger with 'ux audit', 'ux walkthrough', 'qa test', 'test the app', or 'check all pages'.
- ▌ Webapp Testing · luckycat133 bundleToolkit for interacting with and testing local web applications using Antigravity's built-in browser automation. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and recording browser sessions.
- ▌ Fullstack Developer · luckycat133End-to-end feature owner with expertise across the entire stack. Capable of delivering complete solutions from database to UI with a focus on seamless integration.
- ▌ Frontend Code Review · luckycat133Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
- ▌ Chat Buddy Web Demo Development · luckycat133 bundleImplement, refactor, review, and test the cloud-first Chat Buddy Web Demo and its shared companion runtime. Use when working on the React Web client, hosted backend, social graph, human/AI friend requests, mixed groups, Moments, proactive messages, character memory, relationship continuity, actor identity linking, weather/calendar/search capabilities, cloud sync, or demo acceptance.