发现 Skills

Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization

Guide to Jasminum for retrieving CNKI Chinese academic metadata in Zotero

Guide to Zotero PDF Translate for multilingual PDF and annotation translation

Creates Wagmi features across all layers - core actions, query options, framework bindings. Use when adding new actions, hooks, or working across packages/core, packages/react, packages/vue.

Dense platform reference for Salesforce Metadata API — package.xml structure, metadata types, source vs MDAPI format, deploy/retrieve commands, destructive changes, and common errors. Optimized for quick lookup.

Generate Wheels MVC controllers with CRUD actions, filters, parameter verification, and proper rendering. Use when creating or modifying controllers, adding actions, implementing filters for authentication/authorization, handling form submissions, or rendering views/JSON. Ensures proper Wheels conventions and prevents common controller errors.

This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies.

Git提交专家，规范化提交信息和分主题提交。

Verify debug/dev artifacts are removed before commit. Use at session end to apply 'good boy scout' rule - leave code cleaner than you found it.

Model-Deployment standards for model deployment in Ml Ai environments.

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment. **Trigger**: citation anchoring, citation drift, regression, cite stability, 引用锚定, 引用漂移. **Use when**: after editing/polishing, you want to confirm citations did not migrate across `###` subsections. **Skip if**: you do not have a baseline anchor file yet. **Network**: none. **Guardrail**: analysis-only; do not edit content.

Use MCP servers to reduce tokens and avoid manual data transfer

This skill should be used when the user asks to "create a skill", "write SKILL.md", "what are skill best practices", "how to optimize a skill", "improve skill quality", or mentions skill development, trigger phrases, skill structure, or content quality. Provides comprehensive guidance for creating high-quality Claude Code skills following latest standards.

A guide for creating production-ready Agent Skills. Use it when creating new skills, improving existing ones, or diagnosing why a skill isn't working effectively. Covers skill quality standards, five reusable skill types, progressive-disclosure UX design, loading triggers and lazy initialization, and validation checklists.

Skill to extract key information from tender documents (PDF/DOCX/TXT). Trigger scenarios: - The user requests extraction of information from tender documents (tenderer, reference number, price cap, warranty period, validity period, etc.) - The user mentions "tender", "bid document", or "procurement document" and needs key fields extracted - The user needs to batch-extract consistent fields from multiple tender documents - The user needs to organize tender information into a structured format (e.g., CSV) Even if the user does not explicitly say "tender", this skill should be used when the user asks to extract key fields from procurement or bid documents.

Publish long-form content to Telegraph for clean, instant-view reading in Telegram. Use when sending reports, research results, analysis, documentation, or any content that exceeds ~4000 characters. Do NOT use for short messages — send those directly. Do NOT use when the user explicitly asks for a file attachment.

Gemini CLI reference for Google's terminal AI agent. Covers installation, authentication, commands, MCP config, extensions, checkpointing, and cross-invocation with Cursor/Claude agents.

Building WinUI 3 apps. Windows App SDK setup, XAML patterns, MSIX/unpackaged deploy, UWP migration.

Focused pattern for fetching data using URL parameters in Next.js. Covers creating dynamic routes ([id], [slug]) and accessing route parameters in server components to fetch data from APIs. Use when building pages that display individual items (product pages, blog posts, user profiles) based on a URL parameter. Complements nextjs-dynamic-routes-params with a simplified, common-case pattern.

Generates structured IBM i (AS/400) Program Specifications for RPGLE and CLLE programs from business requirements. V2.5 — tiered SDD spec system with Lite/Standard/Full levels, Business Rules (BR-xx), Traceability Matrix, Data Contract, Interface Contract, and mandatory error handling. Automatically selects the right spec level based on change complexity. Use this skill whenever a user provides business requirements, change requests, or functional descriptions and wants them converted into a formal Program Spec document for IBM i development. Also trigger when the user asks to "write a program spec", "create a spec for RPG", "generate a CLLE spec", "document this program", "spec out this AS/400 program", or mentions RPG IV, RPGLE, CLLE, iSeries, or AS/400 in the context of program design. Even if the user just pastes a business requirement and mentions IBM i or RPG — use this skill. This is a specification-generation skill, not a code-generation skill.

Expert knowledge of Express.js and Node.js for building production-ready web applications and APIs. Covers middleware patterns, routing, async/await error handling, security, performance optimization, proxy patterns, static file serving, and production deployment. Use when working with server.js, adding routes, implementing middleware, debugging Express issues, or optimizing API endpoints.

XMind Curated Template Library — 30 professional-grade mind map templates covering six major scenarios: classic layouts, business strategy, project management, analysis & decision-making, learning & knowledge, and creative & personal. Each template includes unique color schemes, layout structures, and content skeletons. Designed to be used with xmind-generator-skill.

Ask Claude Code to produce an implementation plan before you write code. Use when the task is complex, touches multiple files, or has unclear requirements. Claude returns a numbered step-by-step plan with file paths and interfaces — you implement it.

Delegate a code review task to Claude Code via the claude_code MCP tool. Use this when you want Claude's judgment on architecture, security, correctness, test coverage, or code quality for files you've just written or modified.