发现 Skills

Google Search Console optimization. Index coverage, performance analysis, sitemap management, and search appearance debugging.

Implement features from PLANS.md using the plan-driven-coder agent

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Sub-skill of Activepieces: 1. Basic Flow Structure.

Sub-skill of Obsidian: File Information.

Sub-skill of documentation: MkDocs Setup (+3).

Sub-skill of cad-engineering: Open-Source CAD Expertise (+3).

Sub-skill of freecad-automation: Output Formats.

Sub-skill of cfd-pipeline: Path A: FreeCAD/CAD to Gmsh (+3).

Memory sidecar for agent work: recall before tasks, record learnings after tasks, review recommendations, optional backport bundles.

Use when deploying OpenClaw with Codex, enabling a third-party model API, connecting Feishu with plugin auto-detect/install, and enabling browser automation with end-to-end verification.

Use when deploying or troubleshooting OpenClaw with Feishu in single-bot or multi-bot multi-agent routing, including credential collection, bindings, verification, and go-live checks.

Provides real browser automation capabilities for Agents, supporting semantic element locating, form interactions, screenshots and screen recordings, script execution, and session management.

This skill should be used when the user asks about "Next.js with Bun", "Bun and Next", "running Next.js on Bun", "Next.js development with Bun", "create-next-app with Bun", or building Next.js applications using Bun as the runtime.

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.

120+ Vue/Nuxt animated components built for TailwindCSS v4, motion-v, GSAP, and Three.js. Ideal for hero sections, 3D effects, interactive backgrounds, and more. Includes setup guidance and troubleshooting for CSS variable scoping and motion-v integration errors.

This skill should be used when the user asks to "set up Nuxt Studio", "configure Studio OAuth", "deploy Studio to Cloudflare", "add visual editor to Nuxt", "configure studio.domain.com subdomain", "Studio authentication", "Nuxt CMS", or mentions visual content editing, Nuxt Studio module, TipTap editor, Monaco editor, or content management for Nuxt websites.

Detect test smells, overmocking, flaky tests, and coverage issues. Analyze test effectiveness, maintainability, and reliability. Use when reviewing tests or improving test quality.

Guide for using the Team-Shinchan plugin’s agents, skills, and memory system. Use when you need help.

Create a new specification through an adaptive interview process with proactive recommendations and optional research. Supports high-level, detailed, and full technical documentation depths. Use when user says "create spec", "new spec", "generate spec", "write a spec", "PRD", "product requirements", or wants to start a specification document.

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.

Launch the Gemini CLI as a headless sub-agent in a tmux pane, monitor its stream-json JSONL output, and poll for completion. Use this when delegating a well-defined task to a Gemini agent subprocess with live observability. Triggers include "run gemini agent", "delegate to gemini", "gemini sub-agent", or any request to run Gemini headlessly and monitor it.

Validates, sanitizes, and safely stores uploaded files to prevent malware execution, path traversal, and storage abuse. Use whenever accepting file uploads from users. Triggers on: file upload, multipart, file type validation, MIME type, malware scan, S3 upload, path traversal, file extension, image upload, document upload, upload size limit.

Work with jsonwebtoken — integrate, configure, and automate. Use when asked to set up jsonwebtoken, use jsonwebtoken API, integrate jsonwebtoken into a project, troubleshoot jsonwebtoken errors, or build jsonwebtoken automation.