发现 Skills

Interact with and control the Love2D game via IPC. Use this skill when you need to see what's on screen, navigate menus, send input commands, take screenshots, or get game state. Start the game first, then use the IPC commands to control it.

Write, validate, tune, test, and improve ModSecurity 3.0 / Coraza WAF rules and OWASP Core Rule Set (CRS) configurations using a developer-led security approach and OODA loop methodology. Converts OpenAPI specifications into positive-security WAF rules for inclusion before CRS evaluation. Supports false positive analysis, rule exclusions, audit log analysis, go-ftw testing, CRS Sandbox testing, regex assembly with crs-toolchain, CRSLang (next-gen rule format), and CI/CD integration. Use when the user mentions ModSecurity, Coraza, CRS, SecRule, WAF rules, web application firewall, false positives, paranoia level, anomaly scoring, audit logs, go-ftw, rule tuning, OpenAPI to WAF, CRSLang, positive security model, JA4, JA3, TLS fingerprint, CDN (CloudFront, Akamai, Cloudflare, Fastly), or load balancer. Primary target is ModSecurity v3; supports migration from v2.

Set up react-strict-dom with Babel, PostCSS, and CSS-wrapped HTML components for universal Expo apps

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.

Multi-phase data analysis workflow with question formulation, exploration, deep insights, and actionable recommendations. Leverages Gemini's large context for comprehensive data analysis with user interaction checkpoints.

This skill should be used when the user asks to "write Priority code", "create a form trigger", "write a procedure", "create an interface", "debug Priority code", "write a step query", "create a report", "use WSCLIENT", "parse XML in Priority", "use SFTP in Priority", "generate a document", "use WINHTML", "write DBI syntax", "create a table in Priority", "load data with INTERFACE", "use DBLOAD", "write Priority SQL", "create a BPM", "write a dashboard procedure", "use WebSDK", "manage form columns", "add form column via WebSDK", "write column trigger code", "create a subform", "write an expression column", "set up a foreign-key picker", "websdk_form_action", or mentions Priority ERP development, form triggers, SQLI, Priority procedures, or Priority SDK. Provides comprehensive reference for the Priority ERP SDK including SQL dialect, forms, triggers, reports, procedures, interfaces, documents, web services, WebSDK operations, and debugging tools.

Configure, test, and manage log rotation on Linux servers. Prevent disk-full disasters.

Install, configure, and manage Paperless-ngx — a self-hosted document management system with OCR, tagging, and full-text search.

Use when needing to reorder, split, drop, or amend git commits that are not the top commit, without interactive editor access. Covers programmatic rebase via GIT_SEQUENCE_EDITOR, commit splitting with automated hunk selection, and metadata changes (author, message, dates) on any commit in a range.

Capture and organize memories, decisions, and learnings to a memories.md file. Use when you want to save context for future sessions.

Log a bug report. Use when a user asks to create, log, file, or report a bug.

This skill should be used when a user asks to 'search the web', 'fetch content from URL', 'extract page content', 'use Tavily search', 'scrape this website', 'get information from this link', or 'web search for X'.

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use this skill when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when users mention Canvas files in Obsidian.

Search Fetch.ai's Agentverse for agents by keyword, capability, or protocol. Returns agent names, addresses, descriptions, and supported protocols. Use when asked to find, discover, or list available agents on Agentverse. Requires AGENTVERSE_API_KEY env var.

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

Generate taginfo project JSON files for TILDA topics, extracting OSM tags from processing code.

Use when creating, maintaining, reading, or debugging OpenCode plugins. Triggers on any work involving @opencode-ai/plugin, plugin hooks, custom tools for OpenCode, or opencode.json plugin configuration.

Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need a syntax reference, or are troubleshooting library-specific issues.

Implement feature access checks using Flowglad to gate premium features, create paywalls, and restrict functionality based on subscription status. Use this skill when adding paid-only features or checking user entitlements.

Revision and editing assistant for Crucible-drafted novels. Use when author has completed a first draft and wants to revise, edit, or polish their manuscript. Handles developmental editing, line editing, copy editing, and final polish. Triggers on "edit my novel," "revise chapter X," "polish my manuscript," "help me edit," or when user has completed draft chapters and wants to improve them.

Validates Claude Code plugins against architectural best practices for Agents, Skills, MCP, and Progressive Disclosure. Use when validating plugin structure, reviewing manifest files, checking frontmatter compliance, or verifying tool invocation patterns.