发现 Skills

Provides comprehensive guidance for JUnit testing framework including test annotations, assertions, test lifecycle, and best practices. Use when the user asks about JUnit, needs to write Java unit tests, use JUnit annotations, or configure JUnit for Java projects.

Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)

Based on PatSnap (智慧芽) data, generates a complete patent strategy research report for enterprises (HTML format, conventional report layout). Covers eight major sections including company overview, core competencies, competitive landscape, market opportunities, core risks, strategic recommendations and PatSnap solutions — each main assertion is supported by patent or literature evidence.

Effect-TS patterns for Streams. Use when working with streams in Effect-TS applications.

Develops cloud-native Go applications with context propagation, graceful shutdown, health checks, and configuration management for production.

WebSocket connection manager with state machine (connecting/connected/reconnecting/error), exponential backoff, and message routing

Implements GoF design patterns and SOLID/DRY/YAGNI principles to architect scalable, maintainable, and testable software systems.

Real-time market data handling with WebSockets including connection management, data aggregation, and robust error recovery

Implements Makefile best practices for build automation including phony targets, pattern rules, variable scoping, and cross-platform compatibility to streamline software build processes.

Implements intelligent task intelligence with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense

Create, query, audit, and optimize Google Ads campaigns. Supports both API mode (google-ads Python SDK) and browser automation. Use for campaign management, performance analysis, keyword optimization, and ad creation.

Performance coaching for when an AI agent fails significantly. Triggered by "go to remedy". Uses Wendy Rhoades-style coaching (from Billions) to identify root causes, fix systems, and rebuild confidence through evidence. Posts to a dedicated channel with a sub-agent coach.

Create high-quality animated explainer visuals for essays and blog posts. Use when the user wants to visualize concepts, processes, data, or ideas with interactive web animations. Triggers on requests like "create a visual for", "animate this concept", "make an explainer", "visualize this idea", "diagram this process", "show this data", or when essay content would benefit from visual explanation. Handles abstract concepts (mental models, frameworks), technical processes (algorithms, systems), and data visualization (trends, comparisons). Outputs self-contained HTML/CSS/JS that embeds directly in web content.

Work with PDF files - extract text for analysis, get metadata, merge/split documents, convert formats, search content, and OCR scanned documents. Use when you need to read, analyze, or manipulate PDF files.

Sets up Google Tag Manager and Google Analytics 4 for websites with automated browser setup via claude-in-chrome. Use when launching a new site needing tracking, migrating to GTM/GA4, adding event tracking (clicks, forms, conversions), setting up e-commerce tracking, or debugging tracking issues. Trigger phrases include "set up GTM", "configure GA4", "tracking plan", "add event tracking", "debug analytics". NOT for analyzing existing data/reports (use google-analytics MCP), keyword research (use keyword-research), or SEO optimization (use seo-optimization).

Production-ready templates for packaging AI agents as installable software. Use when the user mentions: template, scaffold, boilerplate, starter, skeleton, package.json, pyproject.toml, Dockerfile, docker-compose, MCP server template, Claude Code plugin template, LangGraph deploy, install script, release action, GitHub Actions, agent packaging template, generate template, gen-template, cookiecutter, project structure

Interviews the user to plan a feature and produce a PRD. Covers scoping requirements, defining specs, and designing solutions. Use when starting new work that needs planning, requirements definition, feature scoping, or creating a product requirements document.

Improves CLAUDE.md by analyzing conversation patterns. Use when Claude keeps repeating a mistake, when teaching a new preference, or when consolidating guidance from repeated instructions. Captures recurring corrections and style preferences into project instructions.

Database design, operations, and platform-specific patterns. Schema design principles, migrations, query optimization, transactions, connection pooling, and Convex-specific best practices. Reference skill for all database work.

Parse new financial documents into Moneta. Detect type, run parser, validate output, summarize reconciliation.

Complete PostHog lifecycle management. Audits current state, fixes all issues, and verifies event tracking works end-to-end. Every run does all of this. Auto-invoke when: files contain posthog/analytics/tracking, imports posthog-js package, references POSTHOG_* env vars, event tracking code modified, user mentions "analytics not working" or "events not sending".

Design monochrome ornamental patterns grounded in Alexander Speltz's classical ornament taxonomy. Covers historical period selection, motif structural analysis, prompt construction for line art and silhouette rendering, and AI-assisted image generation via Z-Image. Use when creating decorative borders, medallions, or friezes in a single color, exploring historical ornament styles through generative AI, producing line art or pen-and-ink renderings of classical motifs, or generating reference imagery for design or educational materials.

Set up centralized log aggregation with Loki and Promtail (or ELK stack), including log parsing, label extraction, retention policies, and integration with metrics for correlation. Use when consolidating logs from multiple services into a searchable system, replacing local log files with centralized queryable storage, correlating logs with metrics and traces, implementing structured logging with label extraction, or troubleshooting production incidents requiring cross-service log analysis.

Create a new agent definition file following the development-guides agent template and registry conventions. Covers persona design, tool selection, skill assignment, model choice, frontmatter schema, required sections, registry integration, and discovery symlink verification. Use when adding a new specialized agent to the library, defining a persona for a Claude Code subagent, or creating a domain-specific assistant with curated skills and tools.