发现 Skills

Use this skill when the user asks to "update study", "analyze new experiments", "update experiment document", or "refresh study notes". It produces academic-paper-quality experiment reports with matplotlib plots, an executive summary with comparison tables, implementation structure and code snippets, experimental results with figure interpretation, proposed improvements with code examples, hypotheses, limitations, and LaTeX PDF export including figures. Features include incremental detection (only analyze NEW experiments), data extraction into a pandas DataFrame, automated plot generation, an iterative writing-improvement loop with quality criteria, zero-hallucination verification, and LaTeX PDF export. Usage - `/update-study logs/experiment.log study.md` or `/update-study "logs/exp1.log logs/exp2.log" results/ablation_study.md`

Automated content creation pipeline for business growth. Creates blog posts, landing pages, email sequences, social media content, and video scripts with a 5-dimensional quality diagnosis, a 12-signal authenticity audit, a headline impact matrix, and content-substance scoring. Use when the user needs content marketing, blog posts, email sequences, copywriting, video scripts, or says “write content”, “blog post”, “email sequence”, “content calendar”, “marketing copy”, “video script”, or “hook”.

Write modern C# code using advanced features such as records, pattern matching, and async/await. Optimize .NET applications, implement enterprise patterns, and ensure comprehensive testing. Use PROACTIVELY for C# refactoring, performance tuning, or complex .NET solutions.

Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.

AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.

Use when optimizing, diagnosing, or reviewing Vertica 11.x SQL query performance — covering EXPLAIN plan reading, projection design for predicates/joins/GROUP BY/ORDER BY/analytic functions, segmentation strategies, column encoding, RLE, sort elimination, Top-K, INSERT-SELECT tuning, DELETE/UPDATE internals, and Data Collector diagnostics.

Use Bitwarden Secrets Manager (BWS) to securely inject secrets into MCP servers and agent tools at runtime. Fetches connection strings, API keys, and credentials from BWS by key name — nothing stored on disk. Use when launching MCP servers that need credentials (databases, APIs, etc.) without hardcoding secrets in config files.

When user mentions "system health", "cleanup", "optimize claude-dash", "memory system", "indexes", "watcher", or wants to maintain the claude-dash infrastructure. Provides self-maintenance guidance.

This skill provides comprehensive guidance for implementing advanced SwiftUI animations, transitions, matched geometry effects, and Metal shader integration. Use when building animations, view transitions, hero animations, or GPU-accelerated effects in SwiftUI apps for iOS and macOS.

Capability maturity evaluation using CMMI, DORA, and custom models for software engineering practices. Use when user asks to "assess maturity".

Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.

API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.

ADR Generator - Auto-activating skill for Technical Documentation. Triggers on: adr generator, adr generator Part of the Technical Documentation skill category.

Build asynchronous video generation workflows with Kling AI. Use when integrating video generation into larger systems or pipelines. Trigger with phrases like 'klingai async', 'kling ai workflow', 'klingai pipeline', 'async video generation'.

Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.

Generate comprehensive OpenSpec specifications directly from the current project state. Use this when you want to create or populate main specs by analyzing the existing code, documentation, AGENTS.md, GitHub issues, and pull requests — without going through the change/proposal workflow. Ideal for bootstrapping specs for a project that already has working code but no specs yet, or for refreshing specs so they match the current implementation.

Use this skill when the user asks to "create a diagram", "draw a flowchart", "make a swimlane diagram", "create WBS", "generate RACI matrix", "build network diagram", "create org chart", or mentions draw.io, diagrams.net, BPMN, UML, Gantt, PERT, or project management diagrams. Integrates with the next-ai-draw-io MCP server for real-time diagram creation and editing.

Use this skill when the user asks phrases like “download icon”, “search icon”, “iconfont”, “find an icon”, or when the user needs to search for and download SVG icons from iconfont.cn.

Load comprehensive GitHub issue information including title, description, comments, labels, assignees, milestones, and related items (linked PRs and cross-references). This skill should be used when planning to fix an issue, when detailed issue context is needed for implementation work, or when a plan command needs to understand the full scope of an issue.

Diagnose flat dialogue, same-voice characters, and lack of subtext. Use when conversations feel wooden, characters sound alike, or dialogue only does one thing at a time.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Conductor workflow patterns for multi-phase orchestration including planning, implementation, review cycles, pause points, and handoffs. Use for lifecycle management, delegation, and state tracking.

Perform a comprehensive security assessment of IoT devices and their ecosystems by testing hardware interfaces, firmware, network communications, cloud APIs, and companion mobile applications. Testers use techniques such as firmware extraction and analysis, hardware debugging via UART and JTAG, network protocol analysis, and runtime exploitation to identify vulnerabilities across IoT layers. Suitable for IoT security testing, embedded device assessments, firmware security analysis, or smart device penetration testing request scenarios.

When the user wants to create, optimize, or audit About page content. Also use when the user mentions "about page," "about us," "company story," "our team," "about section," "company overview," "brand story," "team page," or "who we are." For sitewide page planning, use website-structure.