发现 Skills

Implement file upload flows with presigned URLs (S3, GCS, R2), multipart/tus resumable uploads, Sharp image processing, drag-and-drop UI with progress indicators, server-side MIME validation via magic bytes, virus scanning, and CDN serving. Use when adding profile pictures, document attachments, media galleries, or any user-submitted file feature.

Use this skill when creating or editing GitHub Copilot customization Markdown files (agent profiles, prompt files, instruction files, and skills).

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, applications, or redesign existing UIs. Generates creative, polished code that avoids generic AI aesthetics. Triggers on frontend design, UI design, redesign, build component, create page, web interface, React UI.

Audits Claude Code project setup and provides a score with actionable recommendations. Use when a user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.

Formats git commit messages according to Conventional Commits specification. Use this when the user asks to commit changes or write a commit message.

Automate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts. Always search tools first to retrieve current tool schemas.

Generates protocol-based analytics infrastructure with swappable providers (TelemetryDeck, Firebase, Mixpanel). Use when user wants to add analytics, track events, or set up telemetry.

Generates a complete settings screen for iOS/macOS apps with common sections. Use when user wants to add settings, preferences, or configuration UI.

Standardizes testing and validation for rsyslog using the diag.sh framework.

Use when asked to run 'fly ssh console', SSH into Fly.io machines, inspect files on production machines, check processes on Fly.io, or examine deployed machine state. Covers critical pitfalls like images without a shell and Debian vs macOS command differences.

Working with the Navigator Go submodule for web server fixes and enhancements. Use when deployment plans require Navigator changes, config parsing issues arise, or new routing/proxy behavior is needed.

Discover new feature opportunities from multiple sources — creative brainstorming, user feedback, ecosystem evolution, technical possibilities, and cross-project research — and add them to .feature-radar/opportunities/. Use this when the user wants to generate NEW ideas rather than evaluate existing ones. Even casual mentions like "I wonder what else we could do" or "let's think about new features" should trigger this skill. Use when: - Brainstorming creative feature ideas or exploring new directions - User says "what else could we build?" or "give me some ideas" - Reviewing user feedback, GitHub issues, or community requests for unmet needs - Exploring adjacent tools and ecosystems for inspiration - Periodic opportunity refresh to keep the backlog current Trigger phrases: "scan opportunities", "find new features", "brainstorm ideas", "what could we build", "refresh opportunities", "scan ecosystem", "give me feature ideas", "what are we missing", "explore new directions"

Java Web source-code routing multi-level call-chain tracing tool. Given a user-specified route path, it traces the complete call chain from Controller/Action to the DAO layer and outputs each layer's file location, method signature, and possible input parameters. Suitable for parameter-flow analysis for various vulnerability types: (1) SQL injection - trace parameters to SQL concatenation points, (2) command injection - trace parameters to Runtime.exec(), (3) SSRF - trace parameters to HTTP requests, (4) XSS - trace parameters to response output, (5) file operations - trace parameters to File operations, (6) XXE/deserialization/LDAP injection/expression injection, etc. Supports frameworks such as Spring MVC, Struts 2, Servlet, JAX-RS. **Supports decompiling .class/.jar files to extract call chains**. Can be combined with java-route-mapper to achieve complete route + call-chain auditing.

Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

Recognize Fastly CDN queries and delegate to specialized sub-agent to avoid context pollution

Recognize AWS queries and delegate to specialized sub-agent to avoid context pollution

Apply the Kilpi security methodology at the organisational level. Use when helping users complete the Template (Org) covering all 6 NIST CSF 2.0 functions: Govern, Identify, Protect, Detect, Respond, Recover. Triggers on: filling in organisational security templates, org-level risk assessment, org-level security policy, completing Kilpi compliance for the organisation, "apply Kilpi to the org", "fill in the security template".

Breaks a PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets). Use when decomposing a PRD into implementation work, creating tracer-bullet issues, or when the user says "break down PRD," "create issues from PRD," or "/prd-to-issues."

CRITICAL: Use for Makepad packaging and deployment. Triggers on: deploy, package, APK, IPA, 打包, 部署, cargo-packager, cargo-makepad, WASM, Android, iOS, distribution, installer, .deb, .dmg, .nsis

Manage client-side state in Storefront Next using React context providers and feature-level Zustand stores. Use when handling basket/auth UI state, creating extension stores (for example store locator), or syncing client-visible state after server mutations. NOT for server-side data loading — see sfnext-data-fetching for loader patterns.

../../../c-level-advisor/executive-mentor/skills/challenge/SKILL.md

Code review guidelines covering code quality, security, and best practices.

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.