发现 Skills

Build Mojo packages (.mojopkg files) for distribution. Use when creating distributable libraries or during packaging phase.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Running Suricata against PCAPs offline and validating results via eve.json

A skill that searches SUUMO for rental properties matching specified criteria and notifies Slack when there are differences from the previous results.

Event routing with Azure Event Grid. Configure topics, subscriptions, event handlers, and dead-lettering. Use for event-driven architectures, serverless triggers, and reactive systems on Azure.

Build reusable component libraries and design systems. Covers design tokens, atomic design, Storybook documentation, variant patterns, compound components, and theming. Use for creating shared UI libraries, design systems, and consistent component APIs.

Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and guides. Use for system documentation, architecture guides, or technical deep-dives.

HAProxy load balancer configuration and management. Set up TCP/HTTP load balancing, SSL termination, health checks, ACLs, and high availability. Use when working with HAProxy, load balancing, reverse proxy, TCP proxying, or high-traffic applications.

Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, and memory systems. Use for enterprise AI, copilot development, and Microsoft ecosystem integrations.

Performs a deep audit and produces concrete fixes for a single harness-eval dimension. Use together with /harness-eval: first run the full evaluation, then when you see WARN/FAIL use this skill to precisely dig in. Usage: /harness-eval-focus D2 (or D1~D10). Trigger keywords: harness-eval-focus, deep audit, dimension fixes, D2 hook issues, D3 permission issues, D1 CLAUDE.md issues, D9 subagents, D10 codebase navigation, harness fixes, agentic diagnostic deep-dive

Design one-off HTML artifacts (landing, deck, prototype).

Initialize development environment for a project. Use when setting up a new project, onboarding a developer, or configuring dependencies.

DAST/ASM workflow for external asset discovery, probing, and scanning with SARIF output. Use for runtime/endpoint-based assessments and asset management scanning.

Handle production incidents with urgency. Use when production issues occur for debugging, fixes, and post-mortems.

Enhanced dependency analyzer with comprehensive markdown reporting and actionable recommendations. Use when you need to optimize frontend project dependencies, detect security vulnerabilities, identify unused packages, find duplicate functionality, analyze dependency impact, generate cleanup scripts, or produce detailed Markdown reports. Supports JavaScript, TypeScript, Vue, React, Angular, and modern build tools with parallel processing and incremental analysis capabilities.

Create and manage datasets on the Hugging Face Hub. Supports initializing repositories, defining configs and system prompts, streaming row updates, and SQL-based dataset querying and transformation. Designed to work alongside the HF MCP server for comprehensive dataset workflows.

Trigger: When you need to collect input from many people, synthesize scattered feedback into an actionable plan, or return the plan to real users/executors for validation. Common signals include stakeholder input, user feedback, aggregated opinions, alignment, and validation. Use this skill for a collect–synthesize–validate loop.

Apply IN18 Kill-Criteria & Stop Rules to define conditions that trigger project termination before launch.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Review code changes using Hyperlane Warp UI coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.

Java logging best practices with SLF4J, structured logging (JSON), and MDC for request tracing. Includes AI-friendly log formats for Claude Code debugging. Use when a user asks about logging, debugging application flow, or analyzing logs.

> Orchestrates skill discovery, installation, and project lifecycle. > This is the central hub for Skills on Demand.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality and identifying methodological flaws. For formal peer review writing use peer-review.