发现 Skills

Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.

Instrument applications with Azure Monitor and OpenTelemetry for JavaScript (@azure/monitor-opentelemetry). Use when adding distributed tracing, metrics, and logs to Node.js applications with Application Insights.

Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.

Playwright E2E patterns for React apps with Keycloak auth and Apollo Client GraphQL. Two-layer auth bypass, operation-name routing, fixture creation rules, MUI selectors. Based on production PoC.

Proactive log and build monitoring. Scans application logs, test results, build output, and CI artifacts with smart filtering to detect issues before users report them. Language-aware via CC_LANGUAGE — adapts error patterns per stack.

Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.

Guidelines for .NET backend development with C#, ASP.NET Core, and Entity Framework Core

Expert in Laravel PHP development with best practices and modern patterns

Use this skill whenever the user wants to monitor, watch, or track Polymarket prediction market prices over time. This includes setting up price alerts, watching for significant price movements, tracking spread changes, monitoring volume spikes, or getting notified about market activity. Trigger on: monitor prices, price alert, watch market, track prices, notify me, price change, polymarket alerts, market watch, price movement, volume spike, spread monitoring, track odds, prediction market alerts, continuous monitoring, price tracker, market surveillance.

Use this skill for large-project maintenance with a layered CLAUDE.md index system. It triggers when users need to (1) analyze and document existing codebases, (2) generate hierarchical CLAUDE.md files for modules, (3) set up incremental update hooks after code changes, or (4) navigate large projects efficiently. Supports legacy project onboarding and automatic context management.

Expert for Business Continuity Management (BCM) with deep knowledge of ISO 22301, ISO 22313, and integration with ISO 27001. Automatically activated when user asks about business continuity, disaster recovery, crisis management, emergency planning, BC plans, BC exercises, or BCM compliance.

Work with hermes, the GCE VM hosting web services. Use when modifying hermes configuration.

[Responsibility boundary] Dedicated to automatic moodboard generation for Day 3 S1. Clearly distinguished from the paired skills image-gen (general image generation) · media-gpt-image2-builder (GPT Image 2 advertising images) — a moodboard is the design-direction establishment stage, not actual ad image generation. Use this skill for requests such as: "Make a moodboard", "Pick a color palette", "Set the image tone", "I want to define the design direction", "Find reference images", "Plan the atmosphere", "Set tone and manner", "Day3 S1 moodboard". V6 Day3 ⑫ Create 1 moodboard + work card (deliverable ⑫, Day3 S1 demo at 10:10–10:25, SPEC §3.1).

Midjourney v8.1 (2026.03 Alpha) dedicated image prompt builder. It takes a single-line natural-language user input plus AskUserQuestion presets and fine-tuning to collect context, then converts that context into keywords plus `--parameter` format based on the Midjourney official Parameter List. The result can be copied and pasted directly into Discord `/imagine` or alpha.midjourney.com. Supports `--sref`/`--oref`/`--cw`/`--p`/`--hd`/`--q 4`/`--style raw`/`--no`/`--c`/`--s`. As a bonus, it also outputs prompts for GPT-image-2 (6-Block) and Gemini 3 Pro Image (5-component) simultaneously. Use this skill whenever a user requests any of the following: - "Make me a Midjourney prompt", "MJ prompt" - "Midjourney prompt", "Write an /imagine prompt" - "Midjourney v8 prompt", "Midjourney 8.1 prompt" - "--sref prompt", "--oref prompt", "style code prompt" - "/midjourney-v8-prompt" (direct invocation) Because Midjourney restricts official API automation, this skill only produces prompt text; the user must run the actual generation on Discord or the web alpha themselves.

We develop integrated SEO audits and optimization strategies for Naver, Google, and AI search (GEO). Ask: 'Audit my SEO', 'Create a Naver top-ranking strategy', 'Analyze keywords', 'Optimize for Google Search', 'Create a GEO strategy', or 'Tell me how to improve C‑Rank'. Generates on-page and technical SEO, keyword strategy, and AI-search optimization reports.

Apply brand colors and typography to artifacts. Use when brand colors, style guidelines, visual formatting, or company design standards apply. Ensures consistency across branded content.

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Automatically extract reusable patterns from opencode sessions and save them as learned skills for future use.

Create and submit a GitHub Pull Request.

Generate and edit images using Google Gemini's native image generation models (Nano Banana / Nano Banana Pro). Supports text-to-image, image editing with reference images, multi-image composition, and character consistency. Use when the user asks to generate images via Gemini, create AI illustrations, edit photos with Gemini, or needs high-quality image generation with the Google API. Requires GEMINI_API_KEY. Triggers: "generate image with gemini", "nano banana", "gemini image", "create illustration", "AI generate picture", "text to image".

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", "mail.gov.in", "NICeMail", "load saved session", or any task requiring programmatic web interaction.

Use when building IoT apps. Keywords: IoT, Internet of Things, sensor, MQTT, device, edge computing, telemetry, actuator, smart home, gateway, protocol, 物联网, 传感器, 边缘计算, 智能家居

Format all git commit messages using Conventional Commits with a gitmoji prefix. Automatically apply whenever generating or suggesting a commit message.

Generate AWS architecture diagrams from infrastructure JSON. Use when user asks to "generate diagram", "create AWS diagram", "visualize infrastructure", or "draw architecture".