发现 Skills

Switches NixOS and Home Manager configurations, cleans old generations, and performs system maintenance. Use when running os/home switch, pruning the Nix store, or managing system generations.

Stakeholder reporting standard with Notion integration and Markdown fallback for non-technical project dashboards

Use when designing or debugging Kong DataKit plugin flows, including node selection, DAG wiring, jq transforms, cache or vault usage, and phase-specific request or response orchestration. Do not use for generic decK, Terraform, or Konnect workflow questions.

Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and runtime overrides for language model integration.

Parallel exploration of codebase questions by decomposing into independent tracks. Use when exploring architecture, understanding systems, or investigating complex questions that benefit from multiple perspectives.

Implement the VM pattern using Effect and Effect-Atom for reactive, testable frontend state management. Use this skill when building React applications with View Models that bridge domain services and UI.

Implement the complete spec-driven development workflow from instructions through requirements, design, and implementation planning. Use this skill when starting new features or major refactorings that benefit from structured planning before coding.

Clone an existing video ad for a different product or offer. Analyzes the source video's style, pacing, camera work, dialogue, and tone, then adapts and generates a new Seedance 2.0 video customized for the user's product. End-to-end workflow: input video → analysis → adapted prompt → generation → delivery. Use when someone says "clone this ad", "make this ad but for my product", "recreate this video for my brand", or provides a video ad and a product image asking for a similar video.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Use oc virt (or kubectl virt) to manage KubeVirt virtual machines. Use this skill when the user wants to create, start, stop, or manage VMs on OpenShift/Kubernetes.

Test for Cursor IDE CVE-2026-31854 RCE via Indirect Prompt Injection

Analyzes income vs expense balance and financial health scoring. Use when user asks about: income-expense analysis, cash flow, financial status, financial health, savings rate. Triggers: 收支分析, 收支平衡, 现金流, 财务状况, 财务健康, 财务评分, 存了多少钱.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Schematic capture and wiring. Create schematic sheets, place symbols, add wires and net labels, organize hierarchical designs.

Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI application, Next.js AI, useChat, streamText, ai-elements, build AI app, create chatbot

Create and deliver terminal-based presentations from Markdown files with themes, code execution, Mermaid/D2 diagrams, LaTeX/Typst formulas, and PDF/HTML export capabilities.

For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations

Run unit tests with coverage

Claude Code-optimized context transfer for development workflows. Preserves code context, git state, running services, and development environment when moving work between sessions. Works seamlessly with peer review skills (Codex/Gemini). Use when transferring development work to a new Claude Code session.

Development guide for the lemline-core module. Use when working with workflow execution (orchestrators, processors), node tree navigation (Node, NodePosition), task states (TaskState, WorkflowCommand, WorkflowEvent), expression evaluation (JQ, scope), error handling (TryTask, retry, catch), parallel execution (Fork), or DSL parsing. Covers the step-by-step execution model, exception-driven control flow, and stateless architecture.

Extract physics problems from PDF files or image files and output them in a standardized Markdown format. Automatically name images and display them using Markdown, and format formulas with LaTeX. Suitable for organizing physics problem banks, entering questions, digitizing PDF problems, and similar scenarios.

Hard Problem Conquest — Ace AI problem cracking; if you can't solve it, don't expect to hold your ground in the tech community.

検証Agent - 全層の結果を検証し、最終判定（PASS/REVISE/REJECT）を下す

Use when incidents occur and you need to triage, categorize, and execute response runbooks automatically. Correlates alerts, identifies root causes, escalates to appropriate teams, and executes remediation procedures for production incidents.