Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Windows privilege escalation technique using SeImpersonate to escalate from High Integrity to SYSTEM. Use this skill when the user needs to escalate privileges on Windows, mentions token impersonation, SeImpersonate, or wants to run commands as SYSTEM from a High Integrity context. Also trigger when the user has administrative access and wants to impersonate process tokens like winlogon.exe or svchost.exe.
Configure regional settings. Use when: setting timezone, language, compliance rules, currency, or local preferences.
Discover and call remote schema-exposed interfaces with UXC. Use when an agent or skill needs to list operations, inspect operation schemas, and execute OpenAPI, GraphQL, gRPC, MCP, or JSON-RPC calls via one CLI contract.
Clinic-architecture-aligned iOS design system engineering for SwiftUI (iOS 26 / Swift 6.2) covering token architecture, color/typography/spacing systems, component style libraries, asset governance, and theming. Enforces @Equatable on views and keeps design-system usage compatible with Feature-to-Domain+DesignSystem boundaries. Use when building or refactoring DesignSystem infrastructure for the clinic modular MVVM-C stack.
>
Expert reverse engineer specializing in binary analysis, disassembly, decompilation, and software analysis. Masters IDA Pro, Ghidra, radare2, x64dbg, and modern RE toolchains.
Identify, categorize, and prioritize technical debt across six dimensions. Generates remediation plans with effort estimates. Offered by /draft:new-track for refactor tracks.
Manage local skills - list, add, remove, search, edit
Bruk før commit, push eller pull request for å sjekke at koden er trygg å merge
Use when migrating Agentplane tests to @agentplane/testkit, replacing local test helpers, fixing testkit export/build failures, splitting large CLI/backend suites, or diagnosing missing testkit dist exports in package builds.
>-
Shortcut's UI design system. Use when building interfaces inspired by Shortcut's aesthetic - light mode, Inter font, 4px grid.
Intel VTune and AMD uProf profiling skill for microarchitecture analysis. Use when analyzing hotspots, microarchitecture bottlenecks, memory access patterns, pipeline stalls, or using the roofline model. Covers VTune Community Edition (free) and AMD uProf as a free alternative. Activates on queries about VTune, uProf, microarchitecture analysis, pipeline stalls, memory bandwidth, roofline model, or hardware performance analysis.
>
Maintain working context via current-context.md - read before and update after every response with timestamp YYYYMMDD-HHMMSS
PR-backed and current-main optimization manual for the `MiniMaxAI/MiniMax-M2` series, including M2, M2.1, M2.5, M2.7, and M2.7-highspeed. Use when Codex needs to recover, extend, or audit MiniMax-specific optimizations, TP QK norm/all-reduce behavior, parser contracts, distributed runtime behavior, quantized loading, or backend-specific validation.
How to write Claude Code hooks -- event selection, hook types, matcher patterns, blocking vs advisory, portable paths. Use when creating hooks for quality gates, automation, or policy enforcement.
Dependency Upgrade workflow skill. Use this skill when the user needs Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
overledger
>
AWS hosting and deployment patterns covering compute (EC2, ECS, Lambda), networking (ALB, CloudFront, Route 53, API Gateway), databases (RDS, ElastiCache), infrastructure-as-code (CDK), IAM, monitoring (CloudWatch), and cost optimization. Use when deploying applications to AWS or designing cloud architecture. Triggers on AWS, EC2, ECS, Fargate, Lambda, CloudFront, CDK, API Gateway, Route 53, RDS, IAM.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
| Task | Guide |
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
- Use a consistent, professional font (e.g., Arial, Times New Roman) for all deliverables unless otherwise instructed by the user
ai-vulnerability-tracker
>
MicroPython on-device algorithms — PID controller, moving average, Kalman filter, state machine, task scheduler, data logger.
Complete reference for interacting with Bitwarden via the command-line interface.
General-purpose Coda document manager via REST API v1. Supports listing/creating/updating/deleting docs, managing tables/rows/pages, triggering automations, and exploring doc structure. Requires CODA_API_TOKEN environment variable. Delete operations require explicit confirmation; publishing and permission changes require explicit user intent.
Complete Kimai time-tracking API integration. Manage timesheets, customers, projects, activities, teams, invoices and exports via REST API. Supports time tracking workflows, reporting, and administrative operations. Keywords - kimai, zeiterfassung, timesheet, tracking, project, customer, activity, invoice, export, timer, stunden
Location: India Role Focus: DevOps Engineer \| Platform Engineer \|
Connect your agent to TaskMaster — the coordination layer for the agentic economy. Use when your agent needs to post tasks, accept work, earn USDC, and build on-chain reputation. Handles authentication, escrow creation, task lifecycle, dispute flows, and best practices for being a good TaskMaster participant. Requires a TaskMaster API key (get one at taskmaster.tech/connect).
Build multi-panel storyboards programmatically — create projects, upload images/audio to boards, composite annotations, export PDFs, share via public URL. Invoke when the user wants a storyboard, pre-visualization, shot breakdown, animatic, or any ordered sequence of visual panels with text. Hosted at https://agentboard.fly.dev. Works over REST from any agent; MCP tools (mcp__agentboard__*) available in compatible runtimes. If you have your own image/audio generator, use it and UPLOAD the bytes — optional server-side generation endpoints exist as a fallback only for agents without built-in generation.
Non-custodial smart wallets with onchain spending limits and passkey-based human control. Supports **Base** (EVM) and **Solana**. Every wallet gets free gas on creation so your agent can transact imme
Trade on prediction markets. Create a local wallet, list markets, check prices, buy and sell outcome shares. Coming soon: create and fund markets directly from this skill.
GoPlus AgentGuard — AI agent security guard. Run /agentguard checkup for a full security health check: scans all installed skills, checks credentials, permissions, and network exposure, then delivers an HTML report directly to you. Also use for scanning third-party code, blocking dangerous commands, preventing data leaks, evaluating action safety, and running daily security patrols.
Automatically fetch multi-dimensional on-chain data using Nansen CLI, compile a comprehensive and beautifully formatted daily report, and publish it to Binance Square. Auto-run on messages like 'generate nansen daily report', 'post nansen daily to square', or when the user triggers the slash commands `/nansen` or `/post_square`.
>
anti-sycophancy
>
Generate production-quality SVG+PNG technical diagrams from natural language descriptions.
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captures the page with a grid overlay, sends it to the human, and injects clicks based on their reply. Token relay mode detects CAPTCHA type + sitekey, serves the real widget on a relay page for native solving, and injects the token via CDP.
>