发现 Skills

Used in full mode during /mantra:build. Dispatches a fresh subagent per plan task, reviews the task's commit between dispatches, and keeps the main thread's context clean of task-internal details.

Run Claude Code in an isolated Docker sandbox (microVM) for unmonitored tasks. Manage sandboxes, datastore access, data review, and security. Use when launching, managing, or troubleshooting sandbox sessions.

Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with scorecards, findings, owners, remediation actions, and follow-up questions.

Run a 3-agent E2E test team (playwright-cli functional+exploratory, Lighthouse CI, axe-core accessibility) in parallel. Use when the user wants comprehensive end-to-end testing of a web application, including functional tests, performance audits, and accessibility checks. Trigger on phrases like 'run e2e tests', 'full site test', 'test my app end to end', 'check performance and accessibility', or any request for thorough web app quality validation.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Fetches official Hyperliquid API documentation on-demand. Use when answering questions about Hyperliquid API endpoints, websockets, signing, order placement, info queries, exchange actions, rate limits, or any HL API implementation details. Triggers on Hyperliquid API questions.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforce Test-Driven Development (TDD), including unit tests, integration tests, and end-to-end (E2E) tests, ensuring coverage exceeds 80%.

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

Use for Core Location implementation patterns - authorization strategy, monitoring strategy, accuracy selection, background location

Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, deprecated APIs, connection diagnostics, structured concurrency networking.

Use when asking about 'purge files', 'storage pressure', 'disk space iOS', 'isExcludedFromBackup', 'URL resource values', 'volumeAvailableCapacity', 'low storage', 'file purging priority', 'cache management' - comprehensive reference for iOS storage management and URL resource value APIs

Use when creating implementation plans and executing tasks with proactive Codex/Gemini routing and fail-closed Codex behavior before Claude/Sonnet fallback

Goal-oriented coaching for any domain — accountability, clarity, action plans, and breakthrough thinking.

Guidance for building, testing, and reviewing Home Assistant integrations.

Step-by-step guidance for openhue.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Operate across Google Drive, Docs, Sheets, and Slides as one unified workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.

Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years experience managing hundreds of SKUs. Includes forecasting method selection, ABC/XYZ analysis, seasonal transition management, and vendor negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

Renders custom graphics in MewUI controls using IGraphicsContext. Use when implementing OnRender, drawing shapes, text, images, or understanding the Measure/Arrange/Render pipeline.

Enforce branch-based workflow with meaningful Korean commits and PR creation for traceable decision history.

DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, events, messages, and streams.

Algorithmic decision tree enforcing test-first development via boolean conditions instead of imperatives

A fast Rust-based headless browser automation CLI with a Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.