Skill UI

Actively build and sharpen a project's domain model by challenging terminology, recording glossary terms, and writing ADRs when decisions are hard to reverse and surprising.

This skill statically inspects local JavaScript, Electron, native binary, .NET, and CUDA applications to explain feature functionality with file and line evidence. It supports analyzing packaged .asar files, ELF/PE binaries, EVM bytecode, and CUDA programs without execution. Users must be authorized to study the target. It helps understand or reimplement features safely by parsing code and metadata, refusing requests to bypass security mechanisms or DRM.

Generate or modify Nightingale (n9e) alert notification message templates using Go text/template syntax, including variables, helper functions, and channel-specific escaping for DingTalk, Feishu, email, SMS, and voice.

This skill retrieves up-to-date documentation for third-party APIs, SDKs, and libraries using the chub tool. It ensures code accuracy by fetching current references instead of relying on outdated pre-trained knowledge. Use it when users request tasks involving external services like OpenAI or Stripe. Follow chub instructions to search, fetch, and annotate documentation for better future sessions.

Compile user-authorized durable constraints into OpenViking Rules using the Python SDK or HTTP API, then poll tasks and verify saved rules and scenarios.

This skill assesses technical debt by identifying, classifying, and prioritizing maintainability issues based on classic engineering principles. It helps teams build refactoring roadmaps and justify changes to management. It analyzes decay risks using a Pain × Spread formula and excludes infrastructure health checks.

This skill performs automated PR code reviews to identify decay risks, design smells, and maintainability issues. It applies principles from classic engineering books like Brooks's Law and Mythical Man-Month to provide concrete Symptom → Source → Consequence → Remedy findings. It triggers on code sharing, PR checks, or feedback requests regarding architecture and refactoring.

A repeatable method for writing plain-language design-reading books and articles about why systems are built as they are, using a two-layer skeleton: an everyday analogy first, then formal mechanisms, boundaries, and costs.

Gives AI agents a dedicated email address to send, receive, reply, and wait for replies or verification codes over MCP or HTTP, with self-service onboarding and API key management.

Integrate DoomPay self-custodial DOOM and wDOOM checkout links into websites or apps, create hosted sessions, and verify payment receipts on Doomsday L1 or Base Mainnet.

Read-only verification of cryptographic Proof-of-Escrow collateral (L1 UTXO outpoints and Base Mainnet wDOOM receipts) on GitHub bounties before autonomous agents spend compute. Includes an MCP server for escrow listing and audit.

Commit Craft is a Git workflow tool that organizes mixed changes into logical, reviewable commits before pushing. It blocks secrets like .env files, lints commit messages against standards, and ensures each commit builds independently. Using Python scripts, it plans series, gates secrets, and validates messages without modifying the repository directly, enhancing code quality and security.