发现 Skills

Use when simplifying, cleaning up, or de-bloating a patch, branch, PR, or changed diff before review or merge, especially when code may duplicate existing helpers, carry temporary scaffolding or over-abstraction, add hot-path overhead, grow a noisy diff, or accumulate redundant intermediate TDD tests.

Nx, Turborepo, and Lerna workflows for monorepo management. Use for large-scale projects with multiple packages.

Used when it is necessary to identify project risks or handle risk escalations. The Risk Management Commander orchestrates the risk-identification and risk-management sub-skills. Keywords: risk management, risk identification, risk monitoring, risk escalation, risk register, risk alert, emergency escalation, project risk.

Use when you need to consolidate the user-feedback handling process into a complete, deliverable closed‑loop report. The User Feedback Closed‑Loop Report is auto‑generated and includes analysis of feedback sources, processing progress tracking, closed‑loop rate statistics, unresolved issues, and improvement recommendations. Keywords: user feedback closed‑loop, feedback report, feedback tracking, closed‑loop rate, VOC closure, feedback handling, is the feedback handled, user opinions.

Build data pipelines for La-Z-Boy analytics and reporting. Covers ETL/ELT patterns, data validation, scheduling, error handling, and data quality monitoring using Python, Pandas, and Airflow. Use when building data ingestion or transformation workflows.

Analyzes API documentation from OpenAPI specs to provide TypeScript interfaces, request/response formats, and implementation guidance. Use when implementing API integrations, debugging API errors (400, 401, 404), replacing mock APIs, verifying data types, or when user mentions endpoints, API calls, or backend integration.

Create connector-grounded technical discovery memos, repo reconnaissance reports, feasibility assessments, spike plans, risk registers, unknowns lists, and downstream handoff notes before architecture or implementation work. Use this when the user asks to investigate technical feasibility, inspect a repo before planning, research dependencies or integrations, compare implementation options, identify unknowns, map risks, plan a spike, or prepare technical input for architecture-design-desk, issue-planning-desk, or implementation-handoff-desk.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

References PLAN.md and architecture maps to forbid agents from leaking domain boundaries or mixing monolithic files. Covers DDD bounded contexts, context maps, relationship patterns, architecture enforcement tools (ArchUnit, Spring Modulith, ContextCov), modular monolith patterns, and layered enforcement strategy. Use when the user needs to (1) enforce domain boundaries in AI-generated code, (2) prevent domain leakage across bounded contexts, (3) validate code against architecture constraints, (4) maintain modular monolith boundaries, or (5) implement architecture governance and drift detection.

USE WHEN: building web components, pages, or applications requiring distinctive visual design, user says "design", "UI", "frontend", "interface", or wants production-grade aesthetics. DO NOT USE WHEN: backend work, API development, simple scripts, or when generic styling is acceptable.

USE WHEN: teaching complex topics requiring chunked delivery, handling mid-explanation questions, preserving context across interrupts, deep-dive explanations with nested topics. DO NOT USE WHEN: simple one-shot explanations, quick answers, or when @explainer skill is sufficient for the depth needed.

Framework-agnostic CSS patterns for typography, color, motion, and spatial composition.

Complete guide for Axum web framework including routing, extractors, middleware, state management, error handling, and production deployment

Container orchestration with Docker Compose for multi-container applications, networking, volumes, and production deployment

Core JavaScript language features, patterns, and best practices including ES6+ syntax, async/await, closures, prototypes, and modern development patterns

Comprehensive PostgreSQL database engineering skill covering indexing strategies, query optimization, performance tuning, partitioning, replication, backup and recovery, high availability, and production database management. Master advanced PostgreSQL features including MVCC, VACUUM operations, connection pooling, monitoring, and scalability patterns.

Low/high fidelity wireframes, user flows, information architecture, prototyping techniques, and design iteration processes

Generate Excalidraw diagrams from natural language descriptions. Use when asked to create a diagram, make a flowchart, visualize a process, draw a system architecture, create a mind map, or generate an Excalidraw file. Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Splat YAML configuration reference for N64 decompilation projects. Use when working with splat configuration files (.yaml), including: (1) creating or modifying splat.yaml files, (2) configuring segments and subsegments, (3) setting up build options, linker scripts, or paths, and (4) understanding splat configuration structure and options. Triggers on mentions of splat.yaml, splat configuration, segment setup, or when modifying decompilation project settings.

Draft and negotiate CRE financing term sheets from lender quotes. Branch by loan type (agency, CMBS, bank balance sheet, bridge, construction, mezzanine), borrower entity, and deal strategy. Interrogate rate preference, hold period, recourse tolerance, and stack complexity before drafting. Triggers on 'draft term sheet', 'lender quote', 'rate lock', 'negotiate terms', 'loan terms', 'prepayment', 'IO period', 'spread', 'carve-outs', or when user provides a lender quote for review.

NetworkSim provides provider network intelligence using real NPPES data (8.9M providers). Use this skill for ANY request involving: (1) provider search by specialty or location, (2) facility search (hospitals, nursing homes, clinics), (3) NPI validation, (4) network adequacy assessment against CMS/NCQA standards, (5) healthcare desert identification, (6) provider density analysis, (7) network roster generation, (8) hospital or physician quality metrics, (9) cross-product provider assignment, (10) pharmacy network analysis.

Use when the user says "check the UI", "verify changes", "does it look right", or after completing UI work — quick browser spot-check (not a deploy gate; that is /e2e-verify).

Python application architecture with a Functional Core and Imperative Shell, Domain-Driven Design (DDD), and type-safe data modeling. Use when designing application layers, separating pure business logic from I/O, defining domain models, implementing validation, or structuring bounded contexts.

Building REST APIs with FastAPI, Pydantic validation, and OpenAPI. Use when creating routes, handling requests, designing endpoints, implementing validation, error responses, pagination, or generating API documentation.