发现 Skills

Structured script for B2B interviews — separation of buyer and end-user, pain-discovery without leading questions

Pre-commit code quality review for Unity C# code. Checks against Rules, CODING_STANDARDS.md, NAMING_CONVENTIONS.md, and GDD Gherkin test coverage. Use when code has been written and tests are passing but before committing. Runs automatically at Step 8.5 of /uw-cmd-implement-feature. Triggers on "review this code", "check my implementation", "pre-commit review", "code review", "check before commit", "is this ready to commit", "review my changes", or any request to validate code quality before committing.

Auto-fix issues found by code review in REVIEW.md. Spawns a fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

Manage specification files for spec-driven development. Use when creating, updating, or deleting spec files. Supports feat, fix, docs, refactor, and chore scopes.

OTA firmware upload, listing, deletion, and over-the-air update for the Universal ESP32 Workbench. Triggers on "OTA", "firmware", "update", "upload", "binary", "over-the-air".

Resume work from previous session with full context restoration

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).

Validate JSON data against JSON Schema specifications. Use for API validation, config file validation, or data quality checks.

Create photo collages with grid layouts, custom arrangements, borders, and backgrounds. Combine multiple images into single compositions.

Generate professional PDF and HTML reports with charts, tables, and narrative from data. Supports templates, branding, and automated report generation.

Manage Google Play Developer Console using the gpd CLI. Use when working with Android app publishing, Play Store releases, app reviews, Android vitals, in-app purchases, subscriptions, or when the user mentions Google Play, Play Store, Android publishing, or gpd.

Use when executing implementation plans with independent tasks in the current session — dispatches a fresh subagent for each task with automatic code review gates between tasks, enabling fast iteration with quality controls.

Configure Claude Code sandbox network isolation with trusted domains, custom access policies, and environment variables

Verify documentation and procedures with Doc Detective test specifications. MANDATORY: Read SKILL.md first. Format: {"goTo":"url"} {"find":"text"} {"click":"text"} - action IS the key. NEVER {"action":"goTo"}. Keywords: test spec, Doc Detective, test JSON, test documentation, test docs, test procedure, verify procedures.

Use when debugging and troubleshooting dojo.js applications. Triggers: dojo error, torii connection, entity not found, type mismatch, debug dojo, troubleshoot, subscription error, sync issues

Lightweight PRD (Product Requirements Document) writing guide for startups. Provides structured templates covering problem definition, hypothesis, success metrics, scope, and edge cases. Designed to be lean enough for fast iteration while comprehensive enough to align engineering and design teams.

Connect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.

Principles for writing test code. Differentiate unit tests and integration tests, avoid anti-patterns, and follow Python/pytest patterns. Use when writing test code, reviewing test quality, or distinguishing unit vs. integration tests, or when the user mentions "writing tests", "unit tests", "integration tests", "pytest", or "test review". Not for E2E/browser testing (use the Playwright skill instead).

Use when building SwiftUI views, managing state with @Observable, implementing NavigationStack or NavigationSplitView navigation patterns, composing view hierarchies, presenting sheets, wiring TabView, applying SwiftUI best practices, or structuring an MV-pattern app. Covers view architecture, state management, navigation, view composition, layout, List, Form, Grid, theming, environment, deep links, async loading, and performance.

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).

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Diagnose your taste gaps across six skill areas. Know what to practice. Use when starting a taste development program, checking progress, or identifying specific areas to improve.

Guidance for using the Legacy Survey DR10 data (images and catalogs) through viewer URL APIs and release file structure, with local cache refresh workflows, maskbits interpretation, and known-issues checks. Use when tasks involve cutouts, tractor/sweep catalogs, bricks, or quality masking for Legacy Survey data products.