发现 Skills

Create distinctive, usability-focused, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include web apps, landing pages, dashboards, forms, portfolios). Generates creative, polished code that avoids generic AI aesthetics. Applies "Don't Make Me Think" usability principles and a default style guide (Black/White/Gray/Bright Green) when no style preference is provided.

This skill should be used when the user wants to prepare for behavioral interviews, generate a behavioral answer bank, or practice STAR-format answers mapped to their real experiences. Trigger phrases include "prep behavioral", "behavioral interview prep", "prep me for interview at", "practice behavioral questions", "generate behavioral answers", "behavioral prep for", "interview stories for", "STAR method answers", "prep my stories", "answer bank for interview", or when a user has completed a resume-builder run and asks for interview preparation. It chains off resume-builder output (notes.md, resume.tex, candidate-context.md) to produce a tailored question-and-answer bank. If no resume-builder output exists, guide the user to run resume-builder first.

Agent-First Development methodology for building software where AI agents are first-class users. Covers command design, CLI validation, MCP servers, CommandResult schemas, testing strategies, and the core AFD philosophy. Use when: building agent-ready apps, designing commands, integrating MCP, understanding AFD patterns, or following the command-first workflow. Triggers: agent-first, AFD, command-first, MCP server, CommandResult, CLI validation, afd call, honesty check, define-validate-surface.

Addresses PR review comments for Sprout Rails project. Fetches PR comments via gh CLI, systematically addresses each comment, runs rubocop on changed files, and runs relevant tests to ensure nothing broke. Use this when the user asks to address PR feedback or review comments.

Use when invalid data causes failures deep in execution and validation is needed at multiple system layers — validate at every layer data passes through to make such bugs structurally impossible.

Generates structured scaffolds (frameworks, checklists, templates) for technical work — TDD test suites, exploratory data analysis plans, statistical analysis designs, causal vs predictive modeling objectives, and validation checklists. Use when starting technical work that needs systematic planning before execution. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", "design an A/B test", or when technical work needs scaffolding before execution.

Use when developing embedded/no_std Rust. Keywords: embedded, no_std, microcontroller, MCU, ARM, RISC-V, bare metal, firmware, HAL, PAC, RTIC, embassy, interrupt, DMA, peripheral, GPIO, SPI, I2C, UART, embedded-hal, cortex-m, esp32, stm32, nrf, 嵌入式, 单片机, 固件, 裸机

Build browser automation and web scraping with Playwright on your local machine. Prevents 10 documented errors including CI timeout hangs, extension testing failures, and Ubuntu compatibility issues. Includes stealth mode for anti-bot bypass, authenticated sessions, infinite scroll handling, screenshot/PDF generation, and v1.57 Speedboard performance analysis. Use when: automating browsers, scraping protected sites, testing with real IPs, bypassing bot detection, generating screenshots/PDFs, or troubleshooting "target closed", "page.pause() hangs CI", "permission prompts block tests", or "Ubuntu 25.10 installation" errors.

Titanium SDK native feature integration guide. Use when implementing, reviewing, analyzing, or examining Titanium location services, maps (Google Maps v2, Map Kit), push notifications (APNs, FCM), camera/gallery, media APIs, SQLite databases, HTTPClient networking, WKWebView, Android Intents, background services, iOS Keychain/iCloud, WatchKit/Siri integration, or CI/CD with Fastlane and Appium.

Stop all Canvai development servers and free their ports

USE WHEN: the user needs diagrams, flowcharts, ERDs, sequence diagrams, state machines, architecture visualizations, or uses phrases like "visualize", "diagram", "chart", or "show me". DO NOT USE WHEN: ASCII art is sufficient, the user wants code instead of diagrams, or a simple text description is more appropriate.

AdSpaceSDK (AdMob Next-Gen wrapper) integration for Android. Covers all ad types (Banner, Native, Interstitial, Rewarded, Rewarded Interstitial, App Open), CMP consent (UMP/GDPR), Firebase Remote Config, and resume-ads. Supports both View API (XML/Kotlin) and Jetpack Compose. Minimum SDK 26, Java 21.

This skill guides writing Ansible playbooks for server configuration. Use when hardening servers, installing packages, or automating post-provisioning tasks that cloud-init cannot handle.

Insert a new row into a specified Notion database using natural-language property values. Handles property name matching and validation.

Deliver robust API Platform contracts in Symfony with explicit operations, mapping, and policy-safe behavior. Use for api platform state providers tasks.

DEPRECATED - Use the chatkit-backend skill instead. Chat API functionality is now part of the chatkit-backend skill.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Comprehensive AWS cloud services skill covering S3, Lambda, DynamoDB, EC2, RDS, IAM, CloudFormation, and enterprise cloud architecture patterns with AWS SDK

Complete guide for dbt data transformation including models, tests, documentation, incremental builds, macros, packages, and production workflows

Comprehensive guide for building GraphQL APIs including schema design, queries, mutations, subscriptions, resolvers, type system, error handling, authentication, authorization, caching strategies, and production best practices

Comprehensive observability and monitoring skill covering Prometheus, Grafana, metrics collection, alerting, exporters, PromQL, and production monitoring patterns for distributed systems and cloud-native applications

Performance benchmarking expertise for shell tools, covering benchmark design, statistical analysis (min/max/mean/median/stddev), performance targets (<100ms, >90% hit rate), workspace generation, and comprehensive reporting

Comprehensive Svelte development skill covering reactivity runes, components, stores, lifecycle, transitions, and modern Svelte 5 patterns

Alex Hormozi's framework for creating irresistible high-value 'Grand Slam' offers.