发现 Skills

Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.

Prepares candidates for hiring manager rounds at Staff+ (L6+) level — covering scope of impact, influencing without formal authority, navigating ambiguity, mentorship, and strategic thinking. Use when practicing HM rounds or calibrating story depth for the target level. Activate on "hiring manager round", "HM screen", "staff level", "scope of impact". NOT for coding interviews, system design, behavioral/values rounds, or resume writing.

Longitudinal memory tracking, philosophy teaching, and compassionate personal accountability. Expert in pattern recognition, Stoicism and Buddhism, and growth guidance. Activates on keywords: "accountability", "philosophy", "Stoicism", "Buddhism", "personal growth", "commitment tracking", "wisdom teaching". NOT for therapy or mental health treatment (refer to professionals), crisis intervention, or replacing professional coaching credentials.

Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running Ralph Loop.

Retrieves company financial statements, metrics, estimates, and segments via Financial Datasets API. Use when asked about revenue, earnings, margins, P/E, valuations, or financial health.

This skill provides a systematic approach for investigating and fixing bugs and issues in the codebase. Use this skill when users report bugs, unexpected behavior, test failures, or request fixes for specific issues. The skill guides through issue registration, root cause analysis, impact assessment, minimal code changes, quality validation, and E2E testing.

Generate personalized, context-aware greetings for developers at different times of day and moods

Provide inspiring coding wisdom, productivity tips, and encouragement to keep developers motivated and focused

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.

Multi-backend storage layer with automatic failover between Redis, database, and memory backends. Includes circuit breakers per backend and health-aware routing for high availability.

Format TypeORM migrations with beautifully formatted SQL code. Use this skill after generating migrations to ensure consistent SQL formatting.

Detects and corrects common anti-patterns generated by Google AI Studio and similar tools.

Control Home Assistant smart home devices using the hass-cli via uv. Use for: - Listing and inspecting entity states (lights, switches, sensors, etc.) - Turning devices on/off, toggling, setting brightness/temperature - Calling any Home Assistant service - Querying state history - Listing devices, areas, and entities - Monitoring events - Checking system health and logs Requires HASS_SERVER and HASS_TOKEN environment variables to be set.

Universal task initializer that automatically loads PAI context for all user requests. Ensures complete context availability (contacts, preferences, protocols) before responding to any task. (project, gitignored)

Debug and diagnose failed GitHub Actions workflows. Use when a workflow fails, CI/CD pipeline breaks, build errors occur, tests fail in Actions, deployment fails, or user asks about GitHub Actions logs, job failures, or workflow debugging. Supports listing runs, fetching logs, analyzing errors, and suggesting fixes.

Guidance for xUnit v3 on Microsoft.Testing.Platform in .NET repositories. Use when setting the repo test runner, choosing xUnit v3 MTP package variants, writing `dotnet test --project` or `--solution` commands, using xUnit filter switches, configuring MTP-native coverage, designing assembly fixtures, or troubleshooting zero-test and unsupported-switch failures.

**UNIVERSAL TRIGGER**: Iterative PR review + autofix loop. Use when a user wants to review, check, or fix PR changes automatically. Common patterns: - "review my PR", "check my PR", "review changes" - "fix review comments", "address review findings" - "run review loop", "autofix PR issues" - "review and fix my PR", "check PR and fix issues" **PR Review** (iterative review + fix cycle): - "review and fix my PR", "check PR and fix issues" - "iterate on PR review", "review loop" **Code Review Fix** (address existing review comments): - "fix review comments", "address PR feedback" - "fix code review issues", "resolve review findings" **Codex Review** (standalone Codex CLI review): - "codex review", "run codex on my changes" TRIGGERS: review PR, check PR, fix PR, review changes, review loop, autofix, pr review, code review fix, address review, fix comments, review findings, iterate review, codex review, run codex

Generic test generation framework supporting multiple languages and testing frameworks

Fetch latest documentation for libraries and frameworks. CRITICAL - AUTO-INVOKE when: - User wants to implement with ANY external library (GSAP, Lenis, Three.js, Framer, Radix, etc.) - User asks "how to use X", "X docs", "X API", "X reference" - Before writing ANY code that uses external packages - User mentions library names: gsap, lenis, three, framer, motion, radix, sanity, zustand MANDATORY: Never assume API knowledge. Always fetch current docs first.

Build pure, interface-agnostic services with injected dependencies for Next.js/Supabase applications.

Guide AI-assisted UI generation toward enterprise-grade, intentional design. Use when building user interfaces, creating dashboards, designing enterprise software or SaaS applications, generating frontend code with styling, or when the user asks for design help. Enforces principles inspired by Linear, Notion, Stripe, and Vercel.

Implement structured logging with appropriate levels, context, and correlation for effective debugging and monitoring

Create multi-phase project plans for Databricks data platform solutions with the Agent Domain Framework and Agent Layer Architecture. Includes an interactive Quick Start to guide key design decisions, industry-specific domain patterns, complete phase document templates (Use Cases, Agents, Frontend), Genie Space integration patterns, deployment-order requirements, and worked examples. Use when planning any Databricks solution after the Gold layer — for observability, analytics, agent-based frameworks, or multi-artifact projects.