发现 Skills

Check the diff against master and remove all AI generated slop introduced in this branch. This includes extra comments, defensive checks, type casts, and inconsistent code style.

Use when executing dbt commands via the CLI—running models, tests, builds, compiles, or show queries. Use this Skill when you're unsure which dbt executable to use or how to format command parameters.

Secrets-detection expert. Use to create detection rules for API keys, tokens, and credentials in code.

Visual shader effects—glow/bloom, chromatic aberration, distortion, vignette, film grain, scanlines, glitch, dissolve, outline, and Fresnel. Use when adding visual polish, post-processing effects, or stylized rendering to shaders.

Control the Unreal Engine 5 editor via HTTP commands. Spawn, delete, and transform actors; manage blueprints, materials, and animation blueprints; and inspect or modify any UObject property using reflection. Use this when a user asks to create, modify, or query anything in the UE5 editor or mentions UE5, Unreal, actors, blueprints, levels, materials, animation, input, or characters.

Vue.js and TypeScript best practices for building performant applications with Vite, Pinia, VueUse, and Tailwind CSS.

Expert guidance for fetching and parsing web content from URLs, handling various content sizes, JavaScript-rendered sites, and working around tool limitations. Use this when fetching articles, documentation, social media posts, or any web content for translation, analysis, or archiving.

Comprehensive Word document processing with full-format support. Handles creation, editing, formatting preservation, tracked changes, and metadata management.

Guidelines for preparing changelog entries for nextest releases following the Keep a Changelog format

Downloads files, images, or media from URLs using curl, wget, or Python scripts. Can handle single downloads and bulk operations from URL lists and save them to a specified directory.

Substack / Medium–style premium longform layout, suitable for WeChat Official Accounts, blogs and newsletters

GitHub-dark theme + JetBrains Mono monospaced font with terminal-style code blocks; includes agenda and Q&A

Build llm-mux binary and run locally for development/debugging

Expert Java development skill covering Spring Boot, Jakarta EE, and plain Java across versions Java 8 through Java 21+. Use when asked to write, generate, review, architect, or improve Java code. Handles: creating REST APIs, designing domain models, generating boilerplate (entities, repositories, services, controllers), code review for correctness/scalability/security, performance optimization, JVM tuning guidance, concurrency patterns, and applying architecture patterns (layered, hexagonal, DDD). Triggers on any Java programming request.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This ...

Create an empty 1C external processing (scaffold XML sources)

Work with Gemini File API for document caching and efficient multi-query workflows. Use when discussing file uploads, caching strategies, token optimization, or comparing File API vs inline document approaches.

Structured debugging methodology with an error taxonomy, assumption tracking, and root-cause analysis. Primary consumer: Codex CLI (bug investigation), also Claude.

Evidence-based completion verification checklist. Used by all agents before marking work done.

Manage OpenClaw updates and version migrations.

Optimize Deepgram costs and usage for budget-conscious deployments. Use when reducing transcription costs, implementing usage controls, or optimizing pricing tier utilization. Trigger with phrases like "deepgram cost", "reduce deepgram spending", "deepgram pricing", "deepgram budget", "optimize deepgram usage".

Implement PostHog rate limiting, backoff, and idempotency patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for PostHog. Trigger with phrases like "posthog rate limit", "posthog throttling", "posthog 429", "posthog retry", "posthog backoff".

Optimize Vercel API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Vercel integrations. Trigger with phrases like "vercel performance", "optimize vercel", "vercel latency", "vercel caching", "vercel slow", "vercel batch".

Execute analyze, plan, and execute Vercel SDK upgrades with breaking change detection. Use when upgrading Vercel SDK versions, detecting deprecations, or migrating to new API versions. Trigger with phrases like "upgrade vercel", "vercel migration", "vercel breaking changes", "update vercel SDK", "analyze vercel version".