Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Project-specific PR-review rules for the tuist/tuist Elixir codebases (server, cache, processor, xcode_processor, tuist_common, noora). Focuses on the things only this repo knows — authorization invariants, tenancy, write-only ClickHouse, Mimic placement, migration timestamptz, data-export updates, marketing changelog entries, and i18n.
Project-specific pull request review rules for the tuist/tuist Swift codebases. Focuses on the things only this repo knows, including preferring value types, the testing framework choice, and migration of XCTest to Swift Testing.
Methodically run the RivetKit driver test suite file by file across the native (NAPI) and wasm runtimes, tracking progress in ~/.agents/notes/driver-test-progress.md. Use when you need to validate the driver test suite after changes, bring up a new driver, or debug test failures systematically.
Run an E2E smoke test that installs rivetkit packages from npm in an isolated temp project, starts the hello-world counter actor, then verifies both HTTP actions and WebSocket actions + events work end-to-end. Use when the user asks to sanity check, smoke test, or verify a rivetkit release/preview-publish works.
对网文项目做只读体检/诊断（/webnovel-doctor）——检查目录、文件、JSON、SQLite、RAG 配置、依赖与 Dashboard 构建产物是否完整。
给单篇稿子打 rubric 分。**只在控制台输出，不写文件，不预测**。触发词："打分这篇 [path]"/"score this [path]"/"给这稿子打分"/"先打分看看"。是 cheat-predict 之前的轻量探索动作。
Optimize Daft UDF performance. Invoke when user needs GPU inference, encounters slow UDFs, or asks about async/batch processing.
Run Farm verification with build-first constraints. For verify/acceptance, use npm run build only for core, rust plugins, and affected examples; do not run cargo check/clippy. Use when validating changes before merge or push.