Debug and visualization helpers in three.js Core Helpers (AxesHelper, GridHelper, CameraHelper, light helpers, SkeletonHelper, bounding box helpers, PlaneHelper, PolarGridHelper, ArrowHelper) and Addons Helpers (VertexNormalsHelper, VertexTangentsHelper, RectAreaLightHelper, LightProbeHelper, ViewHelper, OctreeHelper, TextureHelper, PositionalAudioHelper, AnimationPathHelper, RapierHelper). Use only for development and editor overlays—not for shipping art; for gizmo-style manipulation use threejs-controls.

Classic three.js materials (non-Node): MeshStandardMaterial, MeshPhysicalMaterial, Phong/Lambert/Toon/Basic, Line/Points/Sprite materials, MeshMatcapMaterial, MeshNormalMaterial, depth/distance materials, ShaderMaterial and RawShaderMaterial. Use when tuning PBR maps, transparency, depth write, skinning flags, or writing GLSL in ShaderMaterial; for TSL/NodeMaterial/WebGPU shader graphs use threejs-node-tsl instead.

three.js math library: Vector2/3/4, Matrix3/4, Quaternion, Euler, Color, Box2/Box3, Sphere, Plane, Ray, Line3, Triangle, Frustum, Cylindrical/Spherical coords, MathUtils, and Interpolant base classes; addon math utilities such as OBB, Octree, Capsule, ConvexHull, MeshSurfaceSampler. Use for transforms, intersection tests, and spatial queries; for keyframe interpolation tied to AnimationMixer use threejs-animation; for picking implementation use threejs-objects with Raycaster.

Integrates uCharts data visualization into UniApp projects including easycom configuration, pages.json and manifest.json setup, platform-specific handling (H5, mini-program, App, nvue), and chart lifecycle management. Use when the user needs to add charts to a UniApp project, configure uCharts components, or handle cross-platform chart rendering.

Integrates uView Pro component library into UniAppX (uni-app-x) projects with TypeScript and Composition API, including easycom configuration, pages.json and manifest.json setup, and platform-specific handling. Use when the user needs to add uView Pro components to a UniAppX project, configure TypeScript .uts integration, or handle cross-platform styling.

Use when quickly generating a single OpenCLI command from a specific URL and goal description. 4-step process — open page, capture API, write TS adapter, test. For full site exploration, use opencli-explorer instead.

Strategies for translating academic papers while preserving technical accuracy

Academic translation, post-editing, and Chinglish correction guide

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.

Generate compelling social media summaries from SRT subtitle files, optimized for different platform characteristics to maximize engagement and reach.

PI 智行合一。触发：编程/开发/fleet/代码/架构/API/调试/修复/优化/bug/报错/测试/编译/compile/test/git/make/发布/验证/产品/需求/运营/增长/创意/设计/协作/团队/沟通/交互/陪伴/情感，或失败2+次/打转/言退/再试试/换个参数/算了

通过搜-读-验-交付工作流、结构化7步调试、证据驱动的代码审查和失败升级协议，引导迭代式问题解决，覆盖编程开发、产品设计和团队协作场景。适用于：处理复杂开发任务、调试持续错误（失败2+次）、执行严格代码审查，或协调需要逐步验证的多步骤项目交付。

Use when 已有经批准的设计/规格说明、多步骤实施任务，在动代码之前需要可执行任务清单时。触发场景：写实施计划、拆解开发任务、implementation plan、执行计划文档、任务拆分、按 TDD 步骤写计划。

Luamake 构建系统指南——用于当前项目的 `luamake` / `make.lua` / Ninja 生成流程。当用户需要编写、修改、排查或理解 `make.lua`、目标定义、`lm:conf`、`deps` / `objdeps`、代码生成、Lua C 模块、Bee 运行时集成，或需要解决当前项目中由 `luamake` 驱动的构建问题时，使用此 skill。即使用户没有明确提到 `luamake`，但上下文明显是在处理本项目的构建脚本、构建目录、目标依赖或 `luamake` 生成的 Ninja 流程，也应使用此 skill。不要把它用于纯通用的 C/C++ 编译知识、与本项目无关的 CMake / xmake / Bazel / Meson 问题，或仅讨论编译器理论而未涉及 `luamake` / `make.lua` 的请求。

> 通用技能

> 通用技能

Perform multi-framework deep analysis for a complex problem or decision. Use when the user wants competing options, assumption testing, adversarial reasoning, long-term tradeoffs, and an actionable recommendation rather than immediate implementation. This replaces the legacy ultra-think prompt.

PPT pipeline 逐页生成器 — 接收 slide-architect 的 Storyboard 单页规格和 decision brief 摘要，按 PageType 专属 prompt 写出 SlideSpec JSON 片段。12 个 PageType 各一份 prompt，统一嵌入 anti-ai-tone 约束。

Specialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a general data engineer — a surgical specialist for when your data is broken and the pipeline can't stop.

**版本**: 1.0

PPT pipeline 品牌声音 skill — public target `skills/ppt-brand-voice/SKILL.md`。锁定 MIRISE 品牌配色 / 字号 / 调性。Mode 1：从 master-template.css 抽取主题 tokens 注入 SlideSpec.theme。Mode 2（PR3+）：anti-AI-tone 检查。

Use twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.

Publish blog posts and articles to multiple platforms (Qiita, CSDN, Blogger, Hatena Blog, Dev.to, Medium, Zenn, Note.com) using Claude in Chrome. Given a topic or draft content, generates platform-optimized articles in the specified language and publishes them via browser automation. Supports Japanese, Chinese, and English. Use when user wants to write and publish blog posts or promotional articles.

This appears to be a transcript of a presentation on AI trends, specifically focusing on agentic workflows, visual AI, and large language models. The speaker discusses several key points, including:

- 根目录包含 `pyproject.toml` 与 `poetry.lock`，用来锁定依赖；研究数据位于 `data/<dataset>`（例如 `icews14`），每个子目录提供 `train.txt`、`valid.txt`、`test.txt` 及 `entity2id.json` 等映射文件。

This document is for AI agents (like Antigravity) working on this repository. It contains project-specific knowledge that should be prioritized.

When working with the LeanSpec documentation site:

本文档面向后续 agent-code 与开发者，提供 VSeed 子包的架构、流程与关键模块的一页式上下文。

This file defines 25 specialized AI agents for Specification Driven Development across all platforms.

Show available workers and their capabilities

> 來源：Boris Cherny (Claude Code 創作者) 的使用技巧

QA 自动化工程师，精通 Playwright/Puppeteer，擅长编写稳定、可维护的端到端测试。

You are GEO-Claw 🔍, an AI visibility optimization specialist. Your skill is loaded at:

这是一个人机协作的需求迭代工作流。人的角色从"告诉 agent 做什么"转变为"工程化条件，让好的结果通过迭代自然出现"。

> **Version:** 1.0.0 | **Organization:** Tai-Action | **Date:** 2026-03-31

7 domain-specific agents analyze CC interaction patterns in parallel.

小米大模型 MiMo TTS 2.5 语音合成。支持多种预设音色（中文/英文/默认）、风格控制（情感、方言、角色扮演、语速）、音频标签精细控制。Use when the user asks to convert text to speech, generate audio, read text aloud with a specific style/emotion/dialect, or create voice files.

Use this skill whenever working with Kingdee K3Cloud ERP system (金蝶云星空). Triggers include: querying sales orders (销售订单), purchase orders (采购订单), inventory (库存), materials (物料), customers (客户), suppliers (供应商), generating daily operational reports (经营日报), customer birthday queries (客户生日), customer category/service specialist lookups, or any ERP document operations (创建/提交/审核/反审核). Also triggers on: Kingdee API error troubleshooting, field name validation, or MCP tool usage for K3Cloud. Keywords: 金蝶, 金蝶云星空, K3Cloud, ERP, 单据, 审核, 提交, 日报, 客户查询, 库存预警.

Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance question.

Generate pytest unit, integration, and GUI tests for LoRAIro with proper fixtures, mocks, and 75%+ coverage using pytest-qt for PySide6 testing