Skill | Added | Review |
|---|---|---|
webapp-testing .agent/skills/webapp-testing/SKILL.md Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. | 91 91 2.17x Agent success vs baseline Impact 100% 2.17xAverage score across 7 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
vrm-springbone-physics .agent/skills/vrm-physics/SKILL.md Debugging and fixing VRM SpringBone physics issues in three-vrm, including hair/clothing physics that flies upward, sticks out horizontally, or behaves unnaturally. | 63 63 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
vrm-mtoon-outline .agent/skills/vrm-mtoon-outline/SKILL.md Adjusting VRM MToon material outline thickness in three-vrm. Covers outline width modes, property access, and how to fix outlines that appear too thick when models are scaled. | 58 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
Vanilla JS UI Race Conditions (VRM vs Live2D) .agent/skills/vanilla-js-ui-race-conditions/SKILL.md Dealing with delayed DOM generation, lazy loading, and optimistic state synchronization in vanilla JavaScript without a reactive framework. | — | |
🎨 UI 设计规范 .agent/skills/ui-system-refactor/SKILL.md Project N.E.K.O. 胶囊化 UI、品牌蓝视觉系统规范 | — | |
tts-error-reporting .agent/skills/tts-error-reporting/SKILL.md Convention for reporting errors from multiprocessing TTS workers to the main process frontend. Use this skill when modifying, adding, or debugging TTS workers in tts_client.py to ensure connection errors, quotas, and API limits correctly display Toast notifications to the user rather than failing silently. | 76 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
ssr-hydration-scraping .agent/skills/ssr-hydration-scraping/SKILL.md Best practices for extracting data from modern React/Vue SSR pages (like Next.js or Nuxt.js) by targeting hydration state blocks (__NEXT_DATA__, __NUXT__) using regex and `jmespath`, avoiding brittle DOM selector scraping. | 69 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: c6f1797 | |
pytest-asyncio-httpx-mocking .agent/skills/pytest-asyncio-httpx-mocking/SKILL.md When masking httpx.AsyncClient with unittest.mock in Pytest, AsyncMock must be used instead of MagicMock for async methods like post/get to prevent TypeError when awaited. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
push-to-pr .agent/skills/push-to-pr/SKILL.md Push commits to an existing GitHub PR's source branch. NEVER create new branches. Use when the user says "push to PR | 80 80 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
📝 任务完成后归档 .agent/skills/post-work-analysis/SKILL.md **重要提醒**: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。 | — | |
pdf .agent/skills/pdf/SKILL.md Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. | 96 96 2.48x Agent success vs baseline Impact 97% 2.48xAverage score across 10 eval scenarios Securityby High Do not use without reviewing Reviewed: Version: c6f1797 | |
neko-plugin .agent/skills/neko-plugin/SKILL.md Work on N.E.K.O plugins end to end. Use when the user asks to create, modify, review, run, debug, inspect, document, validate, package, or reason about N.E.K.O plugins, plugin.toml, plugin SDK usage, plugin UI surfaces, plugin CLI tooling, plugin runtime behavior, or plugin system contracts. | 80 80 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
mcp-builder .agent/skills/mcp-builder/SKILL.md Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | 91 91 2.21x Agent success vs baseline Impact 93% 2.21xAverage score across 10 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: c6f1797 | |
gemini-openai-api .agent/skills/gemini-openai-api/SKILL.md Gemini 模型通过 OpenAI 兼容 API 接入指南。包含:(1) 辅助 API 配置(summary/correction/emotion/vision),(2) extra_body 格式用于控制 thinking,(3) 响应格式处理(markdown 代码块)。当需要将 Gemini 作为辅助模型接入、配置 thinking 参数、或处理 Gemini API 返回格式时使用。 | 74 74 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
ammo-mmd-physics-hacks .agent/skills/ammo-mmd-physics-hacks/SKILL.md 应对 WebGL 端 MMD 物理 (Ammo.js) 炸模、穿模、卡顿等极限边缘工况的终极调优指南与 Hack 技巧。 | 52 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 | |
3d-camera-interaction .agent/skills/3d-interaction/SKILL.md Three.js 中处理 3D 模型拖拽、缩放、边界检测的正确方法。解决鼠标移动与模型移动不同步、缩放后只能看到模型一部分等问题。 | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: c6f1797 |