- 📄 SKILL.md
markdown-customizations
Use this skill when creating or editing GitHub Copilot customization Markdown files (agent profiles, prompt files, instruction files, and skills).
免费获取 · 一键下载即用
Use this skill when creating or editing GitHub Copilot customization Markdown files (agent profiles, prompt files, instruction files, and skills).
Focus code review effort on the 20% of code that causes 80% of issues. Prioritizes data access, security, concurrency, and integration boundaries over formatting and style. Uses blast radius scoring to determine review depth. Includes checkpoint schedules, critical path identification, and a batch review checklist. Load this skill when reviewing code, PRs, or architecture, or when the user mentions "review", "code review", "PR review", "what should I review", "review priorities", "blast radius", or "critical path". --- # 80/20 Review ## Core Principles 1. **Review at checkpoints, not continuously** — Constant review interrupts flow. Schedule reviews at natural breakpoints: post-implementation, pre-PR, post-integration, and post-deploy. Each checkpoint has a different focus. 2. **Focus on data access, security, concurrency, integration** — These are the 20% of code areas that cause 80% of production incidents. A missing `CancellationToken` is more dangerous than a misnamed variable. Review depth should match risk. 3. **Blast radius determines depth** — A utility function used in one place gets a glance. A middleware change that affects every request gets a thorough review. Score changes by blast radius and invest review time proportionally. 4. **Automate the trivial** — Formatting, import ordering, naming conventions, and basic anti-patterns should be caught by tools (formatters, analyzers, hooks), not humans. Save human attention for things tools can't catch: logic errors, design flaws, and missing edge cases. ## Patterns ### Checkpoint Schedule Review at these natural breakpoints, each with a specific focus: ```
Perform non-destructive cross-artifact consistency and quality analysis across spec, plan, and tasks
Collection of agent skills for Helios video engine. Use when working with programmatic video creation, browser-native animations, or Helios compositions. Install individual skills by path for specific capabilities.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Creates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs. Use when scaffolding new custom agents, configuring agent workflows, or setting up agent-to-agent handoffs.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Context window coach. Proactive guidance for token-efficient Claude Code projects, multi-agent systems, and skill architecture.
Evaluate whether an open source project / company is investable by a USD-denominated VC fund in the current AI cycle.
Configure your Flutter app to support assistive technologies like Screen Readers
Web accessibility patterns, WCAG compliance, and inclusive design. Use when implementing accessible UI, keyboard navigation, screen reader support, focus management, semantic HTML, or auditing for compliance. Triggers: accessibility, a11y, WCAG, ARIA, screen reader, keyboard navigation, focus, tab order, tabindex, alt text, color contrast, semantic HTML, landmark, role, aria-label, aria-labelledby, aria-describedby, aria-live, aria-expanded, aria-selected, aria-hidden, focus trap, roving tabindex, skip link, assistive technology.
Manage BibTeX citations including DOI-to-BibTeX conversion, metadata extraction, validation, and deduplication. Use when building reference lists, converting DOIs to citations, or validating existing .bib files.
skill-sample/ ├─ SKILL.md ⭐ 必备:技能说明入口:用途 / 安装 / 用法 / 示例 / 依赖 ├─ manifest.sample.json ⭐ 推荐:机器可读元信息:用于索引 / 校验 / 自动填表 ├─ LICENSE.sample ⭐ 推荐:授权与使用范围:开源 / 限制 / 商用说明 ├─ scripts/ │ └─ example-run.py ✅ 可运行示例脚本:让用户导入后立刻验证“能用” ├─ assets/ │ ├─ example-formatting-guide.md 🧩 输出规范:统一排版 / 结构 / 风格 │ └─ example-template.tex 🧩 模板资源:报告/文档模板,快速生成标准产物 └─ references/ 🧩 参考资料库:方法论 / 结构指南 / 最佳实践 ├─ example-ref-structure.md 🧩 结构参考:章节框架 / 目录组织 ├─ example-ref-analysis.md 🧩 分析参考:常用套路 / 指标口径 └─ example-ref-visuals.md 🧩 视觉参考:图表规范 / 可视化建议
更多 Agent Skills 规范 详见Anthropic官方文档:https://agentskills.io/home
├─ ⭐ 必备:YAML Frontmatter(必须存在,放在文件最顶部) │ ├─ ⭐ name :技能唯一名;须符合命名规则,并建议与目录名一致 │ └─ ⭐ description :技能描述;建议包含触发关键词(便于检索/匹配) │ ├─ ✅ 可选:Frontmatter 扩展字段(规范允许,但非强制) │ ├─ ✅ license :许可证标识(也可配合单独 LICENSE 文件) │ ├─ ✅ compatibility :兼容性/运行环境要求(仅在确实有限制时写) │ ├─ ✅ metadata :任意键值对(如 author/version/source_url 等) │ └─ 🧩 allowed-tools :允许工具白名单(规范标注为 experimental) │ └─ ✅ 推荐:Markdown 正文(自由格式,但建议按“渐进式披露”组织) ├─ ✅ Overview / Purpose :一句话说明目标 + 不做什么(边界) ├─ ✅ When to use :触发条件/适用场景(让模型/用户知道何时调用) ├─ ✅ Step-by-step :步骤化流程(最好 3–6 步,保证可复现) ├─ ✅ Inputs / Outputs :输入格式、输出格式、产物位置(文件/文本/JSON等) ├─ ✅ Examples :至少 1 个可复制示例(越“能跑”越好) ├─ 🧩 Files & References :引用assets/、references/、scripts/(相对路径) ├─ 🧩 Edge cases :边界情况/限制(大文件、速率限制、失败回退) ├─ 🧩 Troubleshooting :常见错误与解决(依赖缺失、路径不对、权限问题) └─ 🧩 Safety notes :涉及联网/写文件/执行命令时给出提醒(建议写)
在 GitHub 和各类社区里,技能文件分散、难检索、也难判断是否可靠。SkillWink 把开源技能集中整理成可搜索、可筛选、可直接下载使用的技能库,让你更快找到“正好能用”的那一个。并且支持在SkillWink上直接上传skills。
我们提供 AI 语义搜索 + 关键字检索,支持 版本更新与多维排序(下载/点赞/评论/更新),并为每个技能提供 SKILL.md 开放标准与来源信息。你还可以在详情页直接 评论讨论、交流用法与改进建议。
快速上手:
支持下载与导入 skills(.zip/.skill),本地放置后即可生效:
~/.claude/skills/(Claude Code)
~/.codex/skills/(Codex CLI)
~/.gemini/skills/(Gemini CLI)
同一份 SKILL.md 跨平台通用。
你需要了解的:技能是什么、怎么运行的、怎么找、怎么导入、怎么判断可信、怎么参与共建。
这里的“skills(技能)”是一种可复用的任务能力包,通常包含 SKILL.md 说明(用途、输入输出、使用方法)以及可选的脚本/模板/示例文件。
你可以把它理解为:给 AI 助手或工具链用的“插件说明书 + 资源包”,可被反复安装与分享。
技能系统采用“渐进式披露”策略,高效管理上下文信息,具体流程如下:
发现阶段:系统启动时,智能体仅加载各技能的名称与简要描述——信息精简,足以判断其适用场景,避免冗余加载。
激活阶段:当任务需求与某技能描述匹配时,智能体才将对应的完整 SKILL.md 说明文档动态载入上下文。
执行阶段:智能体严格遵循文档指引执行操作,并按需调用关联文件或运行内置代码模块。
核心优势:该设计使智能体始终保持轻量高效,同时具备“按需扩展上下文”的能力,既保障响应速度,又确保复杂任务拥有充分执行依据。
推荐 3 种方式组合使用:
注:以上导入方式文件大小控制在10M之内。
常见路径如下(不同系统略有差异,以你本机为准):
同一份 SKILL.md 通常可以跨工具复用。你在 SkillWink 导入后,也可以查看“放置指引/安装说明”。
可以。很多技能本质是标准化说明 + 资源,只要目标工具支持读取该格式,就能共享使用。
比如:检索类技能 + 写作类技能 + 自动化脚本,形成“发现 → 处理 → 输出”的工作流。
一部分skills来源于公开的 GitHub 仓库。我们会筛掉低质量仓库(至少 2 星),并扫描基本质量指标,还有一部分是SkillWink平台的创作者独立上传的。作为使用者,在安装前应始终审查代码,对安全问题负责。
最常见原因是这几类:
我们会尽量避免。你可以用 排序 + 评论 让“好用的”更靠前: