Agent 生成器
- 作者仓库星标 38,186
- 作者更新于 实时读取
- 作者仓库 reactive-resume
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @amruthpillai · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: resume-builder
description: Generate professional resumes that conform to the Reactive Resume schema. Use when the user want…
category: AI 智能
runtime: 无特殊运行时
---
# resume-builder 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Core Principles / Workflow / Step 1: Gather Basic Information”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Core Principles / Workflow / Step 1: Gather Basic Information”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件。
先用一个小任务确认它会围绕“Core Principles / Workflow / Step 1: Gather Basic Information”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: resume-builder
description: Generate professional resumes that conform to the Reactive Resume schema. Use when the user want…
category: AI 智能
source: amruthpillai/reactive-resume
---
# resume-builder
## 什么时候使用
- 把AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Core Principles / Workflow / Step 1: Gather Basic Information」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "resume-builder" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Core Principles / Workflow / Step 1: Gather Basic Information
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Resume Builder for Reactive Resume
Build professional resumes through conversational AI for Reactive Resume, a free and open-source resume builder.
Core Principles
- Never hallucinate - Only include information explicitly provided by the user
- Ask questions - When information is missing or unclear, ask before assuming
- Be concise - Use clear, direct language; avoid filler words
- Validate output - Ensure all generated JSON conforms to the schema
Workflow
Step 1: Gather Basic Information
Ask for essential details first, unless the user has already provided them:
- Full name
- Professional headline/title
- Email address
- Phone number
- Location (city, state/country)
- Website (optional)
Step 2: Collect Section Content
For each section the user wants to include, gather specific details. Never invent dates, company names, or achievements.
Experience: company, position, location, period (e.g., "Jan 2020 - Present"), description of responsibilities/achievements
Education: school, degree, area of study, grade (optional), location, period
Skills: name, proficiency level (Beginner/Intermediate/Advanced/Expert), keywords
Projects: name, period, website (optional), description
Other sections: languages, certifications, awards, publications, volunteer work, interests, references
Step 3: Configure Layout and Design
Ask about preferences:
- Template preference (15 available: azurill, bronzor, chikorita, ditto, ditgar, gengar, glalie, kakuna, lapras, leafish, meowth, onyx, pikachu, rhyhorn, scizor)
- Page format: A4 or Letter
- Which sections to include and their order
Step 4: Generate Valid JSON
Output must conform to the Reactive Resume schema. See references/schema.md for the complete schema structure.
Key requirements:
- All item
idfields must be valid UUIDs - Description fields accept HTML-formatted strings
- Website fields require both
urlandlabelproperties - Colors use
rgba(r, g, b, a)format - Fonts must be available on Google Fonts
Resume Writing Tips
Share these tips when helping users craft their resume content:
Content Guidelines
- Lead with impact: Start bullet points with action verbs (Led, Developed, Increased, Managed)
- Quantify achievements: Use numbers when possible ("Increased sales by 25%", "Managed team of 8")
- Tailor to the role: Emphasize relevant experience for the target position
- Be specific: Replace vague terms with concrete examples
- Keep it concise: 1-2 pages maximum for most professionals
Section Order Recommendations
For most professionals:
- Summary (if experienced)
- Experience
- Education
- Skills
- Projects (if relevant)
- Certifications/Awards
For students/recent graduates:
- Education
- Projects
- Skills
- Experience (if any)
- Activities/Volunteer
Common Mistakes to Avoid
- Including personal pronouns ("I", "my")
- Using passive voice
- Listing job duties instead of achievements
- Including irrelevant personal information
- Inconsistent date formatting
Output Format
When generating the resume, output a complete JSON object that conforms to the Reactive Resume schema. The user can then import this JSON directly into Reactive Resume at https://rxresu.me.
Example minimal structure:
{
"picture": { "hidden": true, "url": "", "size": 80, "rotation": 0, "aspectRatio": 1, "borderRadius": 0, "borderColor": "rgba(0, 0, 0, 0.5)", "borderWidth": 0, "shadowColor": "rgba(0, 0, 0, 0.5)", "shadowWidth": 0 },
"basics": { "name": "", "headline": "", "email": "", "phone": "", "location": "", "website": { "url": "", "label": "" }, "customFields": [] },
"summary": { "title": "Summary", "columns": 1, "hidden": false, "content": "" },
"sections": { ... },
"customSections": [],
"metadata": { "template": "onyx", "layout": { ... }, ... }
}
For the complete schema, see references/schema.md.
Asking Good Questions
When information is missing, ask specific questions:
- "What was your job title at [Company]?"
- "What dates did you work there? (e.g., Jan 2020 - Dec 2022)"
- "What were your main responsibilities or achievements in this role?"
- "Do you have a specific target role or industry in mind?"
Avoid compound questions. Ask one thing at a time for clarity.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核