/resume-builder

name: resume-builder
description: Builds a complete resume as Reactive Resume JSON that conforms to the schema and imports at https://rxresu.me. Asks for missing facts, then produces valid JSON with UUIDs, HTML descriptions, template and layout. Use when the user requests importable JSON, creation in Reactive Resume, or help with its schema, sections, templates or layout. Use resume-writer for a general text draft, resume-content-guide for a content audit, resume-bullet-writer for bullets and resume-tailor for one posting.

Resume Builder for Reactive Resume

Build professional resumes through conversational AI for [Reactive Resume](https://rxresu.me), a free and open-source resume builder.

Core Principles

1. **Never invent** - Only include information the user provided. Ask for missing facts; accept honest ranges and label them as estimates ("about 30%"). If asked to fabricate, decline in one sentence and offer the honest alternative in the same reply 2. **Ask questions** - When information is missing or unclear, ask before assuming 3. **Be concise** - Use clear, direct language; avoid filler words 4. **Validate output** - Ensure all generated JSON conforms to the schema

Related skills

This skill builds the document. Sibling skills do the rest; they may not be installed, and when one is missing, do the light version yourself and say so.

• **resume-writer:** a general resume as copy-ready text, including headlines and summaries. Role-specific resume skills, entry-level-resume, career-change-resume and academic-cv help choose and write the content before this skill turns it into JSON.
• **resume-content-guide:** what goes on the resume and what stays off (photo, date of birth, GPA, gaps, summaries), country and industry norms, length, and audits of an existing resume.
• **resume-bullet-writer:** digs out achievements role by role and turns duties into impact bullets.
• **resume-tailor:** fits a resume to one job posting (requirement table, gap questions, tailored copy, optional cover letter).
• **job-application-manager:** the job-search pipeline: intake, stages, follow-ups, the resume version sent, weekly reviews and messages.
• **interview-prep:** story bank, company brief, likely questions and the post-interview debrief.
• **mock-interview:** role-played practice interviews for a specific job description, with rubric scores.
• **offer-negotiation:** evaluates and negotiates job offers: decodes the terms, benchmarks pay, drafts the counter, role-plays the recruiter and writes the acceptance or decline.

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 (18 available: azurill, bronzor, chikorita, ditto, ditgar, gengar, glalie, kakuna, lapras, leafish, meowth, onyx, persian, pikachu, porygon, rhyhorn, scizor, smeargle)
• Page format: A4 or Letter
• Which sections to include and their order

Step 4: Generate Valid JSON

Output must conform to the schema of the intended Reactive Resume installation. When connected, read its `resume://_meta/schema` MCP resource; otherwise fetch `/schema.json` from that installation ([hosted schema](https://rxresu.me/schema.json)). Both are generated from the schema that the server accepts. Use [references/schema.md](references/schema.md) as an offline reference snapshot, not as proof of current compatibility; if the current schema is unavailable, label validation as pending instead of claiming the JSON is verified for import.

Key requirements:

• All item `id` fields must be valid UUIDs
• Description fields accept HTML-formatted strings (bullets as `<ul><li><p>…</p></li></ul>`, never Markdown)
• Write structured `dates` (`{ "start": "2020-01", "end": null, "present": true }`); the legacy `period` and `date` text is rewritten from them on save
• Website fields require both `url` and `label` properties
• Colors use `rgba(r, g, b, a)` format
• Fonts must be available on Google Fonts

Content Essentials

For deeper content work, hand off to resume-content-guide (what to include, country norms, audits) and resume-bullet-writer (achievement bullets). If neither is installed, apply these core rules:

• **Achievements, not duties**: start each bullet with a plain verb: past tense for completed work, present tense for ongoing duties in a current role. Say what changed or describe supported scope. Use only numbers the user gives you, or honest ranges marked as estimates; never invent one. No "I", "my" or "we".
• **Bullets per role**: 3–6 for recent roles, 1–3 for older ones.
• **Length**: 1 page for students and under ~5 years of experience; 1–2 pages for most experienced candidates; 2–3 for senior or executive roles. US federal (USAJOBS) resumes are 2 pages maximum as of 2026.
• **Order**: experienced candidates: a 2–4 line summary, then Experience, Education, Skills, then Projects or Certifications if relevant. Students and new graduates: Education first, then Projects or Experience (whichever is stronger), then Skills; skip the summary when the page is full or it only repeats the headline.
• **Personal data**: in the US, UK, Canada and