cv-builder
Skill0 starsChanged 4 months agoMITView on GitHub
Use when the user wants to build a tech resume or CV. Generate a programmer/technical resume or CV from local projects, GitHub repositories, old resume files, or plain text. Trigger phrases: help me write a resume, generate a resume from these projects, organize GitHub projects into a resume, polish my resume, generate a technical resume PDF.
- Installs packages
5 other projects use a version of this.
Adopted by
Most recently taken up by
- talgurevich/cv-skilltheir own version, first seen Oct 15, 2026
- koralbonfil-maker/career-kittheir own version, first seen Jun 29, 2026
- marcellobarile/claude-skillstheir own version, first seen Jun 14, 2026
- berkaybuharali/cv-buildertheir own version, first seen Mar 29, 2026
- claude-office-skills/skillstheir own version, first seen Jan 30, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- claude-office-skills/skills★ 433same name
- koralbonfil-maker/career-kit★ 1same name
- marcellobarile/claude-skills★ 1same name
- berkaybuharali/cv-builder★ 0same name
- talgurevich/cv-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- cv-cloneSkill
- github-asset-managerSkill
- creating-skillsSkill
- hot-skillsSkill
- skill-translatorSkill
- init-llm-wikiSkill
- ask-for-toolsSkill
- go-goal-goSkill
- think-twiceSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Use when the user wants to:
- Distinctive: line 19
Create a new resume or CV from scratch
- Distinctive: line 21
Update or reformat an existing resume/CV
- Distinctive: line 27
Do not use for:
- Distinctive: line 37
Can do: read local projects, GitHub repos, old resume files, or plain-text notes.
- Distinctive: line 41
Default behavior: read-only on source materials.
- Distinctive: line 49
Ask the user what materials they have.
- Distinctive: line 59
Do not start generating content until the user has provided all materials.
- Distinctive: line 102
Ask the user for their preferred style through structured interactions:
- Distinctive: line 112
Ask the user about layout preferences through structured interactions:
- Very specific: line 126
Check whether a dedicated uv virtual environment exists in the skill directory and whether WeasyPrint is installed
- Very specific: line 127
If not, create the environment and run uv pip install weasyprint
- Distinctive: line 128
If automatic installation fails, output the HTML preview and provide manual installation instructions
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CV Builder
Overview
Turn scattered developer experience — local projects, GitHub repositories, old resume files, or plain-text notes — into a polished, ready-to-submit resume or CV. This skill acts as a technical recruiter: read source materials in parallel, ask targeted follow-up questions, draft content in Markdown, and render it to HTML/PDF via customizable templates.
When to Use
Use when the user wants to:
- Create a new resume or CV from scratch
- Turn GitHub projects or local codebases into resume bullet points
- Update or reformat an existing resume/CV
- Generate a PDF resume with a specific visual style
- Tailor a resume for a specific role or industry
When Not to Use
Do not use for:
- Writing cover letters or application emails
- Submitting resumes to job boards or company portals
- Verifying the truthfulness of work history or project claims
- Guaranteeing ATS compatibility or interview responses
- Non-technical resumes unless the user explicitly provides all content
Boundaries and Defaults
Can do: read local projects, GitHub repos, old resume files, or plain-text notes; dispatch sub-agents to read materials in parallel; ask targeted follow-up questions; draft a Markdown resume; render to HTML/PDF via built-in (modern/classic/minimal) or custom templates.
Cannot do (without explicit user approval): fabricate experience, projects, or metrics not in the source materials; submit resumes to job boards or company portals; modify any source files outside the skill's output directory.
Default behavior: read-only on source materials; all writes go to the user's chosen output directory and require approval; the user confirms every personal claim (employment dates, project metrics, technologies used) before it enters the draft.
Core Workflow
Execute the following steps in order. During interactive phases where the user must make choices, use the structured question/interaction capabilities provided by the current Agent (e.g., multiple choice, single choice, confirmation boxes) instead of dumping large blocks of text questions into the chat.
Step 1: Collect Input Sources
Ask the user what materials they have. Any combination is supported:
| Source | Handling |
| Local project folder | Read README, package.json, pyproject.toml, and source-code summaries |
| GitHub repository URL | Fetch repository metadata and README |
| Existing resume file (PDF/DOCX/MD) | Extract text; on macOS, use textutil -convert txt for DOCX |
| Plain text or notes | Accept as-is |
| LinkedIn / Notion / portfolio URL | Scrape if possible; otherwise ask the user to export |
Do not start generating content until the user has provided all materials.
Step 2: Dispatch Sub Agents to Read Materials
The main agent decides the dispatch strategy based on project size:
- Large projects (many files, complex code): assign a dedicated sub agent
- Small projects or simple files: combine into one sub agent
- Old resume / text notes: one sub agent
Each sub agent returns a concise summary including:
- Project/file purpose
- Key technologies used
- Notable features or achievements
- Quantifiable impact (if any)
- Suggested resume bullet points
Step 3: Ask for Personal Information
Confirm or collect the following through structured interactions, grouped by topic:
- Basic info: name, email, phone, location, LinkedIn, GitHub
- Career goal: target role, industry, city
- Experience and skills: education, work experience, projects, tech stack
- Bonus items: certifications, languages, awards, open-source contributions
- Photo (optional): whether to provide an ID photo and place it in the top-right corner of the resume
Pre-fill answers using the source summaries and let the user edit or add details.
Step 4: Draft the Markdown Resume
Generate a Markdown resume that:
- Has a clear, ATS-friendly structure
- Includes keywords for the target role
- Uses concise bullet points (preferably STAR method)
- Matches skills to the target role
Show the draft to the user and ask them to edit it. Repeat until the user approves the content.
Step 5: Choose a Template
Ask the user for their preferred style through structured interactions:
- Built-in templates: modern (modern single-column), classic (classic two-column), minimal (minimal)
- User-provided template: accept an HTML/CSS file path
- Agent-designed: user describes the style, and the agent generates HTML/CSS
Render an HTML preview and show it to the user.
Step 6: Confirm Page Layout
Ask the user about layout preferences through structured interactions:
- Page count: squeeze to one page or allow multiple pages?
- Photo: provide an ID photo and place it in the top-right corner?
- Other adjustments: font size, line spacing, margins, etc.?
Modify the HTML/CSS and re-render the preview based on the user's choices. If the user chooses one page, use build_resume.py --one-page to generate a compact layout.
Step 7: Generate the PDF
Convert the HTML preview to PDF using WeasyPrint.
Dependency handling:
- Check whether a dedicated
uvvirtual environment exists in the skill directory and whether WeasyPrint is installed - If not, create the environment and run
uv pip install weasyprint - If automatic installation fails, output the HTML preview and provide manual installation instructions
Iterate with the user on layout, content, and template until satisfied.
Resources
scripts/build_resume.py— main entry point (supports--one-pagecompact layout)scripts/render_pdf.py— HTML to PDF (WeasyPrint, auto-injects Hiragino Sans GB font on macOS)scripts/ensure_weasyprint.py— manages theuvenvironmentscripts/read_project.py— scans key files in local projectsassets/templates/— built-in HTML/CSS templatesreferences/example-resume.md— example Markdown resume format
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

