resume-cover-letter-generator
Skill0 starsChanged 6 months agoMITView on GitHub
Generate tailored resumes and cover letters as PDFs for job applications. Takes job URLs or job analyzer results and creates customized documents. Use to batch-process top job picks.
In this repository3 other files it gives its agents.
- job-analyzerSkill
- linkedin-job-searchSkill
- linkedin-jobs-fetchSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 72
Verify all PDFs created successfully
- Distinctive: line 97
Always fetch actual JD: - Never invent job requirements
- Distinctive: line 98
Reuse existing experience: - Don't fabricate skills or roles, emphasize what's relevant
- Distinctive: line 103
User's resume is source of truth: - All content tailored from provided resume, never invented
- Very specific: line 108
Use Playwright (from scraper/pdf_generator.mjs utility) for HTML → PDF conversion
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
resume-cover-letter-generator
Generates tailored resumes and cover letters for targeted job applications.
Description
Takes a list of job URLs (typically from /job-analyzer results) and automatically generates tailored resume and cover letter PDFs customized for each role. Perfect for batch-processing your top job picks.
Input Format
Users provide one of:
- Job URLs - Direct LinkedIn job URLs or list of URLs
- Job analyzer results - Copy-paste from job-analyzer output (skill auto-extracts URLs)
- Manual job list - Simple list: "TechCorp Senior PM", "Google PM", etc.
Plus:
- User's resume - Paste your current resume text or mention a file path
- Optional context - Any specific achievements or projects you want highlighted
Usage Examples
/resume-cover-letter-generator
Jobs:
- https://www.linkedin.com/jobs/view/123456/
- https://www.linkedin.com/jobs/view/234567/
- https://www.linkedin.com/jobs/view/345678/
Resume: [paste your resume here or say "use my resume at ~/path"]Or after using job-analyzer:
The top 3 picks look great. Generate tailored resumes and cover letters for:
- TechCorp (Senior Product Manager)
- Google (Product Manager)
- Microsoft (Senior PM)
My resume is at ~/Documents/resume.txtWorkflow
Phase 1: Parse Input
- Extract job URLs from user message
- Fetch full job descriptions in parallel (WebFetch)
- Extract company name, job title, key requirements, skills from each JD
Phase 2: Analyze & Generate
- For each job:
- Identify top 3-5 key requirements from JD
- Generate tailored resume (Claude) - reorder/emphasize relevant experience
- Generate tailored cover letter (Claude) - address specific role + company
- Save both as HTML files (for review before PDF if needed)
Phase 3: PDF Export
- Convert each resume HTML → PDF via Playwright
- Convert each cover letter HTML → PDF via Playwright
- Organize in
output/{CompanyName}/folders - Verify all PDFs created successfully
Phase 4: Summary
- Show list of generated documents
- Display file paths for easy access
- Offer to open folder or export summary
Output
File Structure:
output/
├── CompanyName_1/
│ ├── Resume_CompanyName_1.pdf
│ └── CoverLetter_CompanyName_1.pdf
├── CompanyName_2/
│ ├── Resume_CompanyName_2.pdf
│ └── CoverLetter_CompanyName_2.pdfResume: Tailored version highlighting role-relevant experience, reordered to match job requirements Cover Letter: Standard business format with specific company/role references and 1-2 tailored requirements
Key Rules
- Always fetch actual JD - Never invent job requirements
- Reuse existing experience - Don't fabricate skills or roles, emphasize what's relevant
- Specific over generic - Cover letters mention company name + specific requirement
- Parallel generation - Process 3-5 jobs simultaneously (~20-30s total time)
- ATS-friendly - Resume uses standard format readable by applicant tracking systems
- Idempotent - Safe to re-run; overwrites existing PDFs without duplication
- User's resume is source of truth - All content tailored from provided resume, never invented
Implementation Notes
- Reuse
job-analyzerWebFetch pattern for parallel job fetching - Use Playwright (from
scraper/pdf_generator.mjsutility) for HTML → PDF conversion - Resume template: Adapt existing
resume/resume-template.htmlwith dynamic data injection - Cover letter template: New clean HTML template with standard business letter format
- Folder creation: Auto-create
output/{company}/if doesn't exist - Error handling: If any PDF fails, report which job(s) and why; continue with others
Related Skills
job-analyzer- Use this first to find/rate jobs, then pass results here for doc generationlinkedin-jobs-fetch- Use to fetch your saved LinkedIn jobs as input
Feedback Loop
Generated docs can be:
- Reviewed before final PDF (with Claude help for edits)
- Directly submitted via LinkedIn/company career pages
- Fine-tuned for multiple rounds of applications
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.

