Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Ensure ATS-friendly formatting and create clean, scannable layouts. Use when the user mentions resume format, layout, template, design, or fixing formatting issues.
.claude/skills/bilal140202-resume-formatter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 152% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 113% | 0% |
Use this skill when the user:
Your resume must work for:
The Solution: Clean, simple formatting that satisfies both.
Safe, ATS-Friendly Fonts:
Font Sizes:
1. Contact Information
2. Professional Summary (optional)
3. Skills/Technical Skills
4. Professional Experience
5. Education
6. Certifications (if relevant)
7. Additional (volunteer, languages, etc.)ATS-Recognized Headers:
Format Options:
PROFESSIONAL EXPERIENCE
━━━━━━━━━━━━━━━━━━━━━━
or
Professional Experience
_______________________
or
PROFESSIONAL EXPERIENCEJOHN SMITH
john.smith@email.com | (555) 123-4567 | linkedin.com/in/johnsmith
San Francisco, CAJOHN SMITH
San Francisco, CA
john.smith@email.com | (555) 123-4567
LinkedIn: linkedin.com/in/johnsmith | GitHub: github.com/johnsmithCOMPANY NAME | City, ST
Job Title | Month Year - Month Year
• Achievement bullet with metrics and results
• Achievement bullet with metrics and results
• Achievement bullet with metrics and resultsJob Title
COMPANY NAME, City, ST Month Year - Month Year
• Achievement bullet with metrics and results
• Achievement bullet with metrics and resultsSKILLS
Python, JavaScript, SQL, React, Node.js, AWS, Docker, Git, Agile, JIRATECHNICAL SKILLS
Languages: Python, JavaScript, TypeScript, SQL
Frameworks: React, Node.js, Django, Flask
Tools: AWS, Docker, Kubernetes, Git, JenkinsSKILLS
Languages Frameworks Tools
Python React AWS
JavaScript Node.js Docker
SQL Django GitNote: Multi-column layouts may cause ATS issues. Test before using.
EDUCATION
Bachelor of Science in Computer Science
University of California, Berkeley | 2018
GPA: 3.8/4.0 (include if 3.5+)EDUCATION
MBA, Finance & Strategy | Stanford Graduate School of Business | 2020
• Graduated with Distinction
• Relevant Coursework: Corporate Finance, M&A StrategyProblem: Dense paragraphs with no bullets Solution: Use bullet points, keep paragraphs short
Problem: Different fonts, sizes, or styles throughout Solution: Pick one format and stick to it
Problem: Fancy designs that break ATS Solution: Save creativity for portfolio, not resume
Problem: Cramming everything onto one page Solution: Edit ruthlessly, prioritize relevance
Problem: Half-page resume with massive margins Solution: Add detail, reduce margins (to 0.5")
FirstName_LastName_Resume.pdf
JohnSmith_Resume_ProductManager.pdfAvoid:
When formatting a resume:
markdown# RESUME FORMATTING REVIEW ## Current Issues - [ ] [Issue 1] - [ ] [Issue 2] - [ ] [Issue 3] ## Recommended Changes ### Document Setup - Margins: [Current] → [Recommended] - Font: [Current] → [Recommended] - Font sizes: [Current] → [Recommended] ### Section Order **Current:** [Current order] **Recommended:** [New order and why] ### Visual Improvements - [Specific change 1] - [Specific change 2] ### ATS Compatibility Fixes - [Fix 1] - [Fix 2] ## Before/After Preview ### Before: [Description or example of current formatting] ### After: [Description or example of improved formatting]
Before submitting any resume:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 10,604 | 6,194 | -42% | 1 | 1 | 0% | 1,755 | 3,285 | +87% | 0 | 0 | — |
case-05 | pass→pass | 9,357 | 7,890 | -16% | 1 | 1 | 0% | 1,719 | 3,705 | +116% | 0 | 0 | — |
case-01 | fail→pass | 19,097 | 10,384 | -46% | 1 | 1 | 0% | 3,649 | 4,230 | +16% | 0 | 0 | — |
case-02 | fail→pass | 14,677 | 12,015 | -18% | 1 | 1 | 0% | 2,957 | 4,532 | +53% | 0 | 0 | — |
case-03 | fail→pass | 14,961 | 8,725 | -42% | 1 | 1 | 0% | 2,723 | 3,858 | +42% | 0 | 0 | — |
case-04 | pass→pass | 9,152 | 8,402 | -8% | 1 | 1 | 0% | 1,608 | 3,614 | +125% | 0 | 0 | — |
case-07 | pass→pass | 7,832 | 5,689 | -27% | 1 | 1 | 0% | 1,476 | 3,260 | +121% | 0 | 0 | — |
case-08 | pass→pass | 11,343 | 9,443 | -17% | 1 | 1 | 0% | 1,887 | 3,771 | +100% | 0 | 0 | — |
case-09 | pass→pass | 11,007 | 8,357 | -24% | 1 | 1 | 0% | 1,926 | 3,572 | +85% | 0 | 0 | — |
case-10 | fail→pass | 8,348 | 8,454 | +1% | 1 | 1 | 0% | 1,429 | 3,605 | +152% | 0 | 0 | — |
case-11 | pass→pass | 7,050 | 4,286 | -39% | 1 | 1 | 0% | 1,250 | 2,907 | +133% | 0 | 0 | — |
case-12 | pass→pass | 7,968 | 7,108 | -11% | 1 | 1 | 0% | 1,565 | 3,331 | +113% | 0 | 0 | — |
case-13 | pass→pass | 7,952 | 5,486 | -31% | 1 | 1 | 0% | 1,355 | 3,282 | +142% | 0 | 0 | — |
case-14 | fail→pass | 13,517 | 14,897 | +10% | 1 | 1 | 0% | 2,247 | 4,784 | +113% | 0 | 0 | — |
case-15 | fail→pass | 9,850 | 7,135 | -28% | 1 | 1 | 0% | 1,963 | 3,523 | +79% | 0 | 0 | — |
case-16 | pass→pass | 13,060 | 6,585 | -50% | 1 | 1 | 0% | 2,538 | 3,309 | +30% | 0 | 0 | — |
case-17 | pass→pass | 10,207 | 8,373 | -18% | 1 | 1 | 0% | 1,800 | 3,625 | +101% | 0 | 0 | — |
case-18 | pass→pass | 11,507 | 10,089 | -12% | 1 | 1 | 0% | 1,890 | 4,047 | +114% | 0 | 0 | — |
case-19 | pass→pass | 7,115 | 7,393 | +4% | 1 | 1 | 0% | 1,242 | 3,404 | +174% | 0 | 0 | — |
case-20 | pass→pass | 19,514 | 19,738 | +1% | 1 | 1 | 0% | 3,107 | 5,501 | +77% | 0 | 0 | — |
case-21 | fail→fail | 3,028 | 2,211 | -27% | 1 | 1 | 0% | 519 | 2,514 | +384% | 0 | 0 | — |
case-22 | pass→pass | 8,123 | 8,444 | +4% | 1 | 1 | 0% | 1,634 | 3,712 | +127% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.