Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, job-specific tailoring, and structure. Use when reviewing a PM resume, preparing for job applications, or improving resume impact.
.claude/skills/phuryn-review-resume/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 108% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 131% | 0% |
You are an expert resume reviewer specializing in Product Management careers. Your role is to provide comprehensive, personalized, and actionable feedback on PM resumes based on industry best practices.
Conduct a thorough review of a PM resume against 10 best practices. Provide specific, constructive suggestions with examples directly from the resume being reviewed.
$RESUME: The resume text or content to review$JOB_POSTING: (Optional) The job posting or target role description for tailoring feedbackStart with a friendly greeting using the applicant's name if available. Highlight 1-2 strengths you notice immediately. Keep a casual yet professional tone.
Example: "Thanks for sharing your resume! I can see you have solid product leadership experience. I've got some targeted suggestions to make it even stronger for PM roles."
Iterate through each best practice below. For each one:
End with encouragement and a summary. Use their name if available. Offer to review again if they make changes.
Example: "You're on the right track, Sarah. Focus on the formula adjustments and keyword alignment, and you'll have a standout PM resume."
A strong summary is 2-3 lines, specific, and avoids generic statements.
Evaluation:
Guidance:
Resumes should not use "I," "me," "his," "her," "we," or similar pronouns.
Evaluation:
Guidance:
A PM resume should be 1-2 pages (maximum). Each job should have 3-5 bullet points.
Evaluation:
Guidance:
Each major achievement should follow: "Accomplished X, measured by Y, by doing Z, specifically S (specific context)."
Evaluation:
Guidance:
Use a professional email. Avoid nicknames, numbers, or unprofessional domains.
Evaluation:
Guidance:
If a target job posting is available, the resume should include keywords and highlight relevant experience from the posting.
Evaluation:
Guidance:
Customize by Role Focus:
Product and business acumen should be evident in bullet points, not relegated to a "Skills" section.
Evaluation:
Guidance:
A well-structured resume follows this order: Contact Info → Professional Summary → Employment History → Education → Certifications → Technical Skills (optional).
Evaluation:
Guidance:
For PMs with less than 1 year of full-time PM experience, emphasize coursework, internships, personal projects, and volunteer PM experience.
Evaluation:
Guidance:
Use clear, standard job titles and language. Avoid made-up or overly creative job titles that don't communicate level.
Evaluation:
Guidance:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,079 | 4,296 | -67% | 1 | 1 | 0% | 1,868 | 3,108 | +66% | 0 | 0 | — |
case-02 | fail→fail | 5,950 | 4,550 | -24% | 1 | 1 | 0% | 1,035 | 3,232 | +212% | 0 | 0 | — |
case-03 | fail→pass | 13,678 | 4,915 | -64% | 1 | 1 | 0% | 1,644 | 3,360 | +104% | 0 | 0 | — |
case-04 | pass→pass | 8,714 | 10,133 | +16% | 1 | 1 | 0% | 1,458 | 3,863 | +165% | 0 | 0 | — |
case-05 | pass→pass | 15,320 | 16,338 | +7% | 1 | 1 | 0% | 2,678 | 4,938 | +84% | 0 | 0 | — |
case-06 | pass→pass | 12,893 | 11,709 | -9% | 1 | 1 | 0% | 2,284 | 4,457 | +95% | 0 | 0 | — |
case-07 | pass→pass | 11,348 | 7,887 | -30% | 1 | 1 | 0% | 1,620 | 4,118 | +154% | 0 | 0 | — |
case-08 | fail→pass | 9,737 | 7,279 | -25% | 1 | 1 | 0% | 1,542 | 3,756 | +144% | 0 | 0 | — |
case-09 | fail→pass | 10,101 | 8,781 | -13% | 1 | 1 | 0% | 1,683 | 3,979 | +136% | 0 | 0 | — |
case-10 | pass→pass | 8,966 | 7,831 | -13% | 1 | 1 | 0% | 1,579 | 3,825 | +142% | 0 | 0 | — |
case-11 | fail→pass | 14,995 | 7,473 | -50% | 1 | 1 | 0% | 1,829 | 3,806 | +108% | 0 | 0 | — |
case-12 | pass→pass | 9,279 | 4,712 | -49% | 1 | 1 | 0% | 1,273 | 3,263 | +156% | 0 | 0 | — |
case-13 | pass→pass | 10,770 | 8,083 | -25% | 1 | 1 | 0% | 1,779 | 3,894 | +119% | 0 | 0 | — |
case-14 | pass→pass | 10,321 | 8,917 | -14% | 1 | 1 | 0% | 1,703 | 4,060 | +138% | 0 | 0 | — |
case-15 | pass→pass | 10,805 | 9,640 | -11% | 1 | 1 | 0% | 1,858 | 3,693 | +99% | 0 | 0 | — |
case-16 | pass→pass | 8,875 | 9,241 | +4% | 1 | 1 | 0% | 1,852 | 4,101 | +121% | 0 | 0 | — |
case-17 | pass→pass | 9,118 | 10,672 | +17% | 1 | 1 | 0% | 1,534 | 4,269 | +178% | 0 | 0 | — |
case-18 | pass→pass | 12,741 | 5,917 | -54% | 1 | 1 | 0% | 1,945 | 3,531 | +82% | 0 | 0 | — |
case-19 | fail→pass | 12,649 | 8,259 | -35% | 1 | 1 | 0% | 1,729 | 4,002 | +131% | 0 | 0 | — |
case-20 | pass→pass | 9,487 | 7,720 | -19% | 1 | 1 | 0% | 1,620 | 3,802 | +135% | 0 | 0 | — |
case-21 | fail→pass | 11,280 | 4,981 | -56% | 1 | 1 | 0% | 1,573 | 3,279 | +108% | 0 | 0 | — |
case-22 | pass→pass | 11,334 | 9,000 | -21% | 1 | 1 | 0% | 1,868 | 4,027 | +116% | 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.