Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Find opportunities to add metrics and estimate numbers when exact data is unavailable. Use when the user wants to quantify achievements, add numbers, percentages, or impact metrics to a resume.
.claude/skills/bilal140202-resume-quantifier/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 87% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-10 | ✓→✓ | = Same ✓ | 152% | 0% |
Use this skill when the user:
The Problem:
Studies Show:
1. Money
2. Time
3. Percentages
4. Volume/Scale
5. Quality
6. Frequency
For any experience, ask:
Scale Questions:
Impact Questions:
Comparison Questions:
Sales:
Marketing:
Customer Service:
Operations:
Engineering:
Project Management:
HR/Admin:
When you don't have exact numbers:
Principle: Estimate low to maintain credibility
Example:
Format: "X-Y" or "X to Y"
Examples:
Format: "X+" or "at least X"
Examples:
Format: Calculate from known totals
Example:
Format: Work backwards from frequency
Example:
"Improved [X] from [before number] to [after number], resulting in [Y]% improvement"
Example:
"Improved page load time from 8 seconds to 2 seconds, resulting in 75% reduction and 20% increase in user engagement""[Verb] [number] [things], resulting in [impact]"
Example:
"Managed 25 concurrent projects worth $3M, delivering 95% on-time with zero budget overruns""Processed [number] [items] per [time period], achieving [quality metric]"
Example:
"Resolved 50+ customer tickets daily, maintaining 98% satisfaction rating and 4-hour average response time""Ranked #[X] out of [Y] in [metric], [context]"
Example:
"Ranked #2 out of 45 sales representatives nationally, generating $3.2M in annual revenue"Solution: Focus on YOUR contribution
Example:
Solution: Quantify activities and inputs
Example:
Solution: Measure the work itself
Example:
Solution: Use percentages or ranges
Example:
Solution: Quantify learning, throughput, accuracy
Example:
When quantifying a resume:
markdown# RESUME QUANTIFICATION ## Analysis Summary **Bullets without numbers:** X **Bullets with numbers:** Y **Target:** 100% of bullets should have at least one metric ## Quantified Bullets ### Original Bullet #1: "Managed customer accounts" ### Questions to Find Metrics: - How many accounts? → [User answer: ~40] - What was the revenue? → [User answer: ~$2M] - What results did you achieve? → [User answer: retained most] ### Quantified Version: "Managed portfolio of 40 enterprise accounts representing $2M ARR, achieving 95% retention rate" ### Metrics Added: - Account count: 40 - Revenue: $2M ARR - Retention: 95% --- ### Original Bullet #2: [Continue for each bullet] ## Estimation Notes - [Metric]: Estimated based on [reasoning] - [Metric]: Conservative estimate using [method] ## Remaining Questions - [Questions to ask user for missing information]
For each bullet:
Every bullet can be quantified. If you think your work can't be measured, you haven't asked the right questions yet.
The goal isn't to have impressive numbers—it's to have SPECIFIC numbers that show the scope and impact of your work.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | pass→pass | 8,061 | 9,643 | +20% | 1 | 1 | 0% | 1,584 | 3,994 | +152% | 0 | 0 | — |
case-04 | pass→pass | 6,115 | 5,558 | -9% | 1 | 1 | 0% | 1,301 | 3,219 | +147% | 0 | 0 | — |
case-01 | fail→pass | 10,492 | 8,133 | -22% | 1 | 1 | 0% | 2,100 | 3,924 | +87% | 0 | 0 | — |
case-02 | fail→pass | 12,429 | 9,538 | -23% | 1 | 1 | 0% | 2,439 | 4,188 | +72% | 0 | 0 | — |
case-03 | fail→pass | 10,614 | 12,287 | +16% | 1 | 1 | 0% | 2,193 | 4,231 | +93% | 0 | 0 | — |
case-05 | pass→pass | 3,295 | 5,862 | +78% | 1 | 1 | 0% | 719 | 3,343 | +365% | 0 | 0 | — |
case-06 | pass→pass | 4,506 | 4,993 | +11% | 1 | 1 | 0% | 998 | 3,296 | +230% | 0 | 0 | — |
case-07 | pass→pass | 10,099 | 7,715 | -24% | 1 | 1 | 0% | 1,914 | 3,572 | +87% | 0 | 0 | — |
case-08 | pass→pass | 10,361 | 8,136 | -21% | 1 | 1 | 0% | 1,913 | 3,735 | +95% | 0 | 0 | — |
case-09 | pass→pass | 6,946 | 6,568 | -5% | 1 | 1 | 0% | 1,316 | 3,355 | +155% | 0 | 0 | — |
case-11 | fail→pass | 9,573 | 7,164 | -25% | 1 | 1 | 0% | 1,870 | 3,539 | +89% | 0 | 0 | — |
case-12 | pass→pass | 9,677 | 7,006 | -28% | 1 | 1 | 0% | 1,684 | 3,476 | +106% | 0 | 0 | — |
case-13 | pass→pass | 9,728 | 6,749 | -31% | 1 | 1 | 0% | 1,964 | 3,446 | +75% | 0 | 0 | — |
case-14 | pass→pass | 8,648 | 7,419 | -14% | 1 | 1 | 0% | 1,784 | 3,679 | +106% | 0 | 0 | — |
case-15 | pass→pass | 12,331 | 9,553 | -23% | 1 | 1 | 0% | 2,032 | 3,834 | +89% | 0 | 0 | — |
case-16 | pass→pass | 13,129 | 10,623 | -19% | 1 | 1 | 0% | 2,331 | 4,081 | +75% | 0 | 0 | — |
case-17 | pass→pass | 10,687 | 11,050 | +3% | 1 | 1 | 0% | 2,246 | 4,393 | +96% | 0 | 0 | — |
case-18 | pass→pass | 9,628 | 8,553 | -11% | 1 | 1 | 0% | 1,685 | 3,677 | +118% | 0 | 0 | — |
case-19 | pass→pass | 7,238 | 6,197 | -14% | 1 | 1 | 0% | 1,284 | 3,289 | +156% | 0 | 0 | — |
case-20 | pass→pass | 8,310 | 6,691 | -19% | 1 | 1 | 0% | 1,530 | 3,429 | +124% | 0 | 0 | — |
case-21 | pass→pass | 10,217 | 7,106 | -30% | 1 | 1 | 0% | 2,058 | 3,472 | +69% | 0 | 0 | — |
case-22 | pass→pass | 10,641 | 6,077 | -43% | 1 | 1 | 0% | 1,913 | 3,276 | +71% | 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 +18 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.