Resume bullet rewriter

Skill nicholashidalgo/claude-skillforge/career/resume-bullet-rewriter

Install

npx -y skills add nicholashidalgo/claude-skillforge --skill resume-bullet-rewriter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Rewrites a single resume bullet to be metric-backed, action-verb-led, and free of banned phrases.

SKILL.md

2.9 KB, as published. Nobody here has run it

resume-bullet-rewriter

Purpose: Targeted single-bullet rewriter. Accepts one weak bullet and returns a strengthened version plus a metric-gap warning if no number is available.

Input Schema

Field	Type	Required
`bullet`	string	yes
`context`	string	no - role, company, level
`available_metrics`	string[]	no - numbers to work in
`preserve_facts`	string[]	yes

{
  "bullet": "Responsible for improving the checkout experience and working with design.",
  "context": "Senior Product Manager, e-commerce startup",
  "available_metrics": ["checkout conversion up 12%", "reduced 3-step flow to 1-step"],
  "preserve_facts": ["12%", "1-step"]
}

Output Schema

{
  "original": "...",
  "revised": "...",
  "changes": ["removed 'responsible for'", "added metric 12%", "started with action verb 'Redesigned'"],
  "metric_warning": null
}

Prompt Flow

Pass 1: Rewrite starting with action verb. Inject best available metric from available_metrics. Remove all banned phrases. Preserve preserve_facts.

Pass 2: If no metric available, output revised bullet + metric_warning: "No metric available - add a number before publishing." Never fabricate a metric.

Examples

Short

Before: "Responsible for improving the checkout experience." After: "Redesigned checkout from a 3-step to 1-step flow, lifting conversion by 12%."

Medium

Before: "Helped to streamline the onboarding process and assisted with implementation." After: "Wrote the engineer onboarding runbook adopted across 3 teams; ramp time dropped from 6 weeks to 3."

Long (with context)

Before: "Results-driven PM passionate about delivering innovative solutions that leverage data to drive business outcomes at scale." After: "Shipped 6 product features in Q2 2024 driven by customer cohort analysis; 4 of 6 exceeded their 90-day retention targets."

Unit Tests

# tests/skills/test_resume_bullet_rewriter.py
from resume_banned import flag_banned_phrases
from ai_pattern_scrubber import detect_patterns
import re

REVISED = "Redesigned checkout from a 3-step to 1-step flow, lifting conversion by 12%."
METRIC_PATTERN = re.compile(r'\d+[%xKMB]?|\$[\d,]+|\d+\s*(weeks?|days?|steps?)')

def test_revised_no_banned_phrases():
    assert flag_banned_phrases(REVISED) == []

def test_revised_contains_metric():
    assert METRIC_PATTERN.search(REVISED), "Revised bullet must contain a metric"

def test_revised_no_high_severity():
    assert not [h for h in detect_patterns(REVISED) if h.severity == "high"]