Purpose
Compare a described benefits package against market norms for the company's industry, size, and talent tier — then return a category-by-category gap analysis with competitiveness ratings and a prioritized set of additions or upgrades. Replaces the slow, survey-stitching process of figuring out where a benefits offering is ahead, at par, or behind the market.
When to Use
Invoke this skill when the user asks to:
- Benchmark their benefits package against competitors or market norms
- Prepare for an open enrollment redesign or annual benefits review
- Build the business case for adding or upgrading a specific benefit
- Diagnose why candidates are declining offers for non-base-salary reasons
- Identify the highest-impact gaps in their total rewards offering
- Justify benefits spend to finance or leadership with market context
Inputs Required
Before starting, collect:
- Company profile: Industry, headcount, growth stage (e.g., Series B SaaS, ~250 employees, scaling)
- Talent tier: Who they compete against for talent (FAANG-tier, well-funded startups, regional employers, etc.)
- Geography: Primary employee locations (US national, specific metros, remote-distributed, international)
- Current benefits: The package as it stands — health, retirement, leave, equity, perks, anything offered
- Workforce composition: Rough mix (e.g., mostly early-career engineers, dual-income parents, distributed senior ICs)
- Constraints: Budget posture, fixed-cost limits, or benefits that are off the table
- Strategic goal: What they want benefits to do — improve retention, win competitive offers, control cost, support a specific demographic
If talent tier or geography is missing, default to the company's stated industry peers at the same headcount band and note the assumption.
Instructions
Step 1: Establish the Benchmark Cohort
Before analyzing anything, define what "market" means for this employer.
- Set the comparison cohort using industry + headcount band + talent tier — not a generic national average
- Identify the two relevant benchmarks: table stakes (what's required to be considered) and differentiators (what wins competitive offers in this cohort)
- State the cohort explicitly so every rating that follows is anchored to it (e.g., "Benchmarked against well-funded 100–500 person SaaS companies competing for senior engineering talent in major US metros")
Step 2: Analyze Each of 8 Benefit Categories
For every category below, do four things: (1) summarize what the employer currently offers, (2) state the cohort norm, (3) assign a competitiveness rating, (4) name the specific gap or strength.
Competitiveness rating scale (use exactly):
- Below Market — falls short of table stakes; actively costs offers or retention
- At Market — meets table stakes; neither a draw nor a deterrent
- Above Market — exceeds the norm; a genuine differentiator in the cohort
- Best in Cohort — top decile; a recruiting and retention asset worth promoting
Category 1 — Health & Medical Coverage Plan types offered, employee premium share, deductible/out-of-pocket exposure, dependent coverage cost, and HSA/FSA availability. Cohort norm centers on employer premium contribution % and dependent affordability.
Category 2 — Retirement & Long-Term Savings 401(k) match structure, vesting schedule, auto-enrollment, and any profit-sharing. Benchmark on effective match value (% of salary) and vesting speed.
Category 3 — Equity & Long-Term Incentives Grant size relative to level, refresh/evergreen policy, vesting schedule, early-exercise options, and extended post-termination exercise windows. Critical for startup and tech cohorts — often the single largest competitive lever.
Category 4 — Paid Time Off & Leave Vacation policy (accrued vs. unlimited), sick leave, parental leave (primary and secondary caregiver weeks, pay %), sabbatical, and bereavement. Parental leave is frequently the most-scrutinized item.
Category 5 — Family & Caregiving Support Fertility/IVF coverage, adoption/surrogacy assistance, childcare stipends or backup care, and dependent care FSA. Increasingly a table-stakes differentiator in competitive tech cohorts.
Category 6 — Mental Health & Wellbeing EAP, therapy/coaching platforms (Lyra, Spring Health, etc.), wellness stipends, and covered visit counts. Benchmark on access and session caps, not just "we have an EAP."
Category 7 — Professional Development & Growth Learning stipend, conference budget, tuition reimbursement, internal mobility, and coaching. Especially weighted by early-career and senior IC populations.
Category 8 — Flexibility & Lifestyle Perks Remote/hybrid policy, home office stipend, flexible hours, commuter benefits, and meaningful perks (vs. perks-as-noise). Rate the policy substance, not the perk count.
Step 3: Map Gaps Against Workforce Composition
Re-read the category ratings through the lens of who actually works there.
- Flag any Below Market rating in a category that matters disproportionately to this workforce (e.g., weak parental leave for a dual-income-parent-heavy team is a higher-severity gap than for an early-career team)
- Identify "wasted spend" — Above Market or Best in Cohort benefits the current workforce underuses
- Surface the one or two gaps most likely to be driving the stated strategic problem
Step 4: Build the Cost-vs-Impact Matrix
Place each recommended change into one of four quadrants:
- Quick Wins — low cost, high impact (do first)
- Strategic Investments — high cost, high impact (build the case)
- Fill-Ins — low cost, low impact (bundle opportunistically)
- Reconsider — high cost, low impact (likely deprioritize) Assign each recommendation a rough cost posture (Low / Moderate / Significant) relative to per-employee spend, and an impact rationale tied to retention, recruiting, or the stated goal.
Step 5: Prioritized Recommendations
Produce 5–8 recommendations ranked by expected impact on the stated strategic goal. For each: the specific change, where it moves the rating (e.g., "At Market → Above Market"), the rough cost posture, and a one-line rationale. Be opinionated about sequence.
Output Format
- Structure: Benchmark cohort statement → 8-category analysis table → workforce-fit gap flags → cost-vs-impact matrix → ranked recommendations
- Length: 1,000–1,400 words
- Format: Category analysis as a table (Category | Current Offering | Cohort Norm | Rating | Gap/Strength); recommendations as a ranked numbered list; cost-vs-impact as a labeled four-quadrant breakdown
- Sections: Benchmark Cohort → Category-by-Category Analysis → Workforce-Fit Gaps → Cost vs. Impact Matrix → Prioritized Recommendations
- Tone: Total rewards analyst — data-anchored, decisive, and budget-aware; reads like an internal brief leadership can act on, not a vendor pitch
Quality Checklist
Before delivering output, verify:
- [ ] All 8 categories are analyzed with all four elements (current offering, cohort norm, rating, gap/strength)
- [ ] Every rating uses one of the four defined labels — no improvised ratings
- [ ] The benchmark cohort is stated explicitly and every rating is anchored to it (not a generic national average)
- [ ] At least one gap is connected directly to the workforce composition and the stated strategic goal
- [ ] Every recommendation includes a rating movement, a cost posture, and a one-line rationale
- [ ] Recommendations are ranked by impact — not listed by category order
Notes
- The most common diagnostic error is benchmarking against a national average instead of the actual talent-competition cohort — a "generous" package can still be Below Market against FAANG-tier competitors.
- Equity and parental leave are disproportionately scrutinized by candidates in tech cohorts; weight them accordingly even when other categories look strong.
- When the user's strategic goal is retention vs. recruiting, the same gap can carry different priority — recruiting losses point to offer-stage benefits (equity, sign-on-adjacent perks), retention losses point to lived-experience benefits (leave, flexibility, caregiving).
- If current benefits are described vaguely in a category, rate what's stated and flag the ambiguity rather than assuming a generous default.
How to use this skill
This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.
Installing in Claude Code:
~/.claude/skills/<folder-name>/SKILL.md— auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)<your-project>/.claude/skills/<folder-name>/SKILL.md— auto-loads only when working in that project (recommended for project-specific skills)
Restart Claude Code or open a new session to register.
Using in Claude.ai, ChatGPT, Gemini, or other AI tools:
- Drag this file into a new chat, or copy and paste its contents
- Send your task or request as your next message — the AI will apply the skill where it fits
For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills