Purpose
Compare a finance function's key operating metrics against industry-median and top-quartile benchmarks, then quantify the gap to each threshold and the dollar/FTE headroom available — producing a defensible, prioritized view of where the function underperforms and how much improvement is realistically on the table.
When to Use
Invoke this skill when the user asks to:
- Benchmark their finance function's cost, headcount, or cycle-time metrics against peers
- Assess whether their cost of finance or days-to-close is competitive
- Build the business case for a finance transformation or automation initiative
- Prepare a benchmarking slide or narrative for the board or CFO staff
- Identify which finance sub-processes (close, AP, FP&A, T&E) have the most headroom
- Quantify the FTE or dollar savings available from reaching top-quartile performance
Inputs Required
Before starting, collect:
- Company revenue: Annual revenue (for normalizing FTE and cost ratios)
- Industry/sector: Primary industry (benchmarks vary materially by sector)
- Finance function metrics: Any subset of — cost of finance as % of revenue, finance FTEs per $1B revenue, days to close (monthly/quarterly), cost per invoice processed, DSO/DPO if relevant, % of transactions touchless/automated, forecast accuracy, FP&A analyst-to-business-partner ratio
- Business complexity factors: Number of legal entities, ERP count, M&A activity, currencies, shared-services maturity
- Comparison ambition: Benchmark to industry median, top quartile, or top decile
- Timeframe context: Whether metrics are current-state or a trailing average
If a metric is missing, benchmark only what is provided and flag the gap. If industry is unknown, default to a cross-industry median and note that sector-specific figures would tighten the analysis.
Instructions
Step 1: Normalize and Validate the Inputs
Before comparing, convert every metric to its standard benchmarking unit:
- Cost of finance: total finance function cost (people + systems + outsourcing) ÷ revenue, expressed as a %
- FTE efficiency: finance FTEs ÷ (revenue in $B) → FTEs per $1B revenue
- Days to close: business days from period-end to books-closed
- Cost per invoice: fully-loaded AP processing cost ÷ invoice volume
- Flag any metric that looks internally inconsistent (e.g., very low cost of finance but very high FTE count) and note the likely data issue rather than benchmarking a distorted figure.
Step 2: Apply the Benchmark Ranges
For each provided metric, place the company against three tiers. Use these general benchmark ranges as the baseline, adjusting the commentary for the stated industry and complexity:
- Cost of finance as % of revenue: Top quartile ≤ 0.6%; Median ~1.0%; Bottom quartile ≥ 1.5%
- Finance FTEs per $1B revenue: Top quartile ≤ 50; Median ~90–110; Bottom quartile ≥ 150
- Days to monthly close: Top quartile ≤ 4 days; Median ~6–7 days; Bottom quartile ≥ 10 days
- Cost per invoice processed: Top quartile ≤ $2; Median ~$6–10; Bottom quartile ≥ $15
- Touchless invoice %: Top quartile ≥ 80%; Median ~40–50%; Bottom quartile ≤ 20%
- Forecast accuracy (revenue, +/- variance): Top quartile ≤ 3%; Median ~5–8%; Bottom quartile ≥ 12%
For each metric, state the tier the company falls into and adjust for complexity — a company with many legal entities and multiple ERPs will legitimately sit above the median cost line, and this should be acknowledged, not scored as pure inefficiency.
Step 3: Quantify the Gap and the Headroom
For each metric, compute two numbers:
- Gap to median: distance from current performance to the median benchmark
- Gap to top quartile: distance from current performance to top-quartile benchmark Then translate the gap into a business impact:
- Cost/FTE metrics → dollars or FTEs of potential savings (gap × revenue base)
- Cycle-time metrics → days recovered and downstream reporting/decision-speed benefit
- Quality metrics → risk reduction or decision-quality improvement Always present headroom as a range (median target as conservative, top-quartile as stretch), never a single point estimate.
Step 4: Rank the Opportunities
Order the metrics by opportunity size, weighted by both the dollar/FTE headroom and the realistic effort to close the gap. Distinguish:
- Quick structural wins: process/automation fixes with clear precedent (e.g., touchless invoicing, close-task automation)
- Investment-dependent gains: require system change or reorg (e.g., FTE-per-$1B reduction via shared services)
- Constrained by design: gaps driven by legitimate business complexity that should not be chased
Step 5: Produce the Benchmark Summary Table and Narrative
Assemble the benchmark table (metric × current × median × top quartile × tier × headroom) followed by a prioritized narrative of the top 3–5 opportunities, each with the gap, the estimated headroom range, the likely lever to close it, and a one-line read on feasibility given the stated complexity.
Output Format
- Structure: Benchmark comparison table first, then ranked opportunity narrative, then a short executive read
- Length: 700–1,000 words plus the table
- Format: One structured table (metric, current value, median benchmark, top-quartile benchmark, tier, headroom range) followed by prose sections
- Sections: Input normalization notes → Benchmark comparison table → Gap & headroom analysis → Ranked opportunities (top 3–5) → Executive read (2–3 sentences)
- Tone: FP&A director briefing the CFO — quantitative, plainspoken, honest about where complexity explains a gap versus where inefficiency does
Quality Checklist
Before delivering output, verify:
- [ ] Every provided metric appears in the table with a median AND top-quartile benchmark
- [ ] Each metric is placed in a specific tier (top quartile / median / bottom quartile)
- [ ] Headroom is expressed as a range (median target + top-quartile stretch), not a single number
- [ ] At least one gap is attributed to legitimate business complexity rather than scored as pure underperformance
- [ ] Opportunities are ranked by headroom-weighted impact, not listed in input order
- [ ] Dollar/FTE headroom figures tie back to the stated revenue base and are arithmetically consistent
Notes
- The single most common error is benchmarking a distorted cost-of-finance figure — always confirm the numerator includes systems and outsourced cost, not just internal payroll
- Complexity adjustment is what makes the analysis credible to a CFO; a raw "you're above median, cut costs" read gets dismissed in the room
- Cost of finance and FTEs-per-$1B are highly correlated — if one shows large headroom and the other doesn't, investigate the data before presenting
- Frame top-quartile targets as multi-year; most functions can close 30–50% of the gap to top quartile within 18 months, not immediately
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