peer-benchmarking
Skill15 starsChanged 3 months agoMITView on GitHub
Compares a company's key financial ratios against true peer medians and quartiles, flagging which peers were excluded and why, so the read is defensible rather than a single flattering comparison. Use whenever the user wants to benchmark a company against competitors, needs a peer comparison for a board deck or investor update, or has a benchmarking claim with no stated peer set or exclusion logic behind it.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Distilla-AI/distilla-skillstheir own version, first seen Nov 1, 2026
- sakuruamayday-ops/enterprise-project-application-assistanttheir own version, first seen Oct 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Distilla-AI/distilla-skills★ 9same name
- sakuruamayday-ops/enterprise-project-application-assistant★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- annual-operating-planSkill
- ar-ap-aging-analyzerSkill
- balance-sheet-health-checkSkill
- board-reporting-pack-builderSkill
- capex-roi-evaluatorSkill
- cash-runway-burn-analyzerSkill
- covenant-headroom-monitorSkill
- credit-risk-scoringSkill
- debt-schedule-modelSkill
- driver-based-budget-builderSkill
- fx-exposure-advisorSkill
- kpi-tree-dashboardSkill
- liquidity-stress-testSkill
- margin-decompositionSkill
- month-end-close-acceleratorSkill
- recurring-report-builderSkill
- rolling-forecast-builderSkill
- scenario-planning-engineSkill
- thirteen-week-cash-forecastSkill
- three-statement-modelSkill
- variance-bridge-analyzerSkill
- working-capital-optimizerSkill
- zero-based-budget-plannerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
State exclusions explicitly: If a company in the obvious peer group is excluded (different fiscal year, recent M&A distorting the numbers, …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Peer Benchmarking
When to use
Use whenever a performance claim needs external context, "our margin is strong" means nothing without knowing what peers actually post, or when preparing a board or investor update that will get challenged on comparability. Also use to check a benchmarking claim someone else made, where the peer set and exclusions were never stated.
What it does
Builds a defensible peer comparison: a real peer set (not cherry-picked), calendarized to the same period, with median and quartile ranges per metric, and an explicit note on which companies were excluded and why. The output is a range with a position in it, not a single flattering number lifted from the best comparison available.
Method
- Define the peer set by real comparability criteria — similar business model, similar scale (revenue or headcount band), similar growth stage, similar geography — not just "companies in the same industry label."
- State exclusions explicitly. If a company in the obvious peer group is excluded (different fiscal year, recent M&A distorting the numbers, private and unreported), name it and why. An unexplained exclusion is exactly how benchmarking gets cherry-picked.
- Calendarize before comparing. Companies with different fiscal year ends are not directly comparable on a raw calendar-quarter basis — align to trailing twelve months or the nearest common period.
- Compute median and quartile range per metric, not just an average — an average can be dragged by one outlier peer; the quartile range shows where the real distribution sits.
- Place the subject company's actual number inside that range and state the percentile plainly: "24th percentile on gross margin" is a finding; "below average" is not.
- Separate metrics where the company is structurally different (different revenue recognition, different capital intensity) — flag these instead of forcing a comparison that isn't apples-to-apples.
- State what the benchmark implies for action, not just where the company sits — a bottom-quartile metric with a plausible structural explanation needs different follow-up than one with no explanation at all.
Inputs
- The company's own financials for the metrics being benchmarked
- Candidate peer companies with comparability rationale
- Peer financial data (public filings, industry surveys, or available comparables)
- The specific metrics that matter for this comparison
Output format
Peer set with comparability rationale; explicit exclusion list with reasons; calendarized metric table; median and quartile range per metric; subject company's percentile position per metric; a plain read on what the position implies.
Example
A SaaS company claims "our gross margin beats the industry" citing one hand-picked competitor. Rebuilding the peer set with eight comparable companies (similar ARR band, similar go-to-market motion) calendarized to trailing twelve months shows the company actually sits at the 40th percentile, not top of class — the original claim relied on comparing against the one peer with unusually low margin, not a representative set.
Common pitfalls
- Comparing against whichever peer happens to look most favorable instead of a defensible, stated peer set.
- Averaging instead of showing the quartile range, hiding how spread out the real comparison actually is.
- Comparing raw numbers across different fiscal year ends without calendarizing first.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

