agentleFS
reatlatreatlat/fullstory-claude-plugin/skills/revenue-impact/SKILL.md

revenue-impact

Skill36 starsChanged 17 days agoMITView on GitHub

Attach revenue estimates to UX issues and conversion problems. Use when the user wants to know what a friction point or conversion drop is costing in dollars.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Ask the user for:

    line 25
  2. Distinctive:

    If they don't know, offer to compute from Fullstory:

    line 30
  3. Distinctive:

    Never fabricate AOV or conversion rates.

    line 67
  4. Distinctive:

    Use ranges, not precise numbers.

    line 68
  5. Distinctive:

    If the UX issue only affects a subset of users (e.g., Safari users on mobile), narrow the calculation to that subset.

    line 70

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Revenue Impact

Estimate the revenue cost of UX issues — put a dollar figure on rage clicks, conversion drops, and error spikes.

When This Runs

Invoked automatically by frustration-hunter, funnel-doctor, and error-forensics when the user asks "what does this cost us?" or "what's the revenue impact?" Not user-invocable directly.

Workflow

Step 1: Get the affected user count

From whichever skill invoked this, extract:

  • How many users are affected (from get_opportunity_stats or compute_metric)
  • Over what time period

Step 2: Get the business numbers

Ask the user for:

  • Average order value (AOV) or average revenue per user
  • Conversion rate for the affected flow (if not already known)
  • Traffic volume to the affected page (if not already known)

If they don't know, offer to compute from Fullstory:

fullstory:build_metric(query="completed purchases", output_type="single_number")
fullstory:compute_metric(metric_id)
→ also compute total unique users on the checkout page
→ derive: conversion rate = completed / total

For AOV: Fullstory doesn't track revenue natively (unless it's sent as a custom event). If revenue data isn't in Fullstory, ask the user for AOV. Don't guess.

Step 3: Calculate

Basic formula:

Revenue lost = affected users × conversion rate × AOV

Example:

  • 412 users rage-clicked "Apply Promo" on checkout
  • Checkout conversion rate: 20%
  • AOV: $85

"Of those 412 users, if the rage click caused even half of them to abandon — that's potentially 41 lost purchases (412 × 20% × 50% abandon rate). At $85 AOV, that's ~$3,500 in the last 7 days, or $182K annualized."

Be explicit about assumptions. Use ranges: "$3,000–5,000" not "$3,472."

Step 4: Present with context

Always show:

  1. The UX issue (what's broken)
  2. User impact (how many affected)
  3. Revenue estimate (with assumptions stated)
  4. Time period (per week, per month, annualized)
  5. Confidence level (high if you have session evidence, low if you're extrapolating from small samples)

Guidelines

  • Never fabricate AOV or conversion rates. If you don't have the data, say "I need your average order value to estimate the revenue impact."
  • Use ranges, not precise numbers. Revenue estimates are directional, not accounting-grade.
  • Annualize cautiously. A 7-day sample × 52 is a rough heuristic, not a forecast.
  • If the UX issue only affects a subset of users (e.g., Safari users on mobile), narrow the calculation to that subset.
  • Frame revenue impact as motivation to fix, not as a promise. "Fixing this could recover ~$3,500/week" not "You're losing $3,500/week."

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.