competitor-pricing
Skill0 starsChanged 33 days agoMITView on GitHub
Compare competitor pricing, subscription plans, features, usage limits and matched product offers. Use for SaaS pricing research, plan comparisons, ecommerce competitor prices and price-change analysis. Preserve currency, billing period, variants and source dates so unlike offers are not ranked together.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 8
Create an offer comparison that a person can verify.
- Distinctive: line 16
Use evidence-contract.md to save observations.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Competitor pricing
Create an offer comparison that a person can verify. Read the user's product, accepted competitor list and existing exports before collecting data. All live runs follow execution.md.
For public subscription or service pricing, select known pricing URLs using firecrawl-alternative from actors.json. Quote only the short relevant price or offer fragment; retain the public URL and collection date. Capture plan, currency, advertised amount, monthly or annual billing, per-seat/usage basis, minimum seats, included limits, overage, trial, tax and conditions when stated. An annual price advertised as a monthly equivalent is not a month-to-month offer. Enterprise "contact sales" stays unknown; do not estimate it.
For Amazon offers, use amazon-competitor-price-tracker with user-approved ASINs, explicit marketplace and at most three competitors initially. Omit alertWebhookUrl; sending alerts needs a separately approved destination. Verify matching product, variant, pack size, condition, seller and fulfillment. The Actor's isUndercut indicates a numeric comparison within that run; it does not establish product equivalence or a recommendation to change prices.
Build separate matrices for comparable segments or variants. Show advertised price and normalized equivalent only when conversion is transparent and mathematically valid. Do not mix currencies or silently apply exchange rates. Separate trial/promotional/list prices from the current recurring offer. Currency, billing, tax, shipping or variant gaps require a qualified comparison or a new baseline.
Use evidence-contract.md to save observations. Repeated measurements of the same offer can be compared by the local helper; failed fetches, empty datasets and missing prices do not prove an offer was removed. Preserve both dated citations for material changes.
Deliver the pricing/feature matrix, material caveats, justified opportunities and questions worth testing. Pricing proposals are hypotheses; implementing a price change, purchase or seller action is outside this skill.
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.