Compare Prices
Skill35 starsChanged 4 days agoMITView on GitHub
Cross-store price comparison with an explicit verdict. 1. Determine the exact product identity from the task (model, size, variant). If ambiguous, pick the most common variant and say so in the answer. 2. search the product + "buy" on the first preferred site, open the best product link with new_tab. 3. On each product page extract: title, current price (with currency), rating, review count, delivery cost/eta if shown, and the canonical URL. 4. Repeat for at least one more site…
In this repository11 other files it gives its agents.
- Deep ResearchSkill
- Extract DataSkill
- Fill FormSkill
- Find AlternativesSkill
- Manage BookmarksSkill
- Monitor PageSkill
- Organize TabsSkill
- Read LaterSkill
- Save PageSkill
- Screenshot WalkthroughSkill
- Summarize PageSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
If ambiguous, pick the most common variant and say so in the answer.
- Distinctive: line 35
If a site fails/blocks, note it and continue with the others.
- Very specific: line 36
Prefer preferred-sites first, then any relevant store from the task text.
≈ “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
Compare Prices
Cross-store price comparison with an explicit verdict.
Procedure
- Determine the exact product identity from the task (model, size, variant). If ambiguous, pick the most common variant and say so in the answer.
searchthe product + "buy" on the first preferred site, open the best product link withnew_tab.- On each product page
extract: title, current price (with currency), rating, review count, delivery cost/eta if shown, and the canonical URL. - Repeat for at least one more site (
switch_tabbetween them, max 4 tabs). - Return
donewith a comparison table and the winner.
Tool discipline
- Open real product pages — do not price from search-result snippets.
- If a site fails/blocks, note it and continue with the others; never stall.
- Prefer
preferred-sitesfirst, then any relevant store from the task text.
Answer format
| Store | Product | Price | Rating | URL |
Winner: <store> at <price> (<savings vs next best>)Also mirror the rows in data: { "comparisons": [...], "best": {...} }.
Verify before done
- Prices are read from the product page itself, not memory or snippets.
- At least 2 stores compared.
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.

