test-compare
Skill1 starsChanged 37 days agoMITView on GitHub
Compare CSS extraction results between two runs or two selectors on the same page, to verify consistency and correctness
In this repository6 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- build-checkSkill
- test-extractSkill
- test-mcpSkill
- clone-pageSkill
- extractSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Run extraction on one or two selectors and compare/analyze the results.
- Distinctive: line 15
If only URL and one selector provided:
- Distinctive: line 17
Run extraction twice on the same URL + selector
- Distinctive: line 20
If differences found, show exactly what differs
- Distinctive: line 24
If URL and two selectors provided:
- Very specific: line 26
Run extraction on selector1, save to /tmp/snipkiwi-test-1.json
≈ “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 Extraction Results
Run extraction on one or two selectors and compare/analyze the results.
Mode 1: Single selector stability test (2 args)
If only URL and one selector provided:
- Build:
npx tsc - Run extraction twice on the same URL + selector
- Compare the two JSON outputs
- Report whether results are deterministic (identical CSS, HTML, Tailwind)
- If differences found, show exactly what differs
Mode 2: Two selector comparison (3 args)
If URL and two selectors provided:
- Build:
npx tsc - Run extraction on selector1, save to /tmp/snipkiwi-test-1.json
- Run extraction on selector2, save to /tmp/snipkiwi-test-2.json
- Compare:
- How many CSS rules each produced
- Whether they share any CSS rules
- Tailwind class overlap
- HTML structure differences
Commands
# Run extraction and capture JSON
node dist/index.js --url "$URL" --selector "$SEL" --format json 2>/dev/nullOutput
Present results as a clear comparison table with pass/fail indicators. Clean up temp files when done.
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.

