perf-verifier
llms.txt0 starsChanged 29 days agoMITView on GitHub
One Agent Skill plus a Python 3 script. No third-party package. The script does not import a network library. Repo: https://github.com/David-Florian2013/perf-verifier npx skills add David-Florian2013/perf-verifier -g -a '*' -y Do not call code faster without a measurement. scan flags patterns such as a list copied inside a loop. bench, profile, scale and compare print times. FASTER is the only compare result that supports the word "faster". The demo runs scan on examples/slow.py and examples/fast.py. slow.py copies the list on every…
In this repositoryOne other file it gives its agents.
- perf-verifierSkill
The file
We split this llms.txt 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 11
Do not call code faster without a measurement.
≈ “Common” is an estimate: at least 1 in 5 of the 3,806 llms.txt 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
# perf-verifier One Agent Skill plus a Python 3 script. No third-party package. The script does not import a network library. Repo: https://github.com/David-Florian2013/perf-verifier Install: npx skills add David-Florian2013/perf-verifier -g -a '*' -y Do not call code faster without a measurement. scan flags patterns such as a list copied inside a loop. bench, profile, scale and compare print times. FASTER is the only compare result that supports the word "faster". The demo runs scan on examples/slow.py and examples/fast.py. slow.py copies the list on every iteration. fast.py appends. The scan output is the locked transcript. Timings are not, because they change per machine. MIT.
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.

