UditAkhourii / quicksilver
Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
Why this job: says: benchmark
What it does
A big share of every Claude Code session is spent reading things only to decide whether they matter. *Which of these 187 files handle auth? Which of these 3,000 log lines are real failures? Which of these 200 tickets are refund requests?* Claude reads it all, pays for it all, and the context fills up with noise.
Get started
npx github:UditAkhourii/quicksilver - Maintenance
- Active
- Last commit 45 days ago
- Stars
- 142
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- JavaScript
- 98% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 2 still open
- Pull requests
- 0 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| openlayer-ai / jevals | 117 | 2 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- JavaScript 98%
- PowerShell 1%
- Shell 1%
Topics
- ai-agents
- claude
- claude-code
- developer-tools
- jev
- llm
- skill
- tokens
- typesafe
Project record
- JobEvals and observability
- StatusListed
- Commits2
- Forks11
- Watching2
- Stars in 28 days+20
- CreatedSep 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026