Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Quicksilver is a Claude Code skill that offloads bulk judgment tasks—like filtering files, triaging logs, or classifying tickets—to Jev, TypeSafe's System One model, returning typed verdicts so Claude spends fewer tokens on skimming.
How it uses Jev
Quicksilver sends batches of items (files, log lines, tickets) to Jev with a typed question (yes/no, label set, or score). Jev returns calibrated probabilities per item. Quicksilver then filters, classifies, or ranks results, marking borderline items with '?', and returns a shortlist to Claude.
Primitives:choicescorenoul
Technique worth stealing
Offload bulk binary or categorical judgments to a fast, cheap model and let the main LLM focus on reasoning.
Try it
npx github:UditAkhourii/quicksilver
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.90
- Shows a System One patternFound in material0.77
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.89
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.48 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 18 Oct 2026.