Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Skillbox is a self-hosted, versioned skills library for AI agents, built with React, Bun, Hono and PostgreSQL. It provides MCP access, scoped client keys, profiles with grants, and optional task-aware recommendations for teams running their own skills infrastructure.
How it uses Jev
When a user requests recommendations, Skillbox sends task text and authorized active skill descriptions to the configured provider (Vercel AI Gateway, TypeSafe AI, or OpenRouter). Jev scores the bounded skill catalog against the task, and the ranked results are returned to the client. On missing key or failure, it falls back to deterministic search with an explicit reason.
Primitives:score
Technique worth stealing
Bounded catalog scoring with batched evaluation and deterministic fallback on any provider failure.
Try it
Run `bash scripts/skillbox.sh setup` then `bash scripts/skillbox.sh start`, open http://127.0.0.1:4791, and configure a provider key in Settings → Jev recommendations.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectnot found in the excerpt0.03
- Shows a System One patternnot found in the excerpt0.05
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.09
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.23 / 2
- About JevFound in material0.60
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 28 Oct 2026.