by valentynkit
Typed decisions with TypeSafe's Jev, the first System One model
# Add to your Claude Code skills
git clone https://github.com/valentynkit/awesome-jev-typesafeGuides for using ai agents skills like awesome-jev-typesafe.
Last scanned: 9/21/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-21T09:37:48.000Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how awesome-jev-typesafe compares with popular alternatives.
awesome-jev-typesafe is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by valentynkit. Typed decisions with TypeSafe's Jev, the first System One model. It has 190 GitHub stars.
Yes. awesome-jev-typesafe passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/valentynkit/awesome-jev-typesafe" and add it to your Claude Code skills directory (see the Installation section above). awesome-jev-typesafe ships a SKILL.md manifest, so compatible agents can discover and load it automatically.
awesome-jev-typesafe is primarily written in JavaScript. It is open-source under valentynkit on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh awesome-jev-typesafe against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
See comparison
A hand-curated list of what people build on Jev, kept in one readme and published as data.
https://awesomejev.vercel.app/projects.json once per session. It is under 400 KB and has every entry.section, subsection (the host agent for coding-agent tools), type (project, resource, list), github.stars, github.pushedAt, github.archived, jev.hostAgent, jev.tags (router, gate, compaction, judge, browserAgent as probabilities), jev.intents (probability per canonical intent, keys listed under meta.intents).trustPhrase set, higher github.stars, recent github.pushedAt, and jev.tags.riskBulkScaffold below 0.5.url and its one-sentence description verbatim. Do not paraphrase claims into stronger ones.Smaller views: https://awesomejev.vercel.app/llms.txt (index), https://awesomejev.vercel.app/llms-full.txt (every entry as markdown), https://awesomejev.vercel.app/c/<section-slug>.md (one section).
https://awesomejev.vercel.app/api/rerank. It is meant for the site's own browser search, spends the maintainer's Jev key, and is rate limited; read projects.json instead.Pull request only. Add one line in the format - [name](url) - One sentence. at the bottom of the most specific section of readme.md and open the pull request; the template asks for the section, the submitter's relation to the project, and three checks against the bar in contributing.md. Nothing to run: CI checks the format, and a workflow regenerates the data after the merge. Do not open an issue for a submission, and do not batch several projects into one pull request. If you act for a person, say so in the pull request body.