User repository on GitHub
Rank your agent skills against a request so your agent can suggest which to invoke; powered by Jev
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Skill Picker
A Python CLI that ranks your own agent skills against a request so your agent can suggest the right one to invoke, printing JSON with a fit probability per skill and a gate probability for whether any skill applies. Ranking runs on Jev and costs two calls, 1.9 seconds on average.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Muskan Paliwal
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- Takes skill definitions from a directory and prints JSON suggestions with a fit_probability for each, plus a gate_probability for whether any skill applies.
- Ranking runs on Jev's Choice primitive, so a request comes back as a number per skill instead of a paragraph to parse.
- Two calls, 1.9 seconds on average per the README; no daemon, no background process, and it never invokes a skill for you.
- Without a TypeSafe API key it still runs, reports status: unavailable, and your agent carries on as before.
- Key lookup order: TYPESAFE_API_KEY, then ~/.config/typesafe/api-key, then a TYPESAFE_API_KEY_COMMAND secret-manager helper.
Quickstart
bash
uv tool install git+https://github.com/MuskanPaliwal/skill-pickerWatch out
Grounded in the repository README and GitHub metadata reviewed on 2026-10-15; the README shows one worked example and a 1.9-second average over two calls but no wider benchmark, and its Codex CLI section was cut off mid-page. MIT, Python 3.11+, 0 stars at review time.
Questions about this entry
Short answers drawn from the linked project or page.
It ranks your own agent skills against what you just asked for, so your agent can offer the right skill and you decide whether to use it. The README frames it as having thirty skills and remembering four.
The tool sends your request and skill definitions to Jev's Choice primitive and gets back a fit probability per skill plus a gate probability for whether any skill applies. A number you can compare against a threshold replaces prose to parse.
With uv: uv tool install git+https://github.com/MuskanPaliwal/skill-picker. Or clone the repo and pip install . with pip 24.2 or newer; it needs Python 3.11 or newer and has no dependencies.
It prints JSON with status, a gate_probability and suggestions, each carrying name, description, invocation, kind, fit_probability and relative_probability. It does nothing else: no daemon and no invocation of the skill itself.
Yes for ranking. Without one the tool still runs, reports status unavailable, and your agent carries on as before. The key can come from TYPESAFE_API_KEY, ~/.config/typesafe/api-key, or a TYPESAFE_API_KEY_COMMAND helper.
The README measures two Jev calls averaging 1.9 seconds. It gives no token or dollar figures, so treat the latency as the only published performance number and check current Jev pricing yourself.
Muskan Paliwal built skill-picker under MIT; it had 0 stars and 1 fork at review time. It only suggests skills and never invokes one, and ranking quality depends on your skill descriptions being clear.
More Jev resources like this
A macOS wrapper for Codex that has Jev pick the model and reasoning effort for the first task in a thread, pins that route so later turns reuse their model cache, and offers a menu bar app for routing preferences and quota-aware selection.
Jev Tools & CLIs#community#catalog-import#logicrw
An Ollama-style local runner for System One decision models from Hugging Face: pull, serve and query them behind the same /v1/systemone API as TypeSafe's Jev, with a terminal model manager and a browser playground.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
nvkudva/ollajevPython
nvkudva/ollajevPythonCLI and agent skill that finds useful notes in a local Obsidian vault or Logseq Markdown graph: it shortlists candidates on your machine, then has Jev rank them against your question and returns the exact source passage.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
emlembow/jev-graph-searchJavaScript
emlembow/jev-graph-searchJavaScriptAn open-source, local-first model router for coding harnesses: Jevia asks Jev for a capability tier per task, applies your safety policy, and keeps recorded execution history in your project or database so later routes learn from outcomes.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
assistant-ui/jeviaRust
assistant-ui/jeviaRustA Rust CLI that searches code by meaning with Jev: describe a concept in plain English and get relevant files, line ranges, confidence scores and source snippets, with tunable file and match thresholds plus retry handling.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
peu77/jevfindRust
peu77/jevfindRustA C/C++ compiler driver that combines Clang's optimiser with Jev for function-call inlining at every discretionary call site. The project reports 58.2% code-size reduction on Statemate from the Embench benchmark; Linux with pinned LLVM 21.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ramneet-singh/jevoptPython
ramneet-singh/jevoptPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.