<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs
Devsly

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 1d ago

by lawrence3699

jev-style

JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.

  • Active — Updated in the last 14 days
Works with
  • Claude
View on GitHub (opens in a new tab)

54 GitHub stars (54)

+40 in 30 days

Stars gained per day · daily snapshots since Oct 2
Stars gained per day, Oct 2 to Nov 5: +43 in total; the busiest day was Nov 5 with +26 stars.Oct 3: +1 starsOct 4: +1 starsOct 5: +1 starsOct 6: 0 starsOct 7: +1 starsOct 8: +1 starsOct 9: 0 starsOct 10: 0 starsOct 11: 0 starsOct 12: +1 starsOct 13: +2 starsOct 14: +2 starsOct 15: 0 starsOct 16: 0 starsOct 17: 0 starsOct 18: 0 starsOct 19: +1 starsOct 20: 0 starsOct 21: +1 starsOct 22: −1 starsOct 23: 0 starsOct 24: 0 starsOct 25: 0 starsOct 26: 0 starsOct 27: +1 starsOct 28: −1 starsOct 29: 0 starsOct 30: 0 starsOct 31: +1 starsNov 1: +1 starsNov 2: 0 starsNov 3: 0 starsNov 4: +4 starsNov 5: +26 stars
Stars gained between daily snapshots
PeriodNew stars
Oct 3+1
Oct 4+1
Oct 5+1
Oct 60
Oct 7+1
Oct 8+1
Oct 90
Oct 100
Oct 110
Oct 12+1
Oct 13+2
Oct 14+2
Oct 150
Oct 160
Oct 170
Oct 180
Oct 19+1
Oct 200
Oct 21+1
Oct 22−1
Oct 230
Oct 240
Oct 250
Oct 260
Oct 27+1
Oct 28−1
Oct 290
Oct 300
Oct 31+1
Nov 1+1
Nov 20
Nov 30
Nov 4+4
Nov 5+26
  • 6 skills (6 skills found in its SKILL.md files)
  • 2 forks (2 forks)
  • 1d ago last update (Last updated 1d ago)

Install

Skills CLI

npx skills add lawrence3699/jev-style

Asks which skills and agents to install. Just one: npx skills add lawrence3699/jev-style --skill jev-style-adopt — add -g for every project.

Claude Code

git clone https://github.com/lawrence3699/jev-stylecp -r "jev-style/skills/jev-style-adopt" ~/.claude/skills/

Copies the jev-style-adopt skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add lawrence3699/jev-style

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • jev-style-adopt

    Find LLM API calls in a codebase that only return a decision (a category, yes/no, or a 1-5 rating) and move them to the local Jev-Style decision model safely - scan, pick candidates with the user, rewrite each as a typed noul/choice/score question with a confidence cascade back to the LLM, run in shadow mode, measure agreement with jev-style eval, then switch. Use when the user wants to cut LLM c…

    skills/jev-style-adopt/SKILL.md on GitHub (opens in a new tab)

  • jev-style-eval

    Measure the Jev-Style local decision model on the user's own labelled examples before relying on it - accuracy, Brier, ECE, how many decisions can be automated at a 1/5/10 % error budget and at which confidence threshold, plus a refitted calibration temperature. Use when the user asks whether the local model is good enough for their task, wants thresholds for automating a classification/routing/g…

    skills/jev-style-eval/SKILL.md on GitHub (opens in a new tab)

  • jev-style-guard

    Install the Jev-Style guard, a Claude Code PreToolUse hook that has a local decision model check every Bash, Write, Edit, Read, WebFetch and MCP tool call for destructive actions, data exfiltration, secrets access and out-of-project paths, and answers allow / ask / deny. Use when the user wants a local safety net or approval gate for Claude Code (or another agent with PreToolUse-style hooks), wan…

    skills/jev-style-guard/SKILL.md on GitHub (opens in a new tab)

  • jev-style-mcp

    Connect the Jev-Style local decision model to an AI coding agent as an MCP server (tools decide, noul, choice, score, model_info) - Claude Code, Claude Desktop, Cursor, Codex CLI, Windsurf or any MCP client. Use when the user wants their agent to classify, route, gate or score text with a local model through MCP, or asks to add jev-style as an MCP server.

    skills/jev-style-mcp/SKILL.md on GitHub (opens in a new tab)

  • jev-style-serve

    Install and start the Jev-Style local decision server (systemone-compatible API + Playground at http://127.0.0.1:8765) on macOS, Linux or Windows/WSL, pick the right backend (MLX on Apple silicon, PyTorch CUDA/CPU elsewhere, llama.cpp GGUF optional), verify it answers, and optionally keep it running at login. Use when the user wants to run Jev-Style, set up a local decision model / systemone endp…

    skills/jev-style-serve/SKILL.md on GitHub (opens in a new tab)

  • jev-style

    Call the local Jev-Style decision model (systemone-compatible API, default http://127.0.0.1:8765) to answer typed questions about text or JSON - yes/no probabilities (noul), one-of-N choices, ordered scores - for routing, classification, gating, triage, guardrails and scoring. Use when writing code that classifies, routes, scores or checks text with a small local model, when replacing an LLM call…

    skills/jev-style/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.