ruflo-jujutsu
claudeAdvanced git workflows with diff analysis, risk scoring, and reviewer recommendations
2 skills · 1 command · 1 agent
Walks users through a four-phase methodology (consult, baseline, loop, finalize) producing a frozen classification prompt under per-stage information isolation.
Plugin spp from marketplace supervised-prompt-producer in JayLBean/supervised-prompt-producer. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
runRun the spp methodology against a classification task. Use when the user wants to produce a production-grade classification prompt through disciplined supervised prompt learning, has a labeled baseline available (or is willing to label one), and wants human-in-the-loop control over the process. Walk
baseline-qualitylabel-panelmetric-designpreprocessprompt-architectschema-designerstructure-advisortechnique-advisorpython3
Advanced git workflows with diff analysis, risk scoring, and reviewer recommendations
2 skills · 1 command · 1 agent
Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.
1 skill · 1 command · 1 agent
Skills for building apps with the AG-UI .NET SDK: streaming chat (stateless vs hosted agents), server tools, client tools, human-in-the-loop (approvals & interrupts), shared state, multimodal messages, reasoning traces, protobuf transport, and troubleshooting.
9 skills
Turns the corrections and repeated workflows of your work sessions into small, reviewed skill updates: every change comes with its evidence and a written reason, and nothing touches a skill until you approve and install it.
1 skill
Turn Claude Code into a visual creative assistant — AI image generation with creative workflow orchestration, prompt engineering, parallel multi-direction output, and 1,300+ curated inspiration library
2 commands · 3 agents · 1 MCP server
Severity level classification and prompt improvement for marketplace plugins. Assigns severity ratings (S1-Critical through S4-Low) and enhances plugin prompts for clarity, safety, and effectiveness.
1 skill · 2 commands · 1 agent
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.