Data and AI commands

marcusquinn/aidevops

Command Codex

Subjective self-refinement with blind judging, Borda aggregation, and provider-agnostic model routing.

LukeRenton/explore-claude-code

Command

Commands baked into Claude Code that execute fixed logic directly. Type / at the prompt to see them all, or type / followed by any letters to filter. Unlike bundled skills, built-in commands run immediately without agentic orchestration.

kronotop/kronotop

Command

Performs vector similarity search on a bucket using a vector index backed by JVector, with optional post-filtering to combine similarity ranking with structured query predicates.

Prorise-cool/Claude-Code-Multi-Agent

Command Claude Code

Create a Business Model Canvas (Osterwalder) or Lean Canvas (Maurya). Modes - bmc (full canvas), lean (startup-focused), quick (rapid fill). Interactive 9-block business model design.

ucsandman/DashClaw

Command Claude Code

Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates → triage → parallel worktree fixes → verify → ship. The goal prompt that drives the dashclaw-find-and-fix workflow.

MadAppGang/claude-code

Command Claude Code

Orchestrates a 5-phase workflow to update recommended AI models from OpenRouter trending rankings. Delegates scraping and filtering to model-scraper agent, obtains user approval, updates shared models file, and syncs to all plugins with comprehensive error recovery.

MadAppGang/claude-code

Command

Full-cycle agent/command development with multi-model validation and performance tracking. Orchestrates design (architect) -> plan review -> implementation (developer) -> quality review (reviewer) -> iteration. Tracks model performance to ai-docs/llm-performance.json for shortlist optimization. Enable debug mode with…

AizenvoltPrime/claude-setup

Command Claude Code

You are a Prompt Optimization Expert trained on the 10 golden rules for maximizing AI output quality. Your task is to analyze the user's prompt and transform it into a highly effective version.

BlackBeltTechnology/pi-agent-dashboard

Command

List git branches for the current dir (current marked ). Runs locally, no LLM.

DIGI-UW/OpenELIS-Global-2

Command

When the user invokes /audit-branch (optionally with arguments), perform a tiered audit of the current branch diff against its PR target (or develop), identifying LLM-assisted development artifacts, code quality issues, and constitution violations.

timothywarner-org/claude-code

Command Claude Code

Run the prompt-eval suite and report scores against the ship thresholds.

automazeio/claude-code-for-power-users

Command

When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.

disler/agentic-drop-zones

Command Claude Code

Analyze data patterns and generate additional synthetic training data.

dancinlab/hexa-lang

Command Claude Code

A help command that prints the available commands for managing a machine-learning roadmap. Machine learning is software that learns patterns from data.

shuxueshuxue/Spexcode

Command

The invocable command plugins live here: leaf plugins whose body is a prompt preset a human can pick from the / dropdown while launching or driving a session, each carrying surface: command. Grouping them keeps .plugins/ legible at a glance — the command presets on this shelf, the skill plugins on [[skills]], the…

mitulgarg/env-doctor

Command

Check if an AI model fits on your GPU before downloading.

kryptobaseddev/cleo

Command Claude Code

Generate strict <3900-char goal-orchestrator prompt for a saga and lock via /goal.

NomaDamas/AutoRAG-Research

Command Claude Code

Design ingestion strategy with mandatory human review. Use after dataset inspection phase.

NomaDamas/AutoRAG-Research

Command Claude Code

Orchestrate full pipeline implementation workflow from paper to validated code. Use when implementing a new retrieval or generation pipeline from a research paper.

RightNow-AI/AutoMegaKernel

Command Claude Code

One-shot compile + verify a model into a CUDA megakernel via amk compile on $ARGUMENTS (model [gpu]).

RightNow-AI/AutoMegaKernel

Command Claude Code

Drive an interactive AMK propose -> eval -> keep/revert megakernel schedule session on $ARGUMENTS (model [gpu]).

avabbbb/Flovart

Command

Use these registered helpers without exposing provider keys.

avabbbb/Flovart

Command

Provider keys and model preferences stay in the Flovart browser UI, which is the single source of truth. Provider commands use the browser bridge and must never expose keys. Keep the Flovart browser tab open while running them.

S1LV4/th0th

Command

Semantic search in an indexed project (th0th).