Commands

dbhosbu-dotcom/renwei

Command Claude Code

A command for removing an artificial-sounding style from a Chinese manuscript, based on an existing diagnostic report.

PranitMohnot/repo-learner-suite

Command Claude Code

Entry point for the repo-learner skill suite.

ch015/code-pentester

Command Claude Code

A design-stage security review for product requirement documents and other planning documents; a PRD is a document describing what a product should do.

AleksandarBisevac/claude-plugins

Command Claude Code

Perform a code-review.

mtrdesign/whygraph

Command Claude Code

Plan a non-trivial code change with WhyGraph rationale + CodeGraph symbols. Asks scoping questions if needed, then dispatches to the planner subagent (which optionally fans out to 3 researchers + a synthesizer) to produce a step-by-step plan.

xingchengxu/OpenExpertise

Command Claude Code

One-shot LLM-authored OpenExpertise SOP. Drives oe ultra and reports the result.

XPOZpublic/xpoz-cursor-plugin

Command Claude Code

Reference docs for Xpoz query syntax, pagination, field selection, platform tools, and authentication. Usage: /xpoz-best-practices.

jazz-max/ruflo-hub

Command Claude Code

Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

dsswift/ion

Command Claude Code needs its repo

Context-aware alignment. When in plan mode, it reviews the active plan. Otherwise, it reviews all branch changes against Ion quality gates and principles, implements the fixes and commits them after operator approval.

dhruvil009/QuotaSentry

Command Claude Code needs its repo

Check, configure, start, or install the local Codex quota guard.

craigcossairt/trellis

Command Claude Code

Set up parallel agent sessions on independent tasks via git worktrees. Use when asked to '/worktree', 'git worktree', 'parallel branches', 'isolated branch workspace', 'work on two things at once'.

SiluPanda/codex-agent-loop

Command Claude CodeCodex

Run a bounded, Claude-Code-style coding loop with onboarding helpers like --doctor, --demo, and shorthand budgets like 10m.

elbalen/skopus

Command Claude Code

Generate benchmark scenarios from your real corrections for the Correction-Persistence dataset.

crcresearch/llm-wiki-memory-template

Command Claude Code

Consult federated agent(s) via the agent-comms ask primitive (clone-and-invoke).

hassanbazzi/dreamapp

Command Claude CodeCursor

I've got an idea I want to talk through with you. I'd like you to help me turn it into a fully formed design and spec (and eventually an implementation plan) Check out the current state of the project in our working directory to understand where we're starting off, then ask me questions, one at a time, to help refine…

hahaxiang27/FlowHarness

Command Claude Code

A task-execution command that completes the next or a selected development task and runs two levels of checks. TDD means writing or using tests as part of development.

bienhoang/refactoring-kit

Command Claude Code

⚡⚡ Systematic code refactoring [INTELLIGENT ROUTING].

yasuhiro-y/figma-plugin-by-vibe-coding

Command Claude Code

Generate a new Figma plugin feature with full type safety and shadcn/ui integration.

AliYmn/claude-structured

Command Claude Code

You are configuring this project to use the claude-structured template. Your goal is to understand the project and fill in all placeholder files with accurate, project-specific information.

rhaml-23/prompt

Command Claude Code

Compliance Agent System — Slash Commands.

P451M/Arch4

Command Claude Code

Show this repository's rendered Arch4 architecture map widget.

OpenLabor/openlabor

Command Claude Code

Command "x-strategy" from OpenLabor/openlabor, covering how to execute x/twitter actions, available tools, publishing, engagement and bookmarks.

renanflustosa/octo-cluster

Command Claude CodeCursor

Transform the user message into a professional, precise Cursor-ready prompt. Never execute the requested task. Output only the optimized prompt package.

micsapp/micstec-skills

Command Claude Code

You are evaluating a repository intended for use in or alongside Claude Code, where certain features (such as hooks, commands, scripts, or automation) may execute implicitly or with elevated trust once enabled by a user.