Commands

jwynia/agent-skills

Command Claude Code

Merge approved PR, cleanup worktree, and update task status for Gitea.

echoVic/blade-code

Command Claude Code

A command for adding JSDoc comments to TypeScript and JavaScript code. JSDoc is a standard way to describe functions, classes, interfaces, parameters, return values, errors, and examples inside code.

KimYx0207/Kim_Service

Command Claude Code

A workflow that turns a UI screenshot or design into frontend code by combining image analysis, technical planning, code generation, and review.

AmaniDawn/DGame

Command Claude Code

Commands to drive Multiplayer Play Mode (MPPM) Play Mode Scenarios — the main Editor plus one or more virtual player (clone) Editors — and to discover those instances so you can drive each one.

OpenHands/extensions

Command Claude Code

Create a new OpenHands automation with cron scheduling.

duolahypercho/gauntlet-loop

Command Claude Code

GAME skill — pure Gauntlet aim prompt; build a game vs a named reference until the human stops it.

coleam00/dark-factory-experiment

Command Claude Code

Holdout-pattern E2E validator. Drives agent-browser against the running DynaChat app to verify that the PR's user-facing behavior actually matches what the linked issue asked for.

agiletec-inc/airis-mcp-gateway

Command Claude Code

Decide whether to use AIRIS MCP, CLI, hooks, or skills.

wednesday-solutions/ai-agent-skills

Command Claude Code

Identify all dead code in the codebase: unused files and unused exports.

aws-samples/sample-autonomous-cloud-coding-agents

Command Claude Code ✓ vendor

Hold the same bar as reviewpr: a Principal AWS Solutions Architect who is direct, specific, justifies every concern with a concrete risk and a file:line, distinguishes blocking issues from nits, and never rubber-stamps. This command orchestrates that single-PR review across a set of PRs — it does not restate the…

webgptorg/promptbook

Command Claude Code

Expect command describes the desired output of the task (after post-processing).

tilework-tech/nori-skillsets

Command Claude Code

Command "docs" from tilework-tech/nori-skillsets, covering noridoc: commands, how it fits into the larger codebase, core implementation and things to know.

fmflurry/settings-opencode

Command Claude Code

Run LLM arena benchmark (classify/draft models against criteria).

sammcj/agentic-coding

Command Claude Code

Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.

huangjia2019/sdd-in-action

Command Claude Code

Create a change and generate all artifacts needed for implementation in one go.

JacksonTai2007/cc-unlock

Command Claude Code needs its repo

Decompile an Android binary file and perform initial triage analysis.

Goldziher/ai-rulez

Command Claude Code

Review current changes for correctness, style, and potential issues.

op7418/m5-paper-buddy

Command Claude Code

First-time setup for the M5 Paper Buddy — checks PlatformIO, installs Python deps, patches mklittlefs, merges hooks, offers to flash firmware + font, starts the daemon.

digipulse-engineering/GAAI-framework

Command Claude Code

Show workspace audit log with filters and optional JSON export.

shawnla90/gtm-coding-agent

Command Claude Code

Run the stale-opportunity check and summarize the result.

kryptobaseddev/cleo

Command Claude Code

Systematic debugging with persistent state across context resets.

JoasASantos/ClaudeAdvancedPlugins

Command Claude Code

You are an expert game developer specializing in browser-based games using Three.js, React Three Fiber, and related web technologies. You create performant, engaging games that run in any modern browser.

nexus-research-lab/nexus

Command Claude Code

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

davidYichengWei/agentic-engineering-framework

Command Claude Code

A command that invokes a manual self-review mode for the coding agent. It reviews errors corrected in the current conversation and produces structured suggestions.