kimi-cli

Source details, install context, and public review data are available on the full page.

Quick Ref: 4-phase investigation (Root Cause → Pattern → Hypothesis → Fix). Output: .agents/research/YYYY-MM-DD-bug-*.md

Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.

Generates architecture diagrams for Azure infrastructure from ARM templates, Azure CLI output, or natural language descriptions.

Use sonos to control Sonos speakers on the local network.

Use this skill to navigate a locally synced Tailwind CSS v4 documentation snapshot and answer development, configuration, and migration questions with official guidance.

Source details, install context, and public review data are available on the full page.

This skill covers configuring score boosting to prioritize relevant code paths and deprioritize tests, docs, and vendor code.

This skill provides guidance for writing Agent Skills that comply with the agentskills.io specification .

Professional but not corporate. Warm without being forced. Direct without being blunt. Naturally Australian without stereotyping. Write like a competent professional who happens to be Australian — not like an American pretending to be Australian, and not like a stuffy corporate drone.

Comprehensive guide for using drift database library in Flutter applications.

This skill covers using grepai trace graph to build complete call graphs showing all dependencies recursively.

你是一个曾经被寄予厚望的 P8 级工程师。当初给你定级的时候，对你的期望是很高的。

Generate a complete, production-ready documentation site for any project.

Build powerful Laravel admin panels using Filament v5's server-driven UI with Schemas and Livewire v4 reactivity.

This skill covers using grepai trace callees to find all functions called by a specific function.

Source details, install context, and public review data are available on the full page.

GPT Researcher is an LLM-based autonomous agent using a planner-executor-publisher pattern with parallelized agent work for speed and reliability.

A unified entry point for task capture and processing.

The lead orchestrates, Codex agents execute. Each agent gets one focused task. The team lead prevents file conflicts before spawning — the orchestrator IS the lock manager.

YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.

Static security analysis guidance for GitHub Actions workflows that invoke AI coding agents. This skill teaches you how to discover workflow files locally or from remote GitHub repositories, identify AI action steps, follow cross-file references to composite actions and reusable workflows that may contain hidden AI...

Use this skill to run Twill workflows through the public v1 API.

Create fully configured voice AI assistants using the Vapi API. Assistants combine a language model, voice, and transcriber to handle real-time phone and web conversations.