CLI Tools
Command line utilities
replay-playwright
by replayio
Set up and run Playwright tests with Replay Browser to record test executions for debugging and performance analysis.
agent-browser
by gentamura
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
clrun
by Tablesearch
Run and control interactive CLI sessions for AI agents. Handles TUI prompts (select lists, checkboxes, confirms), persistent shell state, and long-running processes. Use when you need to execute terminal commands, respond to interactive prompts, navigate scaffolding wizards like create-vue or create-vite, or manage dev servers.
code-change-verification
by aiagentskills
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents JS monorepo.
smartthings-cli
by 401Unauthorized
Use the SmartThings CLI to manage SmartApps, Edge drivers, devices, locations, capabilities, and automations, based on the official SmartThings CLI repository and documentation.
react-triage
by basst85
Maintain and extend the React Triage Bun CLI that scans React/Next.js projects with Oxlint, custom checks, Vercel best-practice rules, and security auditing. Use this skill when modifying scan logic, adding diagnostics, adjusting scoring, updating CLI/report output, or debugging Bun-based project analysis behavior.
ioredis
by yusenthebot
A robust, performance-focused and full-featured Redis client for Node.js.. Use when: building interactive command-line tools; styled terminal output; progress indicators and spinners. NOT for: web browser UI rendering; server-side HTML generation.
@aws-sdk/client-s3
by yusenthebot
AWS SDK for JavaScript S3 Client for Node.js, Browser and React Native. Use when: yarn add @aws-sdk/client-s3; Initiate client with configuration (e.g. credentials, region); Initiate command with input parameters. NOT for: web browser UI rendering; server-side HTML generation.
hyperstack
by usehyperstack
Build with Hyperstack, real-time Solana data streaming. Covers consuming existing streams and building custom stacks. Use when the user mentions Hyperstack, real-time Solana data, on-chain streaming, ORE mining, or wants to consume/build data stacks.
openclaw-log-report
by junlincobo
Parse OpenClaw session JSONL logs and upload structured telemetry to Langfuse via the Cobo Agentic Wallet TelemetryAPI. Zero external dependencies — only requires Python 3 and a valid caw installation (API key auto-detected). Use when: user wants to analyze an OpenClaw session, upload session telemetry, view session traces in Langfuse, or debug OpenClaw agent behavior.
cross-platform-safety
by janjaszczak
Ensure commands and paths are safe across Windows + WSL + Docker (PowerShell vs bash, path translation, permissions). Use when instructions touch shell, filesystem, Docker, or OS-specific behavior.
pipes-deploy-clickhouse-local
by subsquid-labs
Deploys blockchain indexers to local ClickHouse (Docker) with validation and MCP setup for testing and development.
pokemon-data-fetcher
by kehwar
Fetches Pokemon data from the PokeAPI (pokeapi.co) and organizes it by generation. Use this skill when you need to retrieve Pokemon information, list Pokemon by generation, or collect Pokemon data in JSON format.
pr-screenshots
by nullswan
Capture before/after screenshots for pull requests to document visual changes. Supports both agent-browser CLI and Playwright Python approaches. Use when creating PRs with UI changes, comparing visual states between branches, documenting frontend changes for code review, or generating visual diff reports.
find
by jyasuu
File search and manipulation utility for locating files by name, type, size, permissions, and time.
openclaw-wa-bridge
by andrepaim
"WhatsApp bridge for OpenClaw — send/receive messages, search chats, manage contacts via REST API + CLI. Incoming messages trigger OpenClaw webhooks for real-time agent responses. Use when the user wants to send WhatsApp messages, check WhatsApp chats, search message history, or manage WhatsApp monitoring."
roundcube-webmail
by Daisuke134
Reads and summarizes emails from Roundcube webmail with SAML/TOTP authentication using Playwright. Use when checking webmail, reading university email, automating Roundcube login, or setting up daily email digest via Slack/OpenClaw cron. macOS only.
git-workflow
by leobrival
Complete Git development workflow toolkit. Covers commit, push, PR creation, merge to main, branch cleanup, debug, PR comment resolution, issue-based worktree creation, task execution, and worktree hooks configuration. Use when users need any Git-based development workflow or worktree isolation setup.
fd-search
by wizact
"REQUIRED for file searches. Use instead of bash find - faster, simpler syntax, regex support, respects .gitignore. Syntax: fd [pattern] [path]. Common: fd -e ext, fd -t f/d, fd -g '*.txt', fd -S +100m, fd --changed-within 1day"
opentofu
by jyasuu
Open-source Terraform alternative for infrastructure provisioning with installation and workflow commands.
reload
by gyumaruya
Restart the current Claude Code session from within tmux. Writes a handoff file, launches a restart script in a new tmux window, which stops the current Claude and resumes with --resume. Triggers: /reload, "reload", "restart", "reboot", "再起動"
skills-scout
by servaltullius
Use when a user wants you to discover and optionally install new agent skills for a task, and you must get explicit consent before any global install into Codex.
Project Init Skill
by yousufjoyian
Use session-save to maintain context
webapp-testing
by TheWatcher01
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.