Productivity

Bounded agent-facing skill bundles for coding agents and humans: reviewable execution workflows composed from reusable techniques.

A self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.

Pi skill for pure ANSI C99 projects with memory arena, containerized builds, Valgrind, and static analysis.

Codex skills for Apple dev workflows: Xcode MCP-first execution, automatic xcodebuild/xcrun/SwiftPM fallback, swiftly+toolchain guidance, and Dash local-docset docs.

Production-ready development workflows for Claude Code, powered by specialized AI agents.

🚀 Empower AI Agents with structured skills and workflows for tasks like automated news reporting and data analysis.

📚 Teach Product Managers to use Claude Code for efficient task management and AI-powered workflow automation.

We’re build a swarm of agents for all data tasks. That anyone can use for free, open-source community version.

vigilante is a local control plane for autonomous software delivery. It watches repositories, selects eligible work items, prepares isolated git worktrees, launches a supported coding-agent CLI, and keeps the issue tracker updated while the work moves toward a pull request.

Agent skill for decomposing requests and dispatching background agents in parallel

A read-only OpenClaw review skill for auditing runtime behavior, rule drift, memory hygiene, interaction quality, and workflow design.

Claude Code Skill: Bootstrap structured task management with RIPER-7 lifecycle, risk grading, session handoff, and daily reporting for any new project. Author: junnan.cheng

Portable Agent Skill for semantic diff, review prioritization, and merge workflows

Intelligent context management for OpenClaw agents - prevents session bloat with auto-flush and manual /flush commands

jasontsaicc/notebooklm-studio-skill

Shared memory and identity for your AI agents — Git-native, self-hosted, no vendor lock-in

Windows-first guardrails for AI agents and terminal-capable assistants, with reusable patterns for safer PowerShell and CLI execution

AI-powered earnings calendar tracker for US, HK, and CN markets with sector filtering

Universal browser automation skill for AI agents: navigate, extract, fill forms, handle pagination, and turn repeated web workflows into reusable site recipes.

Guides agents through creating, validating, and optimizing Agent Skills (SKILL.md files) from user requests.

Seven biologically-inspired memory systems for OpenClaw agents: prospective memory, metamemory, procedures, knowledge gaps, consolidation, and reflection.

A collection of Agent Skills for MATLAB development. Skills are specialized instruction sets that extend a coding agent's capabilities for specific tasks, automatically activating when needed.

OpenClaw skill for Telegram self-heal and ClawTeam-to-Telegram auto-reporting on macOS hosts.

Four general-purpose AI agent skills for structured thinking and reliable execution