20 skills found
bytedance / UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
parcadei / Continuous-Claude-v3Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
code-yeongyu / lazycodexThe one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
universal-tool-calling-protocol / code-mode🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
kromahlusenii-ops / ham(HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to directories.
ViryaZheng / promptly-promptClaude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.
entropy-data / dataproduct-mcpA Model Context Protocol (MCP) server for discovering data products and requesting access in Data Mesh Manager, and executing queries on the data platform to access business data.
seuros / mcp_rails_templateA minimal Rails API template for creating MCP (Model Context Protocol) servers with robust tool execution capabilities and examples.
Coooolfan / onlyboxesCode Execution Sandbox Platform Solution for Individuals and Small Teams with MCP
peakmojo / agentic-mcp-clientA standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.
JimmySadek / strategic-partnerEvery other tool executes. This one decides what to execute. Chief of Staff skill for Claude Code.
andyzengmath / quantum-loopSpec-driven autonomous development loop for Claude Code. Combines structured PRD generation, dependency DAG execution, two-stage review gates, and Iron Law verification.
zeuikli / claude-pilot-suiteClaude Code execution playbook with 3 pilot modes: cost-first (Haiku), quality-first (Sonnet), ceiling-elevation (Opus). Quantitative escalation gates.
dpajin / mcp-server-junosMCP server for Juniper devices running Junos. Tools for executing operational commands and changing device configuration
idletoaster / ssh-mcp-serverSSH MCP Server - Connect to remote servers via SSH and execute commands through Model Context Protocol
navox-labs / qaSenior QA Engineer that creates test plans and executes comprehensive testing including auth flows and edge cases. Trigger on testing, QA, test plan, regression, bug report, or auth flow testing.
reichaves / gerar-dossieGera o dossiê PDF final a partir de um arquivo findings-consolidated.json. Usa a sub-skill generate-dossier-pdf com template ReportLab. Requer revisão humana dos achados antes de executar.
bben15600-sys / skill-routerYou are a Skill Navigator. You take the user's free-form intent in natural language and route it to the most appropriate installed skill — printing a ranked list with confidence scores and explicit reasoning to chat, never executing the skill itself until the user confirms.
chalbert / nextShortcut for /backlog — pick & work the next backlog item (routes to the next-backlog-item skill)
SassaGold / rollout-vegvisirExecute the Vegvísir rollout. Everything is pre-staged and verified (349 tests pass on the branch); your job is to ship it in order, verifying each step before the next. Report progress as you go. If any step fails, stop and explain — do not improvise around failures.
