Explore research reports on Claude Code v2.1.88 covering architecture, agent behavior, permissions, prompts, MCP, and context management
npx skills add jalehvesical21/claude-code-decompiledExplore research reports on Claude Code v2.1.88 covering architecture, agent behavior, permissions, prompts, MCP, and context management
Source: https://github.com/jalehvesical21/claude-code-decompiled
Discovered during the daily awesomeskills.dev agent-skill hunt.
MCP server exposing the City of València open data portal (CKAN + ArcGIS) as live tools to AI agents. Web demo at valencia-mcp.vercel.app.
The 7 Laws of AI Agent Discipline for Claude Code. Stops your agent from skipping research, claiming 'done' without verifying, and repeating yesterday's mistakes. 14 enforcement skills, gating hooks, the Mulahazah instinct engine with friction-harvest, and a GitHub Action linter. Beginner: /plugin install. Expert: adds MCP tools.
集中管理的 AI Agent Skills 仓库
🧠 Conduct advanced research using a multi-agent framework that leverages OpenAI and Google Gemini for citation-backed insights.
Automate Kaggle tasks via Rube MCP (Composio). Always search tools first for current schemas.
Korra — персональный AI-агент. Self-hosted на твоём VPS. BYOK (Anthropic / OpenRouter / OpenAI). Telegram + 15 платформ, multimodal, full skill system. Fork Hermes Agent от Nous Research.