DraconDev/respec-spec-reconciler
respec — spec reconciler for AI coding agents. Reads SPEC.md, runs verify-spec.sh, loops until all invariants pass. Alternative to prompt-driven completion.
respec — spec reconciler for AI coding agents. Reads SPEC.md, runs verify-spec.sh, loops until all invariants pass. Alternative to prompt-driven completion.
npx skills add DraconDev/respec-spec-reconcilerrespec — spec reconciler for AI coding agents. Reads SPEC.md, runs verify-spec.sh, loops until all invariants pass. Alternative to prompt-driven completion.
Safe Python Netmiko patterns for read-only collection, bounded batch SSH, TextFSM parsing, guarded config changes, timeouts, and network automation error handling.
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
Recently updated agent-skill-related GitHub repository: agentic-cookbook/agenticdevteam.
A powerful knowledge base management and work-study system. It supports a range of advanced AI features, including multi-role conversations, autonomous multi-turn KB search by Agents, browser automation, session compression, MCP, SKILLS, and bots. The project adopts a decoupled front-end and back-end architecture
10 specialized AI agents for GitHub Copilot — PM, Architect, DBA, UI Designer, Project Manager, Frontend, .NET, QA, DevOps — forming a structured software delivery team with defined handoffs, gate reviews, and phased workflow. Also supports Claude Code and OpenAI Codex CLI.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.