building-agent-systems
100 / 100 · Low risk
Fine to try.
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge). Use when building AI agents, designing RAG pipelines, orchestrating multi-agent workflows, hardening LLM apps, or writing prompts.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'building-agent-systems' ] || [ -L ~/.agents/skills/'building-agent-systems' ]; then echo 'A skill folder named building-agent-systems already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/telagod/code-abyss' "$d" && git -C "$d" checkout --quiet '2544577cf03a67522466450000731e52c64a5184' -- 'skills/building-agent-systems' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/building-agent-systems' ~/.agents/skills/'building-agent-systems' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'building-agent-systems' ~/.claude/skills/'building-agent-systems' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/telagod/code-abyss/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 2544577 | 100 |