Unlock the Power of AI Agents: Build Skill-Augmented Agents with SkillNet
Want to build awesome AI agents that can actually *do* things? SkillNet provides a framework for finding, installing, testing, and organizing reusable AI skills. This tutorial will walk you through a SkillNet use case, showing you how to build AI agents for search, evaluation, graph analysis, and even task planning. You'll learn how to leverage SkillNet to create some seriously advanced AI agents.
Setting Up Your SkillNet Environment for AI Agent Development
Alright, first things first: let's get a SkillNet client set up with SDK and REST fallback. Why? Well, this makes sure the tutorial still works, even if the SDK throws a fit! We'll also configure API keys, model settings, GitHub stuff, and working directories to keep your AI agent project nice and tidy.
Here's the code to get you started:
import sys, subprocess def _pip(*pkgs): subprocess.run([sys.executable, "-m", "pip", "install", "-q", *pkgs], check=False) print("Installing dependencies (skillnet-ai, networkx, matplotlib, requests)...") _pip("skillnet-ai", "networkx", "matplotlib", "requests") import os, re, json, textwrap, pathlib, traceback import requests API_KEY = os.environ.get("API_KEY", "") BASE_URL = os.environ.get("BASE_URL", "https://api.openai.com/v1") MODEL = os.environ.get("SKILLNET_MODEL", "gpt-4o") GITHUB_TOKEN = os.environ.get("GITHUB_TOKEN", "") GITHUB_MIRROR = os.environ.get("GITHUB_MIRROR", "") if not API_KEY: try: from google.colab import userdata API_KEY = userdata.get("API_KEY") or "" except Exception: pass REST_BASE = "http://api-skillnet.openkg.cn/v1" WORKDIR = pathlib.Path("./skillnet_demo"); WORKDIR.mkdir(exist_ok=True) SKILLS_DIR = WORKDIR / "my_skills"; SKILLS_DIR.mkdir(exist_ok=True) def banner(title): line = "=" * 78 print(f"\n{line}\n {title}\n{line}")This little snippet installs the necessary Python packages (skillnet-ai, networkx, matplotlib, and requests) and sets up the environment variables SkillNet needs. Plus, it defines a banner function to keep the output organized. But what's *really* going on here?
Searching for AI Skills: Keyword Search vs. Semantic Search
SkillNet's core feature is its ability to find relevant AI skills. But how does it stack up against traditional methods for AI skill discovery? Let's compare keyword search with semantic search to see how AI skills can be discovered based on different task requirements. We'll explore the nuances of AI skill search and which method delivers more relevant results.
banner("1) Initialize SkillNet client (SDK with REST fallback)") USE_SDK = False client = None try: from skillnet_ai import SkillNetClient client = SkillNetClient( api_key=API_KEY or None, base_url=BASE_URL, github_token=GITHUB_TOKEN or None, ) USE_SDK = True print("SDK loaded: skillnet_ai.SkillNetClient") except Exception as e: print(f"SDK unavailable ({e!r}); using REST fallback for search/download.") def _norm(item): if isinstance(item, dict): g = item.get else: g = lambda k, d=None: getattr(item, k, d) return { "skill_name": g("skill_name") or g("name") or "?", "skill_description": g("skill_description") or g("description") or "", "author": g("author") or "", "stars": g("stars") or 0, "skill_url": g("skill_url") or g("url") or "", "category": g("category") or "", } def search(q, mode="keyword", limit=5, min_stars=0, sort_by="stars", threshold=0.8): if USE_SDK: try: kw = dict(q=q, limit=limit, mode=mode) if mode == "keyword": kw.update(min_stars=min_stars, sort_by=sort_by) else: kw.update(threshold=threshold) res = client.search(**kw) return [_norm(x) for x in (res or [])] except Exception as e: print(f" [SDK search failed -> REST] {e!r}") params = {"q": q, "mode": mode, "limit": limit} if mode == "keyword": params.update(min_stars=min_stars, sort_by=sort_by) else: params.update(threshold=threshold) try: r = requests.get(f"{REST_BASE}/search", params=params, timeout=30) r.raise_for_status() return [_norm(x) for x in r.json().get("data", [])] except Exception as e: print(f" [REST search failed] {e!r}") return [] def show_results(results, title=""): if title: print(f"\n-- {title} --") if not results: print(" (no results / endpoint unreachable)") return for i, s in enumerate(results, 1): desc = textwrap.shorten(s["skill_description"], 70, placeholder="...") print(f" {i}. {s['skill_name']: