Create, Evaluate, and Connect AI Skills
Python ai-agentsai-skillsartificial-intelligenceknowledge-graphlarge-language-modelsnatural-language-processingopenkgskillnetskills
update client and readme
LiamLYYY3ad9e484a18d
diff --git a/skillnet-ai/README.md b/skillnet-ai/README.mdindex 52a2d36..6fd0d7c 100644--- a/skillnet-ai/README.md+++ b/skillnet-ai/README.md@@ -29,101 +29,89 @@ pip install skillnet-ai## 🛠 Usage (Python SDK)-### 1. Search for Skills+The `SkillNetClient` provides a unified interface for searching, downloading, creating, and evaluating skills.-You can search for skills using keywords or natural language (AI Search).+### 1. Initialize the Client++Initialize the client with your credentials. You can also set `API_KEY` and `GITHUB_TOKEN` in your environment variables.```python-from skillnet_ai import SkillNetSearcher+from skillnet_ai import SkillNetClient-searcher = SkillNetSearcher()+# Initialize with optional credentials+client = SkillNetClient(+ api_key="sk-...", # Required for AI Search, Creation, and Evaluation+ base_url="...", # Optional custom LLM base URL+ github_token="ghp-..." # Optional, for private repos or higher rate limits+)+```-# 1. Standard Keyword Search-results = searcher.search(q="pdf")+### 2. Search for Skills+Perform keyword-based or semantic AI searches to find skills.-# 2. Semantic Search-results = searcher.search(q="Help me analyze financial PDF reports", mode="vector")+```python+# 1. Standard Keyword Search+results = client.search(q="pdf tool")-top_skill = results[0]-print(f"Top Skill: {top_skill.skill_name} (Stars: {top_skill.stars})")-print(f"Description: {top_skill.skill_description}")-print(f"URL: {skill.skill_url}")+# 2. Semantic AI Search (requires api_key)+results = client.search(q="Help me analyze financial PDF reports", mode="vector")+if results:+ top_skill = results[0]+ print(f"Found: {top_skill.skill_name} (Stars: {top_skill.stars})")+ print(f"URL: {top_skill.skill_url}")```-### 2. Install a Skill--Once you have a skill's URL (usually from the search results), you can download and install it into your agent's workspace.+### 3. Install a Skill+Download and install a skill directly from a URL (e.g., from search results) into your local workspace.```python-from skillnet_ai import SkillDownloader-skill_url = "https://github.com/anthropics/skills/tree/main/skills/skill-creator"-# Downloads and extracts the skill to target_dir-skilldownloader = SkillDownloader()-local_path = skilldownloader.download(skill_url, target_dir="./my_agent_skills")--if local_path:+try:+ # Downloads to ./my_agent_skills+ local_path = client.download(url=skill_url, target_dir="./my_agent_skills")print(f"Skill successfully installed at: {local_path}")+except Exception as e:+ print(f"Download failed: {e}")```-### 3. Create a Skill from Trajectory--Turn raw conversation logs or execution traces into a polished Skill Package (`SKILL.md`, scripts, etc.).--> **Note:** This feature requires an LLM API Key.+### 4. Create a Skill from Trajectory+Turn conversation logs or execution traces into a polished Skill Package (SKILL.md, scripts, etc.).```python-import os-from skillnet_ai import SkillCreator--# 1. Prepare your trajectory (e.g., a conversation log)+# 1. Prepare your trajectory (e.g., a conversation log string)trajectory_log = """User: I need to rename all .jpg files in this folder to .png.Agent: I will write a python script to iterate through the folder...Agent: Script executed. Renamed 5 files."""-# Set your API key and url-api_key="sk-...", # Your API Key-base_url="xxxxxx", # Optional. Useful if using a proxy or compatible API--# 2. Initialize Creator-creator = SkillCreator(api_key=api_key, base_url=base_url, model="gpt-4o")--# 3. Create Skills-output_dir = "./created_skills"-created_paths = creator.create_from_trajectory(trajectory_log, output_dir=output_dir)+# 2. Generate Skills+# Returns a list of paths to the generated skill folders+created_paths = client.create(+ trajectory_content=trajectory_log,+ output_dir="./created_skills",+ model="gpt-4o"+)-print(f"Created {len(created_paths)} new skills in {output_dir}")+print(f"Created {len(created_paths)} new skills.")+for path in created_paths:+ print(f"- {path}")```-### 4. Skill Evaluation--Assess the Safety, Completeness, Excutability, Modifiability and Cost-Aware of a skill before using it. This tool generates a complete evaluation based on the skill's code and documentation.--> **Note:** This feature requires an LLM API Key.+### 5. Skill Evaluation+Assess the Safety, Completeness, Executability, and Modifiability of a skill. Supports both remote GitHub URLs and local directories.```python-import os-from skillnet_ai import SkillEvaluator, EvaluatorConfig--# 1. Configure the Evaluator-config = EvaluatorConfig(- api_key="sk-...", # Your API Key- base_url="xxxxxx", # Optional. Useful if using a proxy or compatible API- model="gpt-4o" # Model to use for evaluation-)-evaluator = SkillEvaluator(config)--# 2. Evaluate a Skill (from URL or Local Path)-skill_url = "https://github.com/microsoft/autogen/tree/main/samples/tools/web_search"+# target_skill = "./my_skills/web_search"+target_skill = "https://github.com/microsoft/autogen/tree/main/samples/tools/web_search"-# You can also use evaluator.evaluate_from_path("./my_skills/web_search")-result = evaluator.evaluate_from_url(skill_url)+# Evaluates the skill using the client's API key+result = client.evaluate(target=target_skill)-print(f"Evaluation: {result}")+# Display results+print(f"Evaluation Result: {result}")```---@@ -157,7 +145,7 @@ skillnet search "visualization" --category "Data" --sort-by stars --limit 10--min-stars: Filter results by minimum star rating.-### 2. Download Skills (download)+### 2. Install Skills (download)Download and install a skill directly from a GitHub repository subdirectory.@@ -186,7 +174,7 @@ skillnet create ./logs/trajectory.txt --output-dir ./generated_skillsskillnet create ./logs/chat_history.txt --model gpt-4o```-### Evaluate Skills (evaluate)+### 4. Evaluate Skills (evaluate)Generate a comprehensive quality report (Safety, Completeness, Executability, Modifiability, Cost Awareness) for a skill.Requirement: Ensure API_KEY is set in your environment variables.diff --git a/skillnet-ai/src/skillnet_ai/__init__.py b/skillnet-ai/src/skillnet_ai/__init__.pyindex bfff398..bd4d9e6 100644--- a/skillnet-ai/src/skillnet_ai/__init__.py+++ b/skillnet-ai/src/skillnet_ai/__init__.py@@ -5,12 +5,14 @@ SkillNet AI SDKA client library for searching, downloading, creating and evaluating AI Agent Skills."""+from skillnet_ai.client import SkillNetClientfrom skillnet_ai.creator import SkillCreatorfrom skillnet_ai.downloader import SkillDownloaderfrom skillnet_ai.evaluator import SkillEvaluator, EvaluatorConfigfrom skillnet_ai.searcher import SkillNetSearcher__all__ = [+ "SkillNetClient","SkillCreator","SkillDownloader","SkillEvaluator",diff --git a/skillnet-ai/src/skillnet_ai/client.py b/skillnet-ai/src/skillnet_ai/client.pynew file mode 100644index 0000000..423b458--- /dev/null+++ b/skillnet-ai/src/skillnet_ai/client.py@@ -0,0 +1,213 @@+import os+from typing import List, Optional, Dict, Any, Union+from pathlib import Path++from skillnet_ai.creator import SkillCreator+from skillnet_ai.downloader import SkillDownloader+from skillnet_ai.evaluator import SkillEvaluator, EvaluatorConfig+from skillnet_ai.searcher import SkillNetSearcher++class SkillNetError(Exception):+ """Custom exception class for SkillNet Client errors."""+ pass++class SkillNetClient:+ """+ A Python SDK client for interacting with SkillNet AI services.++ This client aggregates Search, Download, Creation, and Evaluation functionalities.+ """++ def __init__(+ self,+ api_key: Optional[str] = None,+ base_url: Optional[str] = None,+ github_token: Optional[str] = None+ ):+ """+ Initialize the SkillNet Client.++ Args:+ api_key: OpenAI/SkillNet API Key. Defaults to env var API_KEY.+ base_url: Base URL for the LLM API. Defaults to env var BASE_URL or OpenAI default.+ github_token: GitHub token for downloading private skills or avoiding rate limits.+ Defaults to env var GITHUB_TOKEN.+ """+ self.api_key = api_key or os.getenv("API_KEY")+ self.base_url = base_url or os.getenv("BASE_URL")+ self.github_token = github_token or os.getenv("GITHUB_TOKEN")+++ def search(+ self,+ q: str,+ mode: str = "keyword",+ category: Optional[str] = None,+ limit: int = 20,+ page: int = 1,+ min_stars: int = 0,+ sort_by: str = "stars",+ threshold: float = 0.8+ ) -> List[Any]:+ """+ Search for skills on SkillNet.++ Args:+ q: The search query.+ mode: 'keyword' or 'vector'.+ category: Filter by category.+ limit: Max results.+ page: Page number (keyword mode only).+ min_stars: Filter by stars (keyword mode only).+ sort_by: 'stars' or 'recent' (keyword mode only).+ threshold: Similarity threshold (vector mode only).++ Returns:+ List[SkillModel]: A list of skill objects found.+ """+ try:+ searcher = SkillNetSearcher()+ results = searcher.search(+ q=q,+ mode=mode,+ category=category,+ limit=limit,+ page=page,+ min_stars=min_stars,+ sort_by=sort_by,+ threshold=threshold+ )+ return results+ except Exception as e:+ raise SkillNetError(f"Search failed: {str(e)}") from e++ def download(+ self,+ url: str,+ target_dir: str = ".",+ token: Optional[str] = None+ ) -> str:+ """+ Download a skill from a GitHub URL.++ Args:+ url: The GitHub URL of the specific skill folder.+ target_dir: Local directory to install into.+ token: Optional override for GitHub token.++ Returns:+ str: The absolute path to the installed skill folder.++ Raises:+ SkillNetError: If download fails.+ """+ # Use instance token if specific token not provided+ use_token = token if token else self.github_token+ downloader = SkillDownloader(api_token=use_token)++ try:+ installed_path = downloader.download(folder_url=url, target_dir=target_dir)+ if not installed_path:+ raise SkillNetError("Download returned None. Check URL validity or permissions.")+ return os.path.abspath(installed_path)+ except Exception as e:+ raise SkillNetError(f"Download failed: {str(e)}") from e++ def create(+ self,+ trajectory_content: str,+ output_dir: Union[str, Path] = "./generated_skills",+ model: str = "gpt-4o"+ ) -> List[str]:+ """+ Generate executable skills from a trajectory log.++ Args:+ trajectory_content: The text content of the execution log/trajectory.+ output_dir: Directory where new skills will be saved.+ model: The LLM model to use.++ Returns:+ List[str]: A list of paths to the generated skill folders.+ """+ if not self.api_key:+ raise SkillNetError("API_KEY is required for skill creation.")++ if not trajectory_content.strip():+ raise SkillNetError("Trajectory content is empty.")++ try:+ creator = SkillCreator(+ api_key=self.api_key,+ base_url=self.base_url,+ model=model+ )++ created_paths = creator.create_from_trajectory(+ trajectory=trajectory_content,+ output_dir=str(output_dir)+ )++ return created_paths if created_paths else []+ except Exception as e:+ raise SkillNetError(f"Creation failed: {str(e)}") from e++ def evaluate(+ self,+ target: str,+ name: Optional[str] = None,+ category: Optional[str] = None,+ description: Optional[str] = None,+ model: str = "gpt-4o",+ max_workers: int = 5+ ) -> Dict[str, Any]:+ """+ Evaluate a skill (local path or URL).++ Args:+ target: Local folder path OR GitHub URL.+ name: Override skill name.+ category: Override skill category.+ description: Override skill description.+ model: LLM model for evaluation.+ max_workers: Concurrency limit.++ Returns:+ Dict[str, Any]: The evaluation report dictionary.+ """+ if not self.api_key:+ raise SkillNetError("API_KEY is required for evaluation.")++ config = EvaluatorConfig(+ api_key=self.api_key,+ base_url=self.base_url,+ model=model,+ max_workers=max_workers+ )+ evaluator = SkillEvaluator(config)++ try:+ is_url = target.startswith("http://") or target.startswith("https://")++ if is_url:+ result = evaluator.evaluate_from_url(+ url=target,+ name=name,+ category=category,+ description=description+ )+ else:+ result = evaluator.evaluate_from_path(+ path=target,+ name=name,+ category=category,+ description=description+ )++ if "error" in result:+ raise SkillNetError(f"Evaluation logic returned error: {result['error']}")++ return result++ except Exception as e:+ raise SkillNetError(f"Evaluation process failed: {str(e)}") from e\ No newline at end of file