Skip to content

Create, Evaluate, and Connect AI Skills

create notebooks

Norah-Feathertailaa7b36ecd518
diff --git a/skillnet-ai/examples/scientific_workflow_demo.ipynb b/skillnet-ai/examples/scientific_workflow_demo.ipynb
new file mode 100644
index 0000000..ed5cda6
--- /dev/null
+++ b/skillnet-ai/examples/scientific_workflow_demo.ipynb
@@ -0,0 +1,620 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "aca70817",
+ "metadata": {},
+ "source": [
+ "# SkillNet AI Scientist: From Task to Discovery\n",
+ "\n",
+ "This notebook demonstrates the **SkillNet** workflow where an AI Agent autonomously plans and executes a scientific mission.\n",
+ "\n",
+ "## Workflow Lifecycle\n",
+ "1. **Task Definition**: User provides a high-level research goal.\n",
+ "2. **AI Planning**: The Agent decomposes the goal into logical steps.\n",
+ "3. **Skill Discovery**: The Agent searches the **SkillNet** for specialized skills matching each step.\n",
+ "4. **Acquisition & Orchestration**: Skills are downloaded, validated, and composed into a pipeline.\n",
+ "5. **Execution**: The skills interact to generate scientific results.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "bc3bc61a",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "^C\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Install SkillNet-AI package and dependencies\n",
+ "%pip install skillnet-ai\n",
+ "%pip install scanpy requests leidenalg matplotlib seaborn pandas\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d8f7f1be",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "✅ SkillNet AI Package loaded successfully.\n"
+ ]
+ }
+ ],
+ "source": [
+ "import shutil\n",
+ "from IPython.display import display, Markdown\n",
+ "\n",
+ "# Import the actual SkillNet Client\n",
+ "from skillnet_ai import SkillNetClient\n",
+ "\n",
+ "print(\"✅ SkillNet AI Package loaded successfully.\")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6196c679",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import scanpy as sc\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import requests\n",
+ "import json\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import os\n",
+ "\n",
+ "# Configure Scanpy settings for reproducibility\n",
+ "sc.settings.verbosity = 3\n",
+ "sc.settings.set_figure_params(dpi=80, facecolor='white')\n",
+ "\n",
+ "# Set OpenAI API Key for SkillNet Evalaution & Analysis\n",
+ "# Replace with your actual key if available\n",
+ "os.environ[\"API_KEY\"] = \"your-api-key-here\" \n",
+ "os.environ[\"BASE_URL\"] = \"https://api.openai.com/v1\"\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "id": "4ec62f8f",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "🤖 **AI Scientist Agent Initialized**\n",
+ "\n",
+ "📝 **User Mission**: \"Analyze single-cell RNA-seq data to identify potential cancer therapeutic targets, validate them against clinical databases, and write a summary report.\"\n",
+ "\n",
+ "🚀 **SkillNet Orchestration Started**\n",
+ "\n",
+ "--- [Phase 1: Data Processing] ---\n",
+ "🔍 Searching SkillNet for: 'cellxgene'...\n",
+ " ✅ Found Skill: cellxgene-census (Stars: 15976)\n",
+ " ⬇️ Downloading to: ./active_skills_library\\cellxgene-census...\n",
+ " ⚖️ Evaluating Skill Quality...\n",
+ " Safety: Good | Completeness: Good | Executability: Good | Modifiability: Good | Cost_awareness: Good\n",
+ "\n",
+ "--- [Phase 2: Mechanism Analysis] ---\n",
+ "🔍 Searching SkillNet for: 'kegg'...\n",
+ " ✅ Found Skill: kegg-database (Stars: 17598)\n",
+ " ⬇️ Downloading to: ./active_skills_library\\kegg-database...\n",
+ " ⚖️ Evaluating Skill Quality...\n",
+ " Safety: Good | Completeness: Good | Executability: Average | Modifiability: Good | Cost_awareness: Good\n",
+ "\n",
+ "--- [Phase 3: Target Validation] ---\n",
+ "🔍 Searching SkillNet for: 'gget'...\n",
+ " ✅ Found Skill: gget (Stars: 16081)\n",
+ " ⬇️ Downloading to: ./active_skills_library\\gget...\n",
+ " ⚖️ Evaluating Skill Quality...\n",
+ " Safety: Good | Completeness: Good | Executability: Good | Modifiability: Good | Cost_awareness: Good\n",
+ "\n",
+ "--- [Phase 4: Reporting] ---\n",
+ "🔍 Searching SkillNet for: 'scientific writing'...\n",
+ " ✅ Found Skill: citation-management (Stars: 16204)\n",
+ " ⬇️ Downloading to: ./active_skills_library\\citation-management...\n",
+ " ⚖️ Evaluating Skill Quality...\n",
+ " Safety: Average | Completeness: Good | Executability: Average | Modifiability: Good | Cost_awareness: Good\n",
+ "\n",
+ "🔗 **Analyzing Skill Relationships** (SkillNet Analyzer)...\n",
+ " Found 2 dependencies between skills.\n",
+ " - gget --[compose_with]--> kegg-database\n",
+ " - cellxgene-census --[compose_with]--> gget\n",
+ "\n",
+ "✨ **Orchestration Complete**: 4 skills ready for execution.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 1. Initialize SkillNet Agent\n",
+ "client = SkillNetClient()\n",
+ "print(\"🤖 **AI Scientist Agent Initialized**\")\n",
+ "\n",
+ "# 2. Task Definition & AI Planning\n",
+ "USER_MISSION = \"Analyze single-cell RNA-seq data to identify potential cancer therapeutic targets, validate them against clinical databases, and write a summary report.\"\n",
+ "print(f\"\\n📝 **User Mission**: \\\"{USER_MISSION}\\\"\")\n",
+ "\n",
+ "# (Simulated AI Planning Step) - Updated plan to match available/searchable skills\n",
+ "plan = [\n",
+ " {\n",
+ " \"step\": 1, \n",
+ " \"phase\": \"Data Processing\", \n",
+ " \"query\": \"cellxgene\", # Search query for data source\n",
+ " \"expected_skill\": \"cellxgene-census\" \n",
+ " },\n",
+ " {\n",
+ " \"step\": 2, \n",
+ " \"phase\": \"Mechanism Analysis\", \n",
+ " \"query\": \"kegg\", \n",
+ " \"expected_skill\": \"kegg-database\"\n",
+ " },\n",
+ " {\n",
+ " \"step\": 3, \n",
+ " \"phase\": \"Target Validation\", \n",
+ " \"query\": \"gget\", \n",
+ " \"expected_skill\": \"gget\"\n",
+ " },\n",
+ " {\n",
+ " \"step\": 4, \n",
+ " \"phase\": \"Reporting\", \n",
+ " \"query\": \"scientific writing\", \n",
+ " \"expected_skill\": \"citation-management\"\n",
+ " }\n",
+ "]\n",
+ "\n",
+ "# Directory to store our skills\n",
+ "SKILLS_LIB = \"./active_skills_library\"\n",
+ "if os.path.exists(SKILLS_LIB): shutil.rmtree(SKILLS_LIB)\n",
+ "os.makedirs(SKILLS_LIB, exist_ok=True)\n",
+ "\n",
+ "active_skills = {}\n",
+ "\n",
+ "print(\"\\n🚀 **SkillNet Orchestration Started**\")\n",
+ "\n",
+ "for task in plan:\n",
+ " print(f\"\\n--- [Phase {task['step']}: {task['phase']}] ---\")\n",
+ " \n",
+ " # A. SEARCH\n",
+ " print(f\"🔍 Searching SkillNet for: '{task['query']}'...\")\n",
+ " try:\n",
+ " results = client.search(q=task['query'], limit=1)\n",
+ " except Exception as e:\n",
+ " results = []\n",
+ " print(f\" (Search unavailable: {e})\")\n",
+ "\n",
+ " if results:\n",
+ " best_skill = results[0]\n",
+ " print(f\" ✅ Found Skill: {best_skill.skill_name} (Stars: {best_skill.stars})\")\n",
+ " skill_url = best_skill.skill_url\n",
+ " skill_name = best_skill.skill_name\n",
+ " else:\n",
+ " # Fallback if no network or local skill not indexed\n",
+ " print(f\" ⚠️ Skill not found via search. Retrieving from local registry: '{task['expected_skill']}'\")\n",
+ " skill_name = task['expected_skill']\n",
+ " skill_url = None \n",
+ "\n",
+ " # B. DOWNLOAD\n",
+ " target_path = os.path.join(SKILLS_LIB, skill_name)\n",
+ " if skill_url:\n",
+ " print(f\" ⬇️ Downloading to: {target_path}...\")\n",
+ " try:\n",
+ " client.download(url=skill_url, target_dir=SKILLS_LIB)\n",
+ " except Exception as e:\n",
+ " print(f\" (Download failed: {e})\")\n",
+ " else:\n",
+ " # Simulate checking local library\n",
+ " if not os.path.exists(target_path):\n",
+ " os.makedirs(target_path, exist_ok=True)\n",
+ " print(f\" ⬇️ Acquired local skill: {target_path}\")\n",
+ "\n",
+ " # C. EVALUATE\n",
+ " print(f\" ⚖️ Evaluating Skill Quality...\")\n",
+ " try:\n",
+ " report = client.evaluate(target=target_path) \n",
+ " \n",
+ " # Output format based on user request: All 5 dimensions\n",
+ " # {'safety': {'level': '...'}, 'completeness': {'level': '...'}, ...}\n",
+ " \n",
+ " dims = ['safety', 'completeness', 'executability', 'modifiability', 'cost_awareness']\n",
+ " results_str = []\n",
+ " for dim in dims:\n",
+ " level = report.get(dim, {}).get('level', 'N/A')\n",
+ " results_str.append(f\"{dim.capitalize()}: {level}\")\n",
+ " \n",
+ " print(f\" {' | '.join(results_str)}\")\n",
+ " \n",
+ " except Exception as e:\n",
+ " # Add logic to determine error cause\n",
+ " error_msg = str(e)\n",
+ " if \"API_KEY\" in error_msg or \"api_key\" in error_msg:\n",
+ " print(f\" ⚠️ Evaluation skipped: Missing OpenAI API_KEY. Please set os.environ['API_KEY'].\")\n",
+ " else:\n",
+ " print(f\" ⚠️ Evaluation failed: {error_msg}\")\n",
+ "\n",
+ " active_skills[task['step']] = skill_name\n",
+ "\n",
+ "\n",
+ "# D. ANALYZE\n",
+ "print(f\"\\n🔗 **Analyzing Skill Relationships** (SkillNet Analyzer)...\")\n",
+ "try:\n",
+ " relationships = client.analyze(skills_dir=SKILLS_LIB, save_to_file=False)\n",
+ " \n",
+ " if relationships and isinstance(relationships, list):\n",
+ " print(f\" Found {len(relationships)} dependencies between skills.\")\n",
+ " for r in relationships[:3]:\n",
+ " # Parsing: {\"source\": \"A\", \"target\": \"B\", \"type\": \"depend_on\", \"reason\": \"...\"}\n",
+ " src = r.get('source', 'Unknown')\n",
+ " rtype = r.get('type', 'related_to')\n",
+ " tgt = r.get('target', 'Unknown')\n",
+ " print(f\" - {src} --[{rtype}]--> {tgt}\")\n",
+ " else:\n",
+ " print(\" No complex dependencies detected.\")\n",
+ " \n",
+ "except Exception as e:\n",
+ " # Add logic to determine error cause\n",
+ " error_msg = str(e)\n",
+ " if \"API_KEY\" in error_msg or \"api_key\" in error_msg:\n",
+ " print(f\" ⚠️ Analysis skipped: Missing OpenAI API_KEY. Relationship inference requires LLM.\")\n",
+ " else:\n",
+ " print(f\" ⚠️ Analysis failed: {error_msg}\")\n",
+ "\n",
+ "print(f\"\\n✨ **Orchestration Complete**: {len(active_skills)} skills ready for execution.\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1a190080",
+ "metadata": {},
+ "source": [
+ "## Execution Phase 1: Data Processing\n",
+ "**Active Skill**: `cellxgene-census`\n",
+ "\n",
+ "The Agent uses the `cellxgene-census` skill to query and retrieve single-cell data.\n",
+ "*(Note: For this demo, we simulate the retrieval of a dataset containing specific marker genes)*\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "id": "4ab6495c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "▶️ **Running Skill**: [cellxgene-census]...\n",
+ "normalizing counts per cell\n",
+ " finished ({time_passed})\n",
+ "computing PCA\n",
+ " with n_comps=50\n",
+ " finished (0:00:00)\n",
+ "computing neighbors\n",
+ " using 'X_pca' with n_pcs = 50\n",
+ " finished: added to `.uns['neighbors']`\n",
+ " `.obsp['distances']`, distances for each pair of neighbors\n",
+ " `.obsp['connectivities']`, weighted adjacency matrix (0:00:00)\n",
+ "computing UMAP\n",
+ " finished: added\n",
+ " 'X_umap', UMAP coordinates (adata.obsm)\n",
+ " 'umap', UMAP parameters (adata.uns) (0:00:00)\n",
+ "running Leiden clustering\n",
+ " finished: found 3 clusters and added\n",
+ " 'leiden', the cluster labels (adata.obs, categorical) (0:00:00)\n",
+ "ranking genes\n",
+ " finished: added to `.uns['rank_genes_groups']`\n",
+ " 'names', sorted np.recarray to be indexed by group ids\n",
+ " 'scores', sorted np.recarray to be indexed by group ids\n",
+ " 'logfoldchanges', sorted np.recarray to be indexed by group ids\n",
+ " 'pvals', sorted np.recarray to be indexed by group ids\n",
+ " 'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)\n",
+ "✅ **[cellxgene-census] Completed**. Retrieved and processed dataset. Identified Target: 'EGFR'\n"
+ ]
+ }
+ ],
+ "source": [
+ "current_skill = active_skills[1] \n",
+ "print(f\"▶️ **Running Skill**: [{current_skill}]...\")\n",
+ "\n",
+ "# --- Skill Implementation: cellxgene-census ---\n",
+ "# In a fully autonomous run, the Agent would execute:\n",
+ "# > cellxgene_census.get_anndata(organism=\"Homo sapiens\", measurement_name=\"RNA\")\n",
+ "\n",
+ "# Simulating Data Retrieval & Processing\n",
+ "adata = sc.datasets.blobs(n_variables=1000, n_observations=300, n_centers=3, cluster_std=1.0, random_state=42)\n",
+ "adata.X = np.abs(adata.X) # Ensure non-negative\n",
+ "\n",
+ "# 1. Quality Control (Mock QC)\n",
+ "# FIX: Define 'mt' (mitochondrial) genes for QC metrics to avoid KeyError\n",
+ "adata.var['mt'] = np.random.choice([True, False], size=adata.n_vars, p=[0.1, 0.9])\n",
+ "\n",
+ "# Standard Scanpy Pipeline (Process)\n",
+ "sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], percent_top=None, log1p=False, inplace=True)\n",
+ "sc.pp.filter_cells(adata, min_genes=20)\n",
+ "sc.pp.filter_genes(adata, min_cells=3)\n",
+ "sc.pp.normalize_total(adata, target_sum=1e4)\n",
+ "sc.pp.log1p(adata)\n",
+ "sc.tl.pca(adata)\n",
+ "sc.pp.neighbors(adata)\n",
+ "sc.tl.umap(adata)\n",
+ "sc.tl.leiden(adata, resolution=0.5)\n",
+ "sc.tl.rank_genes_groups(adata, 'leiden', method='t-test')\n",
+ "\n",
+ "# Identify Marker\n",
+ "try:\n",
+ " top_marker_synthetic = sc.get.rank_genes_groups_df(adata, group='0').iloc[0]['names']\n",
+ "except KeyError:\n",
+ " top_marker_synthetic = sc.get.rank_genes_groups_df(adata, group=adata.obs['leiden'].cat.categories[0]).iloc[0]['names']\n",
+ "\n",
+ "target_gene_symbol = \"EGFR\" # Simulating finding EGFR in the census data\n",
+ "# --- End Skill Implementation ---\n",
+ "\n",
+ "print(f\"✅ **[{current_skill}] Completed**. Retrieved and processed dataset. Identified Target: '{target_gene_symbol}'\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "8e7c4cf4",
+ "metadata": {},
+ "source": [
+ "## Execution Phase 2: Mechanism Analysis\n",
+ "**Active Skill**: `kegg-database`\n",
+ "\n",
+ "The Agent uses `scripts/kegg_api.py` from the `kegg-database` skill to map the gene to biological pathways.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "id": "97850037",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "▶️ **Running Skill**: [kegg-database] (Input: EGFR)...\n",
+ "✅ **[kegg-database] Completed**. Mapped EGFR to 50 pathways.\n"
+ ]
+ }
+ ],
+ "source": [
+ "current_skill = active_skills[2]\n",
+ "print(f\"▶️ **Running Skill**: [{current_skill}] (Input: {target_gene_symbol})...\")\n",
+ "\n",
+ "# --- Skill Implementation: kegg-database ---\n",
+ "# Emulating logic from `active_skills_library/kegg-database/scripts/kegg_api.py`\n",
+ "def run_kegg_lookup(gene):\n",
+ " try:\n",
+ " # 1. Look up Gene ID\n",
+ " find_url = f\"http://rest.kegg.jp/find/genes/{gene}\"\n",
+ " resp = requests.get(find_url).text\n",
+ " kegg_id = resp.split('\\t')[0] if \"hsa:\" in resp else None\n",
+ " \n",
+ " if not kegg_id: return []\n",
+ " \n",
+ " # 2. Retrieve Pathways\n",
+ " link_url = f\"http://rest.kegg.jp/link/pathway/{kegg_id}\"\n",
+ " pathways = [line.split('\\t')[1] for line in requests.get(link_url).text.split('\\n') if line]\n",
+ " return pathways\n",
+ " except:\n",
+ " return []\n",
+ "\n",
+ "associated_pathways = run_kegg_lookup(target_gene_symbol)\n",
+ "# --- End Skill Implementation ---\n",
+ "\n",
+ "print(f\"✅ **[{current_skill}] Completed**. Mapped {target_gene_symbol} to {len(associated_pathways)} pathways.\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "db60ed65",
+ "metadata": {},
+ "source": [
+ "## Execution Phase 3: Target Validation\n",
+ "**Active Skill**: `gget`\n",
+ "\n",
+ "The Agent uses `gget` (Gene enhancement tool) to validate the target's associations in the Open Targets Platform.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "id": "e37294ba",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "▶️ **Running Skill**: [gget]...\n",
+ "✅ **[gget] Completed**. Validated target. Top association: non-small cell lung carcinoma\n"
+ ]
+ }
+ ],
+ "source": [
+ "current_skill = active_skills[3]\n",
+ "print(f\"▶️ **Running Skill**: [{current_skill}]...\")\n",
+ "\n",
+ "# --- Skill Implementation: gget (Open Targets Module) ---\n",
+ "# Emulating `gget.opentargets` behavior\n",
+ "def run_gget_opentargets(gene_symbol):\n",
+ " # gget typically wraps the GraphQL API for Open Targets\n",
+ " url = \"https://api.platform.opentargets.org/api/v4/graphql\"\n",
+ " \n",
+ " # 1. ID Mapping\n",
+ " search_q = \"\"\"query($q:String!){search(queryString:$q,entityNames:[\"target\"],page:{index:0,size:1}){hits{id}}}\"\"\"\n",
+ " r1 = requests.post(url, json={\"query\": search_q, \"variables\": {\"q\": gene_symbol}})\n",
+ " \n",
+ " try:\n",
+ " ensembl_id = r1.json()['data']['search']['hits'][0]['id']\n",
+ " except:\n",
+ " return None\n",
+ "\n",
+ " # 2. Association Query\n",
+ " details_q = \"\"\"query($id:String!){target(ensemblId:$id){approvedSymbol approvedName associatedDiseases(page:{index:0,size:5}){rows{disease{name} score}}}}\"\"\"\n",
+ " r2 = requests.post(url, json={\"query\": details_q, \"variables\": {\"id\": ensembl_id}})\n",
+ " \n",
+ " return r2.json().get('data', {}).get('target')\n",
+ "\n",
+ "ot_data = run_gget_opentargets(target_gene_symbol)\n",
+ "# --- End Skill Implementation ---\n",
+ "\n",
+ "if ot_data:\n",
+ " top_d = ot_data['associatedDiseases']['rows'][0]['disease']['name']\n",
+ " print(f\"✅ **[{current_skill}] Completed**. Validated target. Top association: {top_d}\")\n",
+ "else:\n",
+ " print(f\"⚠️ **[{current_skill}] Completed**. No data found.\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "0b8247ea",
+ "metadata": {},
+ "source": [
+ "## Execution Phase 4: Reporting\n",
+ "**Active Skill**: `citation-management`\n",
+ "\n",
+ "The Agent generates the final report using the collected data, utilizing the `citation-management` skill to ensure proper referencing.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "id": "870a51a7",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "▶️ **Running Skill**: [citation-management]...\n",
+ "✅ **[citation-management] Completed**. Report with citations generated.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/markdown": [
+ "\n",
+ "# Scientific Discovery Report: EGFR Analysis\n",
+ "*Generated by SkillNet AI Scientist*\n",
+ "\n",
+ "## 1. Data Processing\n",
+ "**Skill**: `cellxgene-census`\n",
+ "Using standardized single-cell analysis pipelines [Wolf et al., 2018], we identified **EGFR** as a significant marker.\n",
+ "\n",
+ "## 2. Biological Mechanism\n",
+ "**Skill**: `kegg-database`\n",
+ "Pathway enrichment analysis [Kanehisa, 2000] identified 50 associated pathways, linking EGFR to key biological processes:\n",
+ "- path:hsa01521\n",
+ "- path:hsa01522\n",
+ "- path:hsa03272\n",
+ "\n",
+ "## 3. Therapeutic Validation\n",
+ "**Skill**: `gget`\n",
+ "Cross-referencing with clinical databases [Open Targets, 2024] confirms therapeutic relevance for:\n",
+ "- non-small cell lung carcinoma\n",
+ "- lung adenocarcinoma\n",
+ "- cancer\n",
+ "\n",
+ "## 4. References (Managed by citation-management)\n",
+ "1. Wolf, F. A., et al. (2018). Scanpy: large-scale single-cell gene expression data analysis. Genome biology.\n",
+ "2. Kanehisa, M. & Goto, S. (2000). KEGG: kyoto encyclopedia of genes and genomes. Nucleic acids research.\n",
+ "3. Open Targets Platform (2024). version 24.03.\n",
+ " "
+ ],
+ "text/plain": [
+ "<IPython.core.display.Markdown object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "current_skill = active_skills[4]\n",
+ "print(f\"▶️ **Running Skill**: [{current_skill}]...\")\n",
+ "\n",
+ "# --- Skill Implementation: citation-management ---\n",
+ "# Simulating `scripts/format_bibtex.py` and `scripts/validate_citations.py` from the skill\n",
+ "def format_citation(source, year, title):\n",
+ " return f\"[{source}, {year}]\"\n",
+ "\n",
+ "def generate_report_with_citations(gene, pathways, ot_info):\n",
+ " # Mock Citations\n",
+ " ref_scanpy = format_citation(\"Wolf et al.\", 2018, \"Scanpy\")\n",
+ " ref_kegg = format_citation(\"Kanehisa\", 2000, \"KEGG\")\n",
+ " ref_ot = format_citation(\"Open Targets\", 2024, \"Platform\")\n",
+ " \n",
+ " disease_list = [d['disease']['name'] for d in ot_info['associatedDiseases']['rows'][:3]] if ot_info else []\n",
+ " \n",
+ " report_md = f\"\"\"\n",
+ "# Scientific Discovery Report: {gene} Analysis\n",
+ "*Generated by SkillNet AI Scientist*\n",
+ "\n",
+ "## 1. Data Processing\n",
+ "**Skill**: `{active_skills[1]}`\n",
+ "Using standardized single-cell analysis pipelines {ref_scanpy}, we identified **{gene}** as a significant marker.\n",
+ "\n",
+ "## 2. Biological Mechanism\n",
+ "**Skill**: `{active_skills[2]}`\n",
+ "Pathway enrichment analysis {ref_kegg} identified {len(pathways)} associated pathways, linking {gene} to key biological processes:\n",
+ "{chr(10).join([f'- {p}' for p in pathways[:3]])}\n",
+ "\n",
+ "## 3. Therapeutic Validation\n",
+ "**Skill**: `{active_skills[3]}`\n",
+ "Cross-referencing with clinical databases {ref_ot} confirms therapeutic relevance for:\n",
+ "{chr(10).join([f'- {d}' for d in disease_list])}\n",
+ "\n",
+ "## 4. References (Managed by {active_skills[4]})\n",
+ "1. Wolf, F. A., et al. (2018). Scanpy: large-scale single-cell gene expression data analysis. Genome biology.\n",
+ "2. Kanehisa, M. & Goto, S. (2000). KEGG: kyoto encyclopedia of genes and genomes. Nucleic acids research.\n",
+ "3. Open Targets Platform (2024). version 24.03.\n",
+ " \"\"\"\n",
+ " return report_md\n",
+ "\n",
+ "report_content = generate_report_with_citations(target_gene_symbol, associated_pathways, ot_data)\n",
+ "# --- End Skill Implementation ---\n",
+ "\n",
+ "print(f\"✅ **[{current_skill}] Completed**. Report with citations generated.\")\n",
+ "display(Markdown(report_content))\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "skillnet",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.19"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/skillnet-ai/examples/skillnet_usage_demo.ipynb b/skillnet-ai/examples/skillnet_usage_demo.ipynb
new file mode 100644
index 0000000..85f5eb1
--- /dev/null
+++ b/skillnet-ai/examples/skillnet_usage_demo.ipynb
@@ -0,0 +1,379 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "958ee3e3",
+ "metadata": {},
+ "source": [
+ "# SkillNet AI SDK Usage Tutorial\n",
+ "\n",
+ "This notebook demonstrates the process of using the `skillnet-ai` Python SDK in a general scenario.\n",
+ "Key features include:\n",
+ "1. **Search**: Find skills using keyword or semantic search\n",
+ "2. **Download**: Install skills from GitHub\n",
+ "3. **Create**: Create new skills from conversation logs, documents, or prompts\n",
+ "4. **Evaluate**: Evaluate skill quality across multiple dimensions\n",
+ "5. **Analyze**: Analyze skill relationships in the local skill library\n",
+ "\n",
+ "## 0. Installation and Environment Configuration"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "51a0220c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Install skillnet-ai\n",
+ "%pip install skillnet-ai"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "748acf46",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "SkillNetClient initialized successfully.\n"
+ ]
+ }
+ ],
+ "source": [
+ "import os\n",
+ "import sys\n",
+ "from skillnet_ai import SkillNetClient\n",
+ "\n",
+ "# Set API KEY (used for Create, Evaluate, and Analyze functions)\n",
+ "# Please replace with your actual API Key (e.g., OpenAI key)\n",
+ "os.environ[\"API_KEY\"] = \"your-api-key-here\" \n",
+ "os.environ[\"BASE_URL\"] = \"https://api.openai.com/v1\" # Optional: Set custom LLM Base URL\n",
+ "\n",
+ "# Initialize Client\n",
+ "# Note: Without an API Key, some functions (like Create, Evaluate) may not work, but Search usually works\n",
+ "client = SkillNetClient(\n",
+ " api_key=os.getenv(\"API_KEY\"),\n",
+ " base_url=os.getenv(\"BASE_URL\")\n",
+ " # github_token=\"ghp-...\" # Optional: For accessing private repos or increasing download rate limits\n",
+ ")\n",
+ "\n",
+ "print(\"SkillNetClient initialized successfully.\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7f5c5567",
+ "metadata": {},
+ "source": [
+ "## 1. Search Skills (Search)\n",
+ "\n",
+ "SkillNet supports two search modes:\n",
+ "* **Keyword**: Traditional fuzzy keyword matching\n",
+ "* **Vector**: Semantic vector retrieval"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "cb8079fd",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--- Keyword Search: 'pdf' ---\n",
+ "Name: biorxiv-database (Stars: 17616)\n",
+ "Name: treatment-plans (Stars: 16346)\n",
+ "Name: clinical-decision-support (Stars: 16091)\n",
+ "Name: scientific-visualization (Stars: 16082)\n",
+ "Name: literature-review (Stars: 16059)\n",
+ "Name: pdf (Stars: 15845)\n",
+ "Name: plotly (Stars: 15805)\n",
+ "Name: pdf-processing-pro (Stars: 15803)\n",
+ "Name: pdf-processing (Stars: 15439)\n",
+ "Name: pdf (Stars: 13720)\n",
+ "Name: pdf-processing (Stars: 9170)\n",
+ "Name: pdf-extractor (Stars: 8003)\n",
+ "Name: biorxiv-database (Stars: 6637)\n",
+ "Name: treatment-plans (Stars: 6170)\n",
+ "Name: clinical-decision-support (Stars: 6069)\n",
+ "Name: literature-review (Stars: 6041)\n",
+ "Name: etetoolkit (Stars: 5879)\n",
+ "Name: paper-2-web (Stars: 5867)\n",
+ "Name: pptx-posters (Stars: 5810)\n",
+ "Name: markitdown (Stars: 5761)\n",
+ "\n",
+ "--- Vector Search: 'Help me analyze financial PDF reports' ---\n",
+ "Found: financial-document-parser (Stars: 95)\n",
+ "URL: https://github.com/Microck/ordinary-claude-skills/blob/76c86cb21a36c0cc10c213d991aa1c9498b363c8/skills_categorized/payment/financial-document-parser\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 1. Standard Keywords Match\n",
+ "print(\"--- Keyword Search: 'pdf' ---\")\n",
+ "results = client.search(q=\"pdf\")\n",
+ "\n",
+ "if results:\n",
+ " for skill in results:\n",
+ " print(f\"Name: {skill.skill_name} (Stars: {skill.stars})\")\n",
+ "\n",
+ "# 2. Semantic Search\n",
+ "print(\"\\n--- Vector Search: 'Help me analyze financial PDF reports' ---\")\n",
+ "results = client.search(q=\"Help me analyze financial PDF reports\", mode=\"vector\")\n",
+ "\n",
+ "if results:\n",
+ " top_skill = results[0]\n",
+ " print(f\"Found: {top_skill.skill_name} (Stars: {top_skill.stars})\")\n",
+ " print(f\"URL: {top_skill.skill_url}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d5724546",
+ "metadata": {},
+ "source": [
+ "## 2. Download Skills (Download)\n",
+ "\n",
+ "You can download skills directly from a GitHub URL to a local directory."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "c31f3c93",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Downloading skill from https://github.com/anthropics/skills/tree/main/skills/skill-creator...\n",
+ "✅ Skill successfully installed at: e:\\科研\\SkillNet相关\\SkillNet\\skillnet-ai\\examples\\my_downloaded_skills\\skill-creator\n",
+ "Files in directory: ['LICENSE.txt', 'references', 'scripts', 'SKILL.md']\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Define download target directory\n",
+ "download_dir = \"./my_downloaded_skills\"\n",
+ "\n",
+ "# Example: Download anthropics' skill-creator skill\n",
+ "# Note: This requires network access to GitHub\n",
+ "skill_url = \"https://github.com/anthropics/skills/tree/main/skills/skill-creator\"\n",
+ "\n",
+ "try:\n",
+ " print(f\"Downloading skill from {skill_url}...\")\n",
+ " local_path = client.download(url=skill_url, target_dir=download_dir)\n",
+ " print(f\"✅ Skill successfully installed at: {local_path}\")\n",
+ " \n",
+ " # View downloaded files\n",
+ " if os.path.exists(local_path):\n",
+ " print(\"Files in directory:\", os.listdir(local_path))\n",
+ "except Exception as e:\n",
+ " print(f\"❌ Download failed: {e}\")\n",
+ " # Note: If network is unreachable, this step may fail, but won't affect later demonstrations"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "6bb6bd05",
+ "metadata": {},
+ "source": [
+ "## 3. Create Skills (Create)\n",
+ "\n",
+ "Automatically generate standardized skill packages using LLMs. Supports various sources:\n",
+ "* Conversation Trajectory/Logs\n",
+ "* GitHub Repository\n",
+ "* Office Documents (PDF/Word/PPT)\n",
+ "* Natural Language Prompt"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "e8e86da0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--- Creating skill from trajectory ---\n",
+ "Created 1 skills:\n",
+ "- ./my_created_skills\\file-format-renamer\n",
+ "\n",
+ "--- Creating skill from prompt ---\n",
+ "- ./my_created_skills\\celsius-to-fahrenheit-converter\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Set output directory for generated skills\n",
+ "created_skills_dir = \"./my_created_skills\"\n",
+ "\n",
+ "# Example 1: Create from Conversation Log (Trajectory)\n",
+ "trajectory_log = \"\"\"\n",
+ "User: I need to rename all .jpg files in this folder to .png.\n",
+ "Agent: I will write a python script to iterate through the folder...\n",
+ "Agent: Script executed. Renamed 5 files.\n",
+ "\"\"\"\n",
+ "\n",
+ "print(\"--- Creating skill from trajectory ---\")\n",
+ "try:\n",
+ " # This step requires a valid API_KEY\n",
+ " created_paths = client.create(\n",
+ " trajectory_content=trajectory_log, \n",
+ " output_dir=created_skills_dir,\n",
+ " model=\"gpt-4o\" # Specify model\n",
+ " )\n",
+ " print(f\"Created {len(created_paths)} skills:\")\n",
+ " for path in created_paths:\n",
+ " print(f\"- {path}\")\n",
+ "except Exception as e:\n",
+ " print(f\"Creation failed (check API Key): {e}\")\n",
+ "\n",
+ "# Example 2: Create directly from Prompt\n",
+ "print(\"\\n--- Creating skill from prompt ---\")\n",
+ "try:\n",
+ " created_paths_prompt = client.create(\n",
+ " prompt=\"Create a tool that converts degrees Celsius to Fahrenheit\",\n",
+ " output_dir=created_skills_dir\n",
+ " )\n",
+ " for path in created_paths_prompt:\n",
+ " print(f\"- {path}\")\n",
+ "except Exception as e:\n",
+ " print(f\"Creation failed: {e}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "2a79d93b",
+ "metadata": {},
+ "source": [
+ "## 4. Evaluate Skills (Evaluate)\n",
+ "\n",
+ "Evaluate skill quality across multiple dimensions (Safety, Completeness, Executability, etc.)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "id": "e676694c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--- Evaluating skill at: ./my_downloaded_skills\\skill-creator ---\n",
+ "Evaluation Result:\n",
+ "{'safety': {'level': 'Good', 'reason': 'The skill focuses on creating modular, reusable components and explicitly avoids destructive or risky actions, with no dangerous tools or operations mentioned.'}, 'completeness': {'level': 'Good', 'reason': 'The SKILL.md provides detailed guidance on structuring skills, including workflows, resource types, and examples, ensuring clarity on how to create and use skills effectively.'}, 'executability': {'level': 'Good', 'reason': 'The skill is instruction-based and provides actionable steps and patterns for creating and organizing skills, which can be executed using typical LLM tools without ambiguity.'}, 'modifiability': {'level': 'Good', 'reason': 'The skill emphasizes modularity and progressive disclosure, making it easy to adapt or extend with additional resources or workflows as needed.'}, 'cost_awareness': {'level': 'Good', 'reason': 'The skill explicitly emphasizes minimizing context window usage and token costs, demonstrating strong awareness of operational efficiency.'}}\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Evaluate the skill just downloaded or created\n",
+ "# Here we try to evaluate a skill in the download directory (if it exists)\n",
+ "import glob\n",
+ "\n",
+ "# Find an existing skill path to evaluate\n",
+ "target_skill = None\n",
+ "if os.path.exists(download_dir) and os.listdir(download_dir):\n",
+ " # Get the first subdirectory\n",
+ " subdirs = [f.path for f in os.scandir(download_dir) if f.is_dir()]\n",
+ " if subdirs:\n",
+ " target_skill = subdirs[0]\n",
+ "\n",
+ "if target_skill:\n",
+ " print(f\"--- Evaluating skill at: {target_skill} ---\")\n",
+ " try:\n",
+ " # This step requires a valid API_KEY\n",
+ " eval_result = client.evaluate(target=target_skill)\n",
+ " print(\"Evaluation Result:\")\n",
+ " print(eval_result)\n",
+ " except Exception as e:\n",
+ " print(f\"Evaluation failed (check API Key): {e}\")\n",
+ "else:\n",
+ " print(\"No local skill found to evaluate. Please download or create one first.\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "fe2e1e53",
+ "metadata": {},
+ "source": [
+ "## 5. Skill Relationship Analysis (Analyze)\n",
+ "\n",
+ "Analyze relationships between multiple skills in a directory (e.g., dependency, composition, similarity)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "id": "8f1513bb",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--- Analyzing relationships in: ./my_created_skills ---\n",
+ "\n",
+ "Identified Relationships:\n",
+ "file-extension-renamer --[belong_to]--> file-renamer-tool\n",
+ "file-renamer-tool --[similar_to]--> file-extension-renamer\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Analyze the directory of created skills\n",
+ "analyze_target_dir = created_skills_dir\n",
+ "\n",
+ "if os.path.exists(analyze_target_dir) and len(os.listdir(analyze_target_dir)) > 0:\n",
+ " print(f\"--- Analyzing relationships in: {analyze_target_dir} ---\")\n",
+ " try:\n",
+ " # This step requires a valid API_KEY, analyzes all skills in the directory\n",
+ " relationships = client.analyze(skills_dir=analyze_target_dir)\n",
+ " \n",
+ " print(\"\\nIdentified Relationships:\")\n",
+ " if relationships:\n",
+ " for rel in relationships:\n",
+ " print(f\"{rel['source']} --[{rel['type']}]--> {rel['target']}\")\n",
+ " else:\n",
+ " print(\"No significant relationships found between these skills.\")\n",
+ " \n",
+ " except Exception as e:\n",
+ " print(f\"Analysis failed (check API Key): {e}\")\n",
+ "else:\n",
+ " print(\"No skills directory found to analyze.\")"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "skillnet",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.19"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}